Application of Big Medical Data in Precision Medicine

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Biology biology	4.2	4.0	2012	18.7 Days	CHF 2700
Cancers cancers	5.2	7.4	2009	17.9 Days	CHF 2900

23 pages, 14741 KiB

Open AccessArticle

Development and Experimental Validation of a Novel Prognostic Signature for Gastric Cancer

by Chengcheng Liu, Yuying Huo, Yansong Zhang, Fumei Yin, Taoyu Chen, Zhenyi Wang, Juntao Gao, Peng Jin, Xiangyu Li, Minglei Shi and Michael Q. Zhang

Cancers 2023, 15(5), 1610; https://doi.org/10.3390/cancers15051610 - 05 Mar 2023

Viewed by 1789

Abstract

Background: Gastric cancer is a malignant tumor with high morbidity and mortality. Therefore, the accurate recognition of prognostic molecular markers is the key to improving treatment efficacy and prognosis. Methods: In this study, we developed a stable and robust signature through a series [...] Read more.

Background: Gastric cancer is a malignant tumor with high morbidity and mortality. Therefore, the accurate recognition of prognostic molecular markers is the key to improving treatment efficacy and prognosis. Methods: In this study, we developed a stable and robust signature through a series of processes using machine-learning approaches. This PRGS was further experimentally validated in clinical samples and a gastric cancer cell line. Results: The PRGS is an independent risk factor for overall survival that performs reliably and has a robust utility. Notably, PRGS proteins promote cancer cell proliferation by regulating the cell cycle. Besides, the high-risk group displayed a lower tumor purity, higher immune cell infiltration, and lower oncogenic mutation than the low-PRGS group. Conclusions: This PRGS could be a powerful and robust tool to improve clinical outcomes for individual gastric cancer patients. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

16 pages, 2041 KiB

Open AccessArticle

IGFBP1^hiWNT3A^lo Subtype in Esophageal Cancer Predicts Response and Prolonged Survival with PD-(L)1 Inhibitor

by Meichen Liu, Wanpu Yan, Dongbo Chen, Jiancheng Luo, Liang Dai, Hongsong Chen and Ke-Neng Chen

Biology 2022, 11(11), 1575; https://doi.org/10.3390/biology11111575 - 27 Oct 2022

Cited by 1 | Viewed by 1444

Abstract

PD-(L)1 inhibitor could improve the survival of locally advanced esophageal cancer (ESCA) patients, but we cannot tailor the treatment to common biomarkers. WNT signaling activation was associated with primary resistance to immunotherapy. In this study, we used our two clinical cohorts (BJCH n [...] Read more.

PD-(L)1 inhibitor could improve the survival of locally advanced esophageal cancer (ESCA) patients, but we cannot tailor the treatment to common biomarkers. WNT signaling activation was associated with primary resistance to immunotherapy. In this study, we used our two clinical cohorts (BJCH n = 95, BJIM n = 21) and three public cohorts to evaluate and verify a new immunotherapeutic biomarker based on WNT signaling in ESCA patients. Our findings showed that WNT signaling-related genes stratified TCGA patients into Cluster 1, 2, and 3, among which, Cluster 3 had the worst prognosis. The most up- and down-regulated genes in Cluster 3 were IGFBP1 and WNT3A. Further analysis validated that IGFBP1^hiWNT3A^lo ESCA patients had significantly poor RFS and OS in the TCGA and BJCH cohorts. Interestingly, IGFBP1^hiWNT3A^lo patients had a good response and prognosis with immunotherapy in three independent cohorts, exhibiting better predictive value than PD-L1 expression (signature AUC = 0.750; PD-L1 AUC = 0.571). Moreover, IGFBP1^hiWNT3A^lo patients may benefit more from immunotherapy than standard treatment (p = 0.026). Immune cell infiltration analysis revealed a significant increase in DC infiltration in IGFBP1^hiWNT3A^lo patients post-immunotherapy (p = 0.022), which may enhance immune response. The IGFBP1^hiWNT3A^lo signature could predict patients who benefited from PD-(L)1 inhibitor treatment and may serve as a biomarker in ESCA. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

15 pages, 4181 KiB

Open AccessArticle

Genomic Instability in Cerebrospinal Fluid Cell-Free DNA Predicts Poor Prognosis in Solid Tumor Patients with Meningeal Metastasis

by Peng Wang, Qiaoling Zhang, Lei Han, Yanan Cheng, Zengfeng Sun, Qiang Yin, Zhen Zhang and Jinpu Yu

Cancers 2022, 14(20), 5028; https://doi.org/10.3390/cancers14205028 - 14 Oct 2022

Cited by 1 | Viewed by 1358

Abstract

Genomic instability (GI), which leads to the accumulation of DNA loss, gain, and rearrangement, is a hallmark of many cancers such as lung cancer, breast cancer, and colon cancer. However, the clinical significance of GI has not been systematically studied in the meningeal [...] Read more.

Genomic instability (GI), which leads to the accumulation of DNA loss, gain, and rearrangement, is a hallmark of many cancers such as lung cancer, breast cancer, and colon cancer. However, the clinical significance of GI has not been systematically studied in the meningeal metastasis (MM) of solid tumors. Here, we collected both cerebrospinal fluid (CSF) and plasma samples from 56 solid tumor MM patients and isolated cell-free ctDNA to investigate the GI status using a next-generation sequencing-based comprehensive genomic profiling of 543 cancer-related genes. According to the unfiltered heterozygous mutation data-derived GI score, we found that 37 (66.1%) cases of CSF and 3 cases (6%) of plasma had a high GI status, which was further validated by low-depth whole-genome sequencing analysis. It is demonstrated that a high GI status in CSF was associated with poor prognosis, high intracranial pressure, and low Karnofsky performance status scores. More notably, a high GI status was an independent poor prognostic factor of poor MM-free survival and overall survival in lung adenocarcinoma MM patients. Furthermore, high occurrences of the co-mutation of TP53/EGFR, TP53/RB1, TP53/ERBB2, and TP53/KMT2C were found in MM patients with a high GI status. In summary, the GI status in CSF ctDNA might be a valuable prognostic indicator in solid tumor patients with MM. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

15 pages, 3071 KiB

Open AccessArticle

The C-Terminal Repeat Units of SpaA Mediate Adhesion of Erysipelothrix rhusiopathiae to Host Cells and Regulate Its Virulence

by Chao Wu, Zhewen Zhang, Chao Kang, Qiang Zhang, Weifeng Zhu, Yadong Zhang, Hao Zhang, Jingfa Xiao and Meilin Jin

Biology 2022, 11(7), 1010; https://doi.org/10.3390/biology11071010 - 05 Jul 2022

Cited by 1 | Viewed by 1529

Abstract

Erysipelothrix rhusiopathiae is a causative agent of erysipelas in animals and erysipeloid in humans. However, current information regarding E. rhusiopathiae pathogenesis remains limited. Previously, we identified two E. rhusiopathiae strains, SE38 and G4T10, which were virulent and avirulent in pigs, respectively. Here, to [...] Read more.

Erysipelothrix rhusiopathiae is a causative agent of erysipelas in animals and erysipeloid in humans. However, current information regarding E. rhusiopathiae pathogenesis remains limited. Previously, we identified two E. rhusiopathiae strains, SE38 and G4T10, which were virulent and avirulent in pigs, respectively. Here, to further study the pathogenic mechanism of E. rhusiopathiae, we sequenced and assembled the genomes of strains SE38 and G4T10, and performed a comparative genomic analysis to identify differences or mutations in virulence-associated genes. Next, we comparatively analyzed 25 E. rhusiopathiae virulence-associated genes in SE38 and G4T10. Compared with that of SE38, the spaA gene of the G4T10 strain lacked 120 bp, encoding repeat units at the C-terminal of SpaA. To examine whether these deletions or splits influence E. rhusiopathiae virulence, these 120 bp were successfully deleted from the spaA gene in strain SE38 by homologous recombination. The mutant strain ΔspaA displayed attenuated virulence in mice and decreased adhesion to porcine iliac artery endothelial cells, which was also observed using the corresponding mutant protein SpaA’. Our results demonstrate that SpaA-mediated adhesion between E. rhusiopathiae and host cells is dependent on its C-terminal repeat units. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

12 pages, 865 KiB

Open AccessArticle

Assessing Ethnic Inequalities in Diagnostic Interval of Common Cancers: A Population-Based UK Cohort Study

by Tanimola Martins, Gary Abel, Obioha C. Ukoumunne, Sarah Price, Georgios Lyratzopoulos, Frank Chinegwundoh and William Hamilton

Cancers 2022, 14(13), 3085; https://doi.org/10.3390/cancers14133085 - 23 Jun 2022

Cited by 5 | Viewed by 4600

Abstract

Background: This study investigated ethnic differences in diagnostic interval (DI)—the period between initial primary care presentation and diagnosis. Methods: We analysed the primary care-linked data of patients who reported features of seven cancers (breast, lung, prostate, colorectal, oesophagogastric, myeloma, and ovarian) one year [...] Read more.

Background: This study investigated ethnic differences in diagnostic interval (DI)—the period between initial primary care presentation and diagnosis. Methods: We analysed the primary care-linked data of patients who reported features of seven cancers (breast, lung, prostate, colorectal, oesophagogastric, myeloma, and ovarian) one year before diagnosis. Accelerated failure time (AFT) models investigated the association between DI and ethnicity, adjusting for age, sex, deprivation, and morbidity. Results: Of 126,627 eligible participants, 92.1% were White, 1.99% Black, 1.71% Asian, 1.83% Mixed, and 2.36% were of Other ethnic backgrounds. Considering all cancer sites combined, the median (interquartile range) DI was 55 (20–175) days, longest in lung [127, (42–265) days], and shortest in breast cancer [13 (13, 8–18) days]. DI for the Black and Asian groups was 10% (AFT ratio, 95%CI 1.10, 1.05–1.14) and 16% (1.16, 1.10–1.22), respectively, longer than for the White group. Site-specific analyses revealed evidence of longer DI in Asian and Black patients with prostate, colorectal, and oesophagogastric cancer, plus Black patients with breast cancer and myeloma, and the Mixed group with lung cancer compared with White patients. DI was shorter for the Other group with lung, prostate, myeloma, and oesophagogastric cancer than the White group. Conclusion: We found limited and inconsistent evidence of ethnic differences in DI among patients who reported cancer features in primary care before diagnosis. Our findings suggest that inequalities in diagnostic intervals, where present, are unlikely to be the sole explanation for ethnic variations in cancer outcomes. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

16 pages, 4978 KiB

Open AccessArticle

A Pragmatic Machine Learning Approach to Quantify Tumor-Infiltrating Lymphocytes in Whole Slide Images

by Nikita Shvetsov, Morten Grønnesby, Edvard Pedersen, Kajsa Møllersen, Lill-Tove Rasmussen Busund, Ruth Schwienbacher, Lars Ailo Bongo and Thomas Karsten Kilvaer

Cancers 2022, 14(12), 2974; https://doi.org/10.3390/cancers14122974 - 16 Jun 2022

Cited by 7 | Viewed by 2909

Abstract

Increased levels of tumor-infiltrating lymphocytes (TILs) indicate favorable outcomes in many types of cancer. The manual quantification of immune cells is inaccurate and time-consuming for pathologists. Our aim is to leverage a computational solution to automatically quantify TILs in standard diagnostic hematoxylin and [...] Read more.

Increased levels of tumor-infiltrating lymphocytes (TILs) indicate favorable outcomes in many types of cancer. The manual quantification of immune cells is inaccurate and time-consuming for pathologists. Our aim is to leverage a computational solution to automatically quantify TILs in standard diagnostic hematoxylin and eosin-stained sections (H&E slides) from lung cancer patients. Our approach is to transfer an open-source machine learning method for the segmentation and classification of nuclei in H&E slides trained on public data to TIL quantification without manual labeling of the data. Our results show that the resulting TIL quantification correlates to the patient prognosis and compares favorably to the current state-of-the-art method for immune cell detection in non-small cell lung cancer (current standard CD8 cells in DAB-stained TMAs HR 0.34, 95% CI 0.17–0.68 vs. TILs in HE WSIs: HoVer-Net PanNuke Aug Model HR 0.30, 95% CI 0.15–0.60 and HoVer-Net MoNuSAC Aug model HR 0.27, 95% CI 0.14–0.53). Our approach bridges the gap between machine learning research, translational clinical research and clinical implementation. However, further validation is warranted before implementation in a clinical setting. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

14 pages, 278 KiB

Open AccessArticle

The Insignificant Correlation between Androgen Deprivation Therapy and Incidence of Dementia Using an Extension Survival Cox Hazard Model and Propensity-Score Matching Analysis in a Retrospective, Population-Based Prostate Cancer Registry

by Young Ae Kim, Su-Hyun Kim, Jae Young Joung, Min Soo Yang, Joung Hwan Back and Sung Han Kim

Cancers 2022, 14(11), 2705; https://doi.org/10.3390/cancers14112705 - 30 May 2022

Cited by 3 | Viewed by 1652

Abstract

This study aims to evaluate the effect of androgen-deprivation therapy (ADT) on the incidence of dementia, after considering the time-dependent survival in patients with prostate cancer (PC) using a Korean population-based cancer registry database. After excluding patients with cerebrovascular disease and dementia before [...] Read more.

This study aims to evaluate the effect of androgen-deprivation therapy (ADT) on the incidence of dementia, after considering the time-dependent survival in patients with prostate cancer (PC) using a Korean population-based cancer registry database. After excluding patients with cerebrovascular disease and dementia before or within the 3-month-ADT and those with surgical castration, 9880 (19.3%) patients were matched into ADT and non-ADT groups using propensity-score matching (PSM) among 51,206 patients registered between 2006 and 2013. To define the significant relationship between ADT duration and the incidence of dementia, the extension Cox proportional hazard model was used with p-values < 0.05 regarded as statistically significant. The mean age and survival time were 67.3 years and 4.33 (standard deviation [SD] 2.16) years, respectively. A total of 2945 (9.3%) patients developed dementia during the study period, including Parkinson’s (11.0%), Alzheimer’s (42.6%), vascular (18.2%), and other types of dementia (28.2%). Despite PSM, the PC-treatment subtypes, survival rate, and incidence of dementia significantly differed between the ADT and non-ADT groups (p < 0.05), whereas the rate of each dementia subtype did not significantly differ (p = 0.069). A multivariate analysis for dementia incidence showed no significance of ADT type or use duration among patients with PC (p > 0.05), whereas old age, obesity, regional SEER stage, a history of cerebrovascular disease, and a high Charlson Comorbidity Index were significant factors for dementia (p < 0.05). Insignificant correlation was observed between ADT and the incidence of dementia based on the extension survival model with PSM among patients with PC. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

17 pages, 2080 KiB

Open AccessArticle

External Validation of Two Established Clinical Risk Scores Predicting Outcome after Local Treatment of Colorectal Liver Metastases in a Nationwide Cohort

by Karen Bolhuis, G. Emerens Wensink, Marloes A. G. Elferink, Marinde J. G. Bond, Willemieke P. M. Dijksterhuis, Remond J. A. Fijneman, Onno W. Kranenburg, Inne H. M. Borel Rinkes, Miriam Koopman, Rutger-Jan Swijnenburg, Geraldine R. Vink, Jeroen Hagendoorn, Cornelis J. A. Punt, Sjoerd G. Elias and Jeanine M. L. Roodhart

Cancers 2022, 14(10), 2356; https://doi.org/10.3390/cancers14102356 - 10 May 2022

Cited by 4 | Viewed by 2101

Abstract

Optimized surgical techniques and systemic therapy have increased the number of patients with colorectal liver metastases (CRLM) eligible for local treatment. To increase postoperative survival, we need to stratify patients to customize therapy. Most clinical risk scores (CRSs) which predict prognosis after CRLM [...] Read more.

Optimized surgical techniques and systemic therapy have increased the number of patients with colorectal liver metastases (CRLM) eligible for local treatment. To increase postoperative survival, we need to stratify patients to customize therapy. Most clinical risk scores (CRSs) which predict prognosis after CRLM resection were based on the outcome of studies in specialized centers, and this may hamper the generalizability of these CRSs in unselected populations and underrepresented subgroups. We aimed to externally validate two CRSs in a population-based cohort of patients with CRLM. A total of 1105 patients with local treatment of CRLM, diagnosed in 2015/2016, were included from a nationwide population-based database. Survival outcomes were analyzed. The Fong and more recently developed GAME CRS were externally validated, including in pre-specified subgroups (≤70/>70 years and with/without perioperative systemic therapy). The three-year DFS was 22.8%, and the median OS in the GAME risk groups (high/moderate/low) was 32.4, 46.7, and 68.1 months, respectively (p < 0.005). The median OS for patients with versus without perioperative therapy was 47.6 (95%CI [39.8, 56.2]) and 54.9 months (95%CI [48.8, 63.7]), respectively (p = 0.152), and for below/above 70 years, it was 54.9 (95%CI [49.3–64.1]) and 44.2 months (95%CI [37.1–54.3]), respectively (p < 0.005). The discriminative ability for OS of Fong CRS was 0.577 (95%CI [0.554, 0.601]), and for GAME, it was 0.596 (95%CI [0.572, 0.621]), and was comparable in the subgroups. In conclusion, both CRSs showed predictive ability in a population-based cohort and in predefined subgroups. However, the limited discriminative ability of these CRSs results in insufficient preoperative risk stratification for clinical decision-making. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Graphical abstract

20 pages, 1607 KiB

Open AccessReview

Analytical Considerations of Large-Scale Aptamer-Based Datasets for Translational Applications

by Will Jiang, Jennifer C. Jones, Uma Shankavaram, Mary Sproull, Kevin Camphausen and Andra V. Krauze

Cancers 2022, 14(9), 2227; https://doi.org/10.3390/cancers14092227 - 29 Apr 2022

Cited by 3 | Viewed by 3060

Abstract

The development and advancement of aptamer technology has opened a new realm of possibilities for unlocking the biocomplexity available within proteomics. With ultra-high-throughput and multiplexing, alongside remarkable specificity and sensitivity, aptamers could represent a powerful tool in disease-specific research, such as supporting the [...] Read more.

The development and advancement of aptamer technology has opened a new realm of possibilities for unlocking the biocomplexity available within proteomics. With ultra-high-throughput and multiplexing, alongside remarkable specificity and sensitivity, aptamers could represent a powerful tool in disease-specific research, such as supporting the discovery and validation of clinically relevant biomarkers. One of the fundamental challenges underlying past and current proteomic technology has been the difficulty of translating proteomic datasets into standards of practice. Aptamers provide the capacity to generate single panels that span over 7000 different proteins from a singular sample. However, as a recent technology, they also present unique challenges, as the field of translational aptamer-based proteomics still lacks a standardizing methodology for analyzing these large datasets and the novel considerations that must be made in response to the differentiation amongst current proteomic platforms and aptamers. We address these analytical considerations with respect to surveying initial data, deploying proper statistical methodologies to identify differential protein expressions, and applying datasets to discover multimarker and pathway-level findings. Additionally, we present aptamer datasets within the multi-omics landscape by exploring the intersectionality of aptamer-based proteomics amongst genomics, transcriptomics, and metabolomics, alongside pre-existing proteomic platforms. Understanding the broader applications of aptamer datasets will substantially enhance current efforts to generate translatable findings for the clinic. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

14 pages, 1211 KiB

Open AccessArticle

The Significance of Systemic Inflammation Markers in Intrahepatic Recurrence of Early-Stage Hepatocellular Carcinoma after Curative Treatment

by Bong Kyung Bae, Hee Chul Park, Gyu Sang Yoo, Moon Seok Choi, Joo Hyun Oh and Jeong Il Yu

Cancers 2022, 14(9), 2081; https://doi.org/10.3390/cancers14092081 - 21 Apr 2022

Cited by 6 | Viewed by 1578

Abstract

Systemic inflammatory markers (SIMs) are known to be associated with carcinogenesis and prognosis of hepatocellular carcinoma (HCC). We evaluated the significance of SIMs in intrahepatic recurrence (IHR) of early-stage HCC after curative treatment. This study was performed using prospectively collected registry data of [...] Read more.

Systemic inflammatory markers (SIMs) are known to be associated with carcinogenesis and prognosis of hepatocellular carcinoma (HCC). We evaluated the significance of SIMs in intrahepatic recurrence (IHR) of early-stage HCC after curative treatment. This study was performed using prospectively collected registry data of newly diagnosed, previously untreated HCC between 2005 and 2017 at a single institution. Inclusion criteria were patients with Barcelona Clinic Liver Cancer stage 0 or A, who underwent curative treatment. Pre-treatment and post-treatment values of platelet, neutrophil, lymphocyte, monocyte, neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), and lymphocyte/monocyte ratio (LMR) were analyzed with previously well-known risk factors of HCC to identify factors associated with IHR-free survival (IHRFS), early IHR, and late IHR. Of 4076 patients, 2142 patients (52.6%) experienced IHR, with early IHR in 1018 patients (25.0%) and late IHR in 1124 patients (27.6%). Pre-treatment platelet count and PLR and post-treatment worsening of NLR, PLR, and LMR were independently associated with IHRFS. Pre-treatment platelet count and post-treatment worsening of NLR, PLR, and LMR were significantly related to both early and late IHR. Pre-treatment values and post-treatment changes in SIMs were significant factors of IHR in early-stage HCC, independent of previously well-known risk factors of HCC. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

11 pages, 4460 KiB

Open AccessArticle

Biopsy Ratio of Suspected to Confirmed Sarcoma Diagnosis

by Nasian Mosku, Philip Heesen, Gabriela Studer, Beata Bode, Vito Spataro, Natalie D. Klass, Lars Kern, Mario F. Scaglioni and Bruno Fuchs

Cancers 2022, 14(7), 1632; https://doi.org/10.3390/cancers14071632 - 23 Mar 2022

Cited by 3 | Viewed by 2084

Abstract

The ratio of malignancy in suspicious soft tissue and bone neoplasms (RMST) has not been often addressed in the literature. However, this value is important to understand whether biopsies are performed too often, or not often enough, and may therefore serve as a [...] Read more.

The ratio of malignancy in suspicious soft tissue and bone neoplasms (RMST) has not been often addressed in the literature. However, this value is important to understand whether biopsies are performed too often, or not often enough, and may therefore serve as a quality indicator of work-up for a multidisciplinary team (MDT). A prerequisite for the RMST of an MDT is the assessment of absolute real-world data to avoid bias and to allow comparison among other MDTs. Analyzing 950 consecutive biopsies for sarcoma-suspected lesions over a 3.2-year period, 55% sarcomas were confirmed; 28% turned out to be benign mesenchymal tumors, and 17% non-mesenchymal tumors, respectively. Of these, 3.5% were metastases from other solid malignancies, 1.5% hematologic tumors and 13% sarcoma simulators, which most often were degenerative or inflammatory processes. The RMST for biopsied lipomatous lesions was 39%. The ratio of unplanned resections was 10% in this series. Reorganizing sarcoma work-up into integrating practice units (IPU) allows the assessment of real-world data with absolute values over the geography, thereby enabling the definition of quality indicators and addressing cost efficiency aspects of sarcoma care. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

13 pages, 11414 KiB

Open AccessArticle

MaasPenn Radiomics Reproducibility Score: A Novel Quantitative Measure for Evaluating the Reproducibility of CT-Based Handcrafted Radiomic Features

by Abdalla Ibrahim, Bruno Barufaldi, Turkey Refaee, Telmo M. Silva Filho, Raymond J. Acciavatti, Zohaib Salahuddin, Roland Hustinx, Felix M. Mottaghy, Andrew D. A. Maidment and Philippe Lambin

Cancers 2022, 14(7), 1599; https://doi.org/10.3390/cancers14071599 - 22 Mar 2022

Cited by 4 | Viewed by 2229

Abstract

The reproducibility of handcrafted radiomic features (HRFs) has been reported to be affected by variations in imaging parameters, which significantly affect the generalizability of developed signatures and translation to clinical practice. However, the collective effect of the variations in imaging parameters on the [...] Read more.

The reproducibility of handcrafted radiomic features (HRFs) has been reported to be affected by variations in imaging parameters, which significantly affect the generalizability of developed signatures and translation to clinical practice. However, the collective effect of the variations in imaging parameters on the reproducibility of HRFs remains unclear, with no objective measure to assess it in the absence of reproducibility analysis. We assessed these effects of variations in a large number of scenarios and developed the first quantitative score to assess the reproducibility of CT-based HRFs without the need for phantom or reproducibility studies. We further assessed the potential of image resampling and ComBat harmonization for removing these effects. Our findings suggest a need for radiomics-specific harmonization methods. Our developed score should be considered as a first attempt to introduce comprehensive metrics to quantify the reproducibility of CT-based handcrafted radiomic features. More research is warranted to demonstrate its validity in clinical contexts and to further improve it, possibly by the incorporation of more realistic situations, which better reflect real patients’ situations. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

16 pages, 77814 KiB

Open AccessArticle

Deep Learning-Based Pan-Cancer Classification Model Reveals Tissue-of-Origin Specific Gene Expression Signatures

by Mayur Divate, Aayush Tyagi, Derek J. Richard, Prathosh A. Prasad, Harsha Gowda and Shivashankar H. Nagaraj

Cancers 2022, 14(5), 1185; https://doi.org/10.3390/cancers14051185 - 24 Feb 2022

Cited by 16 | Viewed by 4027

Abstract

Cancer tissue-of-origin specific biomarkers are needed for effective diagnosis, monitoring, and treatment of cancers. In this study, we analyzed transcriptomics data from 37 cancer types provided by The Cancer Genome Atlas (TCGA) to identify cancer tissue-of-origin specific gene expression signatures. We developed a [...] Read more.

Cancer tissue-of-origin specific biomarkers are needed for effective diagnosis, monitoring, and treatment of cancers. In this study, we analyzed transcriptomics data from 37 cancer types provided by The Cancer Genome Atlas (TCGA) to identify cancer tissue-of-origin specific gene expression signatures. We developed a deep neural network model to classify cancers based on gene expression data. The model achieved a predictive accuracy of >97% across cancer types indicating the presence of distinct cancer tissue-of-origin specific gene expression signatures. We interpreted the model using Shapley additive explanations to identify specific gene signatures that significantly contributed to cancer-type classification. We evaluated the model and the validity of gene signatures using an independent test data set from the International Cancer Genome Consortium. In conclusion, we present a robust neural network model for accurate classification of cancers based on gene expression data and also provide a list of gene signatures that are valuable for developing biomarker panels for determining cancer tissue-of-origin. These gene signatures serve as valuable biomarkers for determining tissue-of-origin for cancers of unknown primary. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

11 pages, 3075 KiB

Open AccessArticle

High Red Cell Distribution Width Is Associated with Worse Prognosis in Early Colorectal Cancer after Curative Resection: A Propensity-Matched Analysis

by Kung-Chuan Cheng, Yueh-Ming Lin, Chin-Chen Liu, Kuen-Lin Wu and Ko-Chao Lee

Cancers 2022, 14(4), 945; https://doi.org/10.3390/cancers14040945 - 14 Feb 2022

Cited by 16 | Viewed by 2497

Abstract

The red blood cell distribution width (RDW) is a simple and widely available parameter obtained from a complete blood cell count test and is usually used in the analysis of anemia. Recently, studies have discovered the association between RDW and the host inflammatory [...] Read more.

The red blood cell distribution width (RDW) is a simple and widely available parameter obtained from a complete blood cell count test and is usually used in the analysis of anemia. Recently, studies have discovered the association between RDW and the host inflammatory response of cancer patients. We aimed to determine the prognostic value of RDW in colorectal cancer (CRC) patients. 5315 total patients with stage I-II CRC from the Chang Gung Memorial Hospital between 2001 and 2018 were enrolled. The study cohort was divided into two groups using RDW = 13.8 as the cutoff value as determined by receiver operating curve. High RDW had worse overall survival (OS), disease-free survival (DFS), and cancer-specific survival (CSS), and was also independently related to older age, more advanced tumor stage, lower albumin level, lower hemoglobin level, and more co-morbidities including diabetes, hypertension, and chronic kidney disease. We performed a propensity-score matched analysis to balance the heterogeneity between the two groups and to reduce the influence of confounding factors that may have compromised the prognosis. High RDW remained a negative predictor of OS (HR = 1.49, 95% CI: 1.25–1.78), as well as DFS and CSS. In conclusion, this is the first report using propensity matching to demonstrate the relationship between RDW and the prognosis of early-stage CRC patients. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

15 pages, 7071 KiB

Open AccessArticle

A Pancancer Analysis of the Oncogenic Role of S100 Calcium Binding Protein A7 (S100A7) in Human Tumors

by Ge Peng, Saya Tsukamoto, Ko Okumura, Hideoki Ogawa, Shigaku Ikeda and François Niyonsaba

Biology 2022, 11(2), 284; https://doi.org/10.3390/biology11020284 - 11 Feb 2022

Cited by 1 | Viewed by 1990

Abstract

Background: Although emerging studies support the relationship between S100 calcium binding protein A7 (S100A7) and various cancers, no pancancer analysis of S100A7 is available thus far. Methods: We investigated the potential oncogenic roles of S100A7 across 33 tumors based on datasets from The [...] Read more.

Background: Although emerging studies support the relationship between S100 calcium binding protein A7 (S100A7) and various cancers, no pancancer analysis of S100A7 is available thus far. Methods: We investigated the potential oncogenic roles of S100A7 across 33 tumors based on datasets from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO). Moreover, a survival prognosis analysis was performed with the gene expression profiling interactive analysis (GEPIA) web server and Kaplan–Meier plotter, followed by the genetic alteration analysis of S100A7 and enrichment analysis of S100A7-related genes. Results: S100A7 was highly expressed in most types of cancers, and remarkable associations were found between S100A7 expression and the prognosis of cancer patients. S100A7 expression was associated with the expression of DNA methyltransferase and mismatch repair genes in head and neck squamous cell carcinoma, the infiltration of CD8⁺ T cells and cancer-associated fibroblasts in different tumors. Moreover, glycosaminoglycan degradation and lysosome-associated functions were involved in the functional mechanisms of S100A7. Conclusions: The current pancancer study shows a relatively integrative understanding of the carcinogenic involvement of S100A7 in numerous types of cancers. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

18 pages, 5274 KiB

Open AccessArticle

ATP8B1 Knockdown Activated the Choline Metabolism Pathway and Induced High-Level Intracellular REDOX Homeostasis in Lung Squamous Cell Carcinoma

by Xiao Zhang, Rui Zhang, Pengpeng Liu, Runjiao Zhang, Junya Ning, Yingnan Ye, Wenwen Yu and Jinpu Yu

Cancers 2022, 14(3), 835; https://doi.org/10.3390/cancers14030835 - 07 Feb 2022

Cited by 7 | Viewed by 2367

Abstract

The flippase ATPase class I type 8b member 1 (ATP8B1) is essential for maintaining the stability and polarity of the epithelial membrane and can translocate specific phospholipids from the outer membrane to the inner membrane of the cell. Although ATP8B1 plays important roles [...] Read more.

The flippase ATPase class I type 8b member 1 (ATP8B1) is essential for maintaining the stability and polarity of the epithelial membrane and can translocate specific phospholipids from the outer membrane to the inner membrane of the cell. Although ATP8B1 plays important roles in cell functions, ATP8B1 has been poorly studied in tumors and its prognostic value in patients with lung squamous cell carcinoma (LUSC) remains unclear. By investigating the whole genomic expression profiles of LUSC samples from The Cancer Genome Atlas (TCGA) database and Tianjin Medical University Cancer Institute and Hospital (TJMUCH) cohort, we found that low expression of ATP8B1 was associated with poor prognosis of LUSC patients. The results from cellular experiments and a xenograft-bearing mice model indicated that ATP8B1 knockdown firstly induced mitochondrial dysfunction and promoted ROS production. Secondly, ATP8B1 knockdown promoted glutathione synthesis via upregulation of the CHKA-dependent choline metabolism pathway, therefore producing and maintaining high-level intracellular REDOX homeostasis to aggravate carcinogenesis and progression of LUSC. In summary, we proposed ATP8B1 as a novel predictive biomarker in LUSC and targeting ATP8B1-driven specific metabolic disorder might be a promising therapeutic strategy for LUSC. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

22 pages, 8450 KiB

Open AccessArticle

5mC-Related lncRNAs as Potential Prognostic Biomarkers in Colon Adenocarcinoma

by Yinghui Huang, Huiqian Huang, Yong Wang, Hui Liu and Yingdan Huang

Biology 2022, 11(2), 231; https://doi.org/10.3390/biology11020231 - 01 Feb 2022

Cited by 2 | Viewed by 2029

Abstract

Globally, colon adenocarcinoma (COAD) is one of the most frequent types of malignant tumors. About 40~50% of patients with advanced colon adenocarcinoma die from recurrence and metastasis. Long non-coding RNAs (lncRNAs) and 5-methylcytosine (5mC) regulatory genes have been demonstrated to involve in the [...] Read more.

Globally, colon adenocarcinoma (COAD) is one of the most frequent types of malignant tumors. About 40~50% of patients with advanced colon adenocarcinoma die from recurrence and metastasis. Long non-coding RNAs (lncRNAs) and 5-methylcytosine (5mC) regulatory genes have been demonstrated to involve in the progression and prognosis of COAD. The goal of this study was to explore the biological characteristics and potential predictive value of 5mC-related lncRNA signature in COAD. In this research, The Cancer Genome Atlas (TCGA) was utilized to obtain the expression of genes and somatic mutations in COAD, and Pearson correlation analysis was used to select lncRNAs involved in 5mC-regulated genes. Furthermore, we applied univariate Cox regression and Lasso Cox regression to construct 5mC-related lncRNA signature. Then Kaplan–Meier survival analysis, principal components analysis (PCA), receiver operating characteristic (ROC) curve, and a nomogram were performed to estimate the prognostic effect of the risk signature. GSEA was utilized to predict downstream access of the risk signature. Finally, the immune characteristics and immunotherapeutic signatures targeting this risk signature were analyzed. In the results, we obtained 1652 5mC-related lncRNAs by Pearson correlation analysis in the TCGA database. Next, we selected a risk signature that comprised 4 5mC-related lncRNAs by univariate and Lasso Cox regression. The prognostic value of the risk signature was proven. Finally, the biological mechanism and potential immunotherapeutic response of the risk signature were identified. Collectively, we constructed the 5mC-related lncRNA risk signature, which could provide a novel prognostic prediction of COAD patients. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

20 pages, 7307 KiB

Open AccessArticle

Identification of Tumor Antigens and Immune Subtypes for the Development of mRNA Vaccines and Individualized Immunotherapy in Soft Tissue Sarcoma

by Changwu Wu, Yingjuan Duan, Siming Gong, Georg Osterhoff, Sonja Kallendrusch and Nikolas Schopow

Cancers 2022, 14(2), 448; https://doi.org/10.3390/cancers14020448 - 17 Jan 2022

Cited by 4 | Viewed by 2984

Abstract

Soft tissue sarcomas (STS) are a rare disease with high recurrence rates and poor prognosis. Missing therapy options together with the high heterogeneity of this tumor type gives impetus to the development of individualized treatment approaches. This study identifies potential tumor antigens for [...] Read more.

Soft tissue sarcomas (STS) are a rare disease with high recurrence rates and poor prognosis. Missing therapy options together with the high heterogeneity of this tumor type gives impetus to the development of individualized treatment approaches. This study identifies potential tumor antigens for the development of mRNA tumor vaccines for STS and explores potential immune subtypes, stratifying patients for immunotherapy. RNA-sequencing data and clinical information were extracted from 189 STS samples from The Cancer Genome Atlas (TCGA) and microarray data were extracted from 103 STS samples from the Gene Expression Omnibus (GEO). Potential tumor antigens were identified using cBioportal, the Oncomine database, and prognostic analyses. Consensus clustering was used to define immune subtypes and immune gene modules, and graph learning-based dimensionality reduction analysis was used to depict the immune landscape. Finally, four potential tumor antigens were identified, each related to prognosis and antigen-presenting cell infiltration in STS: HLTF, ITGA10, PLCG1, and TTC3. Six immune subtypes and six gene modules were defined and validated in an independent cohort. The different immune subtypes have different molecular, cellular, and clinical characteristics. The immune landscape of STS reveals the immunity-related distribution of patients and intra-cluster heterogeneity of immune subtypes. This study provides a theoretical framework for STS mRNA vaccine development and the selection of patients for vaccination, and provides a reference for promoting individualized immunotherapy. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

15 pages, 3012 KiB

Open AccessArticle

Exploring Response to Immunotherapy in Non-Small Cell Lung Cancer Using Delta-Radiomics

by Emanuele Barabino, Giovanni Rossi, Silvia Pamparino, Martina Fiannacca, Simone Caprioli, Alessandro Fedeli, Lodovica Zullo, Stefano Vagge, Giuseppe Cittadini and Carlo Genova

Cancers 2022, 14(2), 350; https://doi.org/10.3390/cancers14020350 - 11 Jan 2022

Cited by 22 | Viewed by 3313

Abstract

Delta-radiomics is a branch of radiomics in which features are confronted after time or after introducing an external factor (such as treatment with chemotherapy or radiotherapy) to extrapolate prognostic data or to monitor a certain condition. Immune checkpoint inhibitors (ICIs) are currently revolutionizing [...] Read more.

Delta-radiomics is a branch of radiomics in which features are confronted after time or after introducing an external factor (such as treatment with chemotherapy or radiotherapy) to extrapolate prognostic data or to monitor a certain condition. Immune checkpoint inhibitors (ICIs) are currently revolutionizing the treatment of non-small cell lung cancer (NSCLC); however, there are still many issues in defining the response to therapy. Contrast-enhanced CT scans of 33 NSCLC patients treated with ICIs were analyzed; altogether, 43 lung lesions were considered. The radiomic features of the lung lesions were extracted from CT scans at baseline and at first reassessment, and their variation (delta, Δ) was calculated by means of the absolute difference and relative reduction. This variation was related to the final response of each lesion to evaluate the predictive ability of the variation itself. Twenty-seven delta features have been identified that are able to discriminate radiologic response to ICIs with statistically significant accuracy. Furthermore, the variation of nine features significantly correlates with pseudo-progression. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

13 pages, 3850 KiB

Open AccessArticle

Radiomics-Based Detection of Radionecrosis Using Harmonized Multiparametric MRI

by Clément Acquitter, Lucie Piram, Umberto Sabatini, Julia Gilhodes, Elizabeth Moyal Cohen-Jonathan, Soleakhena Ken and Benjamin Lemasson

Cancers 2022, 14(2), 286; https://doi.org/10.3390/cancers14020286 - 07 Jan 2022

Cited by 10 | Viewed by 2665

Abstract

In this study, a radiomics analysis was conducted to provide insights into the differentiation of radionecrosis and tumor progression in multiparametric MRI in the context of a multicentric clinical trial. First, the sensitivity of radiomic features to the unwanted variability caused by different [...] Read more.

In this study, a radiomics analysis was conducted to provide insights into the differentiation of radionecrosis and tumor progression in multiparametric MRI in the context of a multicentric clinical trial. First, the sensitivity of radiomic features to the unwanted variability caused by different protocol settings was assessed for each modality. Then, the ability of image normalization and ComBat-based harmonization to reduce the scanner-related variability was evaluated. Finally, the performances of several radiomic models dedicated to the classification of MRI examinations were measured. Our results showed that using radiomic models trained on harmonized data achieved better predictive performance for the investigated clinical outcome (balanced accuracy of 0.61 with the model based on raw data and 0.72 with ComBat harmonization). A comparison of several models based on information extracted from different MR modalities showed that the best classification accuracy was achieved with a model based on MR perfusion features in conjunction with clinical observation (balanced accuracy of 0.76 using LASSO feature selection and a Random Forest classifier). Although multimodality did not provide additional benefit in predictive power, the model based on T1-weighted MRI before injection provided an accuracy close to the performance achieved with perfusion. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

16 pages, 4159 KiB

Open AccessArticle

Breast Cancer Surgery 10-Year Survival Prediction by Machine Learning: A Large Prospective Cohort Study

by Shi-Jer Lou, Ming-Feng Hou, Hong-Tai Chang, Hao-Hsien Lee, Chong-Chi Chiu, Shu-Chuan Jennifer Yeh and Hon-Yi Shi

Biology 2022, 11(1), 47; https://doi.org/10.3390/biology11010047 - 29 Dec 2021

Cited by 5 | Viewed by 2158

Abstract

Machine learning algorithms have proven to be effective for predicting survival after surgery, but their use for predicting 10-year survival after breast cancer surgery has not yet been discussed. This study compares the accuracy of predicting 10-year survival after breast cancer surgery in [...] Read more.

Machine learning algorithms have proven to be effective for predicting survival after surgery, but their use for predicting 10-year survival after breast cancer surgery has not yet been discussed. This study compares the accuracy of predicting 10-year survival after breast cancer surgery in the following five models: a deep neural network (DNN), K nearest neighbor (KNN), support vector machine (SVM), naive Bayes classifier (NBC) and Cox regression (COX), and to optimize the weighting of significant predictors. The subjects recruited for this study were breast cancer patients who had received breast cancer surgery (ICD-9 cm 174–174.9) at one of three southern Taiwan medical centers during the 3-year period from June 2007, to June 2010. The registry data for the patients were randomly allocated to three datasets, one for training (n = 824), one for testing (n = 177), and one for validation (n = 177). Prediction performance comparisons revealed that all performance indices for the DNN model were significantly (p < 0.001) higher than in the other forecasting models. Notably, the best predictor of 10-year survival after breast cancer surgery was the preoperative Physical Component Summary score on the SF-36. The next best predictors were the preoperative Mental Component Summary score on the SF-36, postoperative recurrence, and tumor stage. The deep-learning DNN model is the most clinically useful method to predict and to identify risk factors for 10-year survival after breast cancer surgery. Future research should explore designs for two-level or multi-level models that provide information on the contextual effects of the risk factors on breast cancer survival. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

14 pages, 2747 KiB

Open AccessArticle

OSov: An Interactive Web Server to Evaluate Prognostic Biomarkers for Ovarian Cancer

by Zhongyi Yan, Qiang Wang, Susu Zhao, Longxiang Xie, Lu Zhang, Yali Han, Baokun Zhang, Huimin Li and Xiangqian Guo

Biology 2022, 11(1), 23; https://doi.org/10.3390/biology11010023 - 24 Dec 2021

Viewed by 2546

Abstract

Ovarian cancer is one of the most aggressive and highly lethal gynecological cancers. The purpose of our study is to build a free prognostic web server to help researchers discover potential prognostic biomarkers by integrating gene expression profiling data and clinical follow-up information [...] Read more.

Ovarian cancer is one of the most aggressive and highly lethal gynecological cancers. The purpose of our study is to build a free prognostic web server to help researchers discover potential prognostic biomarkers by integrating gene expression profiling data and clinical follow-up information of ovarian cancer. We construct a prognostic web server OSov (Online consensus Survival analysis for Ovarian cancer) based on RNA expression profiles. OSov is a user-friendly web server which could present a Kaplan–Meier plot, forest plot, nomogram and survival summary table of queried genes in each individual cohort to evaluate the prognostic potency of each queried gene. To assess the performance of OSov web server, 163 previously published prognostic biomarkers of ovarian cancer were tested and 72% of them had their prognostic values confirmed in OSov. It is a free and valuable prognostic web server to screen and assess survival-associated biomarkers for ovarian cancer. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

14 pages, 2595 KiB

Open AccessArticle

Prediction of Clinically Significant Cancer Using Radiomics Features of Pre-Biopsy of Multiparametric MRI in Men Suspected of Prostate Cancer

by Chidozie N. Ogbonnaya, Xinyu Zhang, Basim S. O. Alsaedi, Norman Pratt, Yilong Zhang, Lisa Johnston and Ghulam Nabi

Cancers 2021, 13(24), 6199; https://doi.org/10.3390/cancers13246199 - 09 Dec 2021

Cited by 14 | Viewed by 2879

Abstract

Background: Texture features based on the spatial relationship of pixels, known as the gray-level co-occurrence matrix (GLCM), may play an important role in providing the accurate classification of suspected prostate cancer. The purpose of this study was to use quantitative imaging parameters of [...] Read more.

Background: Texture features based on the spatial relationship of pixels, known as the gray-level co-occurrence matrix (GLCM), may play an important role in providing the accurate classification of suspected prostate cancer. The purpose of this study was to use quantitative imaging parameters of pre-biopsy multiparametric magnetic resonance imaging (mpMRI) for the prediction of clinically significant prostate cancer. Methods: This was a prospective study, recruiting 200 men suspected of having prostate cancer. Participants were imaged using a protocol-based 3T MRI in the pre-biopsy setting. Radiomics parameters were extracted from the T2WI and ADC texture features of the gray-level co-occurrence matrix were delineated from the region of interest. Radical prostatectomy histopathology was used as a reference standard. A Kruskal–Wallis test was applied first to identify the significant radiomic features between the three groups of Gleason scores (i.e., G1, G2 and G3). Subsequently, the Holm–Bonferroni method was applied to correct and control the probability of false rejections. We compared the probability of correctly predicting significant prostate cancer between the explanatory GLCM radiomic features, PIRADS and PSAD, using the area under the receiver operation characteristic curves. Results: We identified the significant difference in radiomic features between the three groups of Gleason scores. In total, 12 features out of 22 radiomics features correlated with the Gleason groups. Our model demonstrated excellent discriminative ability (C-statistic = 0.901, 95%CI 0.859–0.943). When comparing the probability of correctly predicting significant prostate cancer between explanatory GLCM radiomic features (Sum Variance T2WI, Sum Entropy T2WI, Difference Variance T2WI, Entropy ADC and Difference Variance ADC), PSAD and PIRADS via area under the ROC curve, radiomic features were 35.0% and 34.4% more successful than PIRADS and PSAD, respectively, in correctly predicting significant prostate cancer in our patients (p < 0.001). The Sum Entropy T2WI score had the greatest impact followed by the Sum Variance T2WI. Conclusion: Quantitative GLCM texture analyses of pre-biopsy MRI has the potential to be used as a non-invasive imaging technique to predict clinically significant cancer in men suspected of having prostate cancer. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

18 pages, 4866 KiB

Open AccessArticle

A Novel Four-Gene Prognostic Signature for Prediction of Survival in Patients with Soft Tissue Sarcoma

by Changwu Wu, Siming Gong, Georg Osterhoff and Nikolas Schopow

Cancers 2021, 13(22), 5837; https://doi.org/10.3390/cancers13225837 - 21 Nov 2021

Cited by 6 | Viewed by 2047

Abstract

Soft tissue sarcomas (STS), a group of rare malignant tumours with high tissue heterogeneity, still lack effective clinical stratification and prognostic models. Therefore, we conducted this study to establish a reliable prognostic gene signature. Using 189 STS patients’ data from The Cancer Genome [...] Read more.

Soft tissue sarcomas (STS), a group of rare malignant tumours with high tissue heterogeneity, still lack effective clinical stratification and prognostic models. Therefore, we conducted this study to establish a reliable prognostic gene signature. Using 189 STS patients’ data from The Cancer Genome Atlas database, a four-gene signature including DHRS3, JRK, TARDBP and TTC3 was established. A risk score based on this gene signature was able to divide STS patients into a low-risk and a high-risk group. The latter had significantly worse overall survival (OS) and relapse free survival (RFS), and Cox regression analyses showed that the risk score is an independent prognostic factor. Nomograms containing the four-gene signature have also been established and have been verified through calibration curves. In addition, the predictive ability of this four-gene signature for STS metastasis free survival was verified in an independent cohort (309 STS patients from the Gene Expression Omnibus database). Finally, Gene Set Enrichment Analysis indicated that the four-gene signature may be related to some pathways associated with tumorigenesis, growth, and metastasis. In conclusion, our study establishes a novel four-gene signature and clinically feasible nomograms to predict the OS and RFS. This can help personalized treatment decisions, long-term patient management, and possible future development of targeted therapy. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Graphical abstract

10 pages, 2061 KiB

Open AccessArticle

Deep Vision for Breast Cancer Classification and Segmentation

by Lawrence Fulton, Alex McLeod, Diane Dolezel, Nathaniel Bastian and Christopher P. Fulton

Cancers 2021, 13(21), 5384; https://doi.org/10.3390/cancers13215384 - 27 Oct 2021

Cited by 7 | Viewed by 2382

Abstract

(1) Background: Female breast cancer diagnoses odds have increased from 11:1 in 1975 to 8:1 today. Mammography false positive rates (FPR) are associated with overdiagnoses and overtreatment, while false negative rates (FNR) increase morbidity and mortality. (2) Methods: Deep vision supervised learning classifies [...] Read more.

(1) Background: Female breast cancer diagnoses odds have increased from 11:1 in 1975 to 8:1 today. Mammography false positive rates (FPR) are associated with overdiagnoses and overtreatment, while false negative rates (FNR) increase morbidity and mortality. (2) Methods: Deep vision supervised learning classifies 299 × 299 pixel de-noised mammography images as negative or non-negative using models built on 55,890 pre-processed training images and applied to 15,364 unseen test images. A small image representation from the fitted training model is returned to evaluate the portion of the loss function gradient with respect to the image that maximizes the classification probability. This gradient is then re-mapped back to the original images, highlighting the areas of the original image that are most influential for classification (perhaps masses or boundary areas). (3) Results: initial classification results were 97% accurate, 99% specific, and 83% sensitive. Gradient techniques for unsupervised region of interest mapping identified areas most associated with the classification results clearly on positive mammograms and might be used to support clinician analysis. (4) Conclusions: deep vision techniques hold promise for addressing the overdiagnoses and treatment, underdiagnoses, and automated region of interest identification on mammography. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

31 pages, 4373 KiB

Open AccessArticle

The Epithelial and Stromal Immune Microenvironment in Gastric Cancer: A Comprehensive Analysis Reveals Prognostic Factors with Digital Cytometry

by Wenjun Shen, Guoyun Wang, Georgia R. Cooper, Yuming Jiang and Xin Zhou

Cancers 2021, 13(21), 5382; https://doi.org/10.3390/cancers13215382 - 27 Oct 2021

Cited by 2 | Viewed by 2740

Abstract

Gastric cancer (GC) is the third leading cause of cancer-related deaths worldwide. Tumor heterogeneity continues to confound researchers’ understanding of tumor growth and the development of an effective therapy. Digital cytometry allows interpretation of heterogeneous bulk tissue transcriptomes at the cellular level. We [...] Read more.

Gastric cancer (GC) is the third leading cause of cancer-related deaths worldwide. Tumor heterogeneity continues to confound researchers’ understanding of tumor growth and the development of an effective therapy. Digital cytometry allows interpretation of heterogeneous bulk tissue transcriptomes at the cellular level. We built a novel signature matrix to dissect epithelium and stroma signals using a scRNA-seq data set (GSE134520) for GC and then applied cell mixture deconvolution to estimate diverse epithelial, stromal, and immune cell proportions from bulk transcriptome data in four independent GC cohorts (GSE62254, GSE15459, GSE84437, and TCGA-STAD) from the GEO and TCGA databases. Robust computational methods were applied to identify strong prognostic factors for GC. We identified an EMEC population whose proportions were significantly higher in patients with stage I cancer than other stages, and it was predominantly present in tumor samples but not typically found in normal samples. We found that the ratio of EMECs to stromal cells and the ratio of adaptive T cells to monocytes were the most significant prognostic factors within the non-immune and immune factors, respectively. The STEM score, which unifies these two prognostic factors, was an independent prognostic factor of overall survival (HR = 0.92,

95 %

CI = 0.89–0.94,

p = 2.05 \times 10^{- 9}

). The entire GC cohort was stratified into three risk groups (high-, moderate-, and low-risk), which yielded incremental survival times (

p < 0.0001

). For stage III disease, patients in the moderate- and low-risk groups experienced better survival benefits from radiation therapy ((HR = 0.16, 95% CI = 0.06–0.4,

p < 0.0001

), whereas those in the high-risk group did not (HR = 0.49, 95% CI = 0.14–1.72,

p = 0.25

). We concluded that the STEM score is a promising prognostic factor for gastric cancer. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

17 pages, 3712 KiB

Open AccessArticle

Trends in Tumor Site-Specific Survival of Bone Sarcomas from 1980 to 2018: A Surveillance, Epidemiology and End Results-Based Study

by Xianglin Hu, Kai Deng, Hui Ye, Zhengwang Sun, Wending Huang, Yangbai Sun and Wangjun Yan

Cancers 2021, 13(21), 5381; https://doi.org/10.3390/cancers13215381 - 27 Oct 2021

Cited by 14 | Viewed by 2286

Abstract

Objectives: As diagnosis and treatment guidelines for bone sarcomas continue updating, it is important to examine whether, when, and which kinds of patients have had a survival improvement over the last four decades. Methods: This cohort study included 9178 patients with primary bone [...] Read more.

Objectives: As diagnosis and treatment guidelines for bone sarcomas continue updating, it is important to examine whether, when, and which kinds of patients have had a survival improvement over the last four decades. Methods: This cohort study included 9178 patients with primary bone and joint sarcomas from 1 January 1980 to 31 December 2018 using data from Surveillance, Epidemiology and End Results (SEER)-9 Registries. The follow-up period was extended to November 2020. Patients were divided by decade into four time periods: 1980–1989, 1990–1999, 2000–2009, and 2010–2018. The primary endpoint was bone sarcomas-specific mortality (CSM). The 5-year bone sarcomas-specific survival (CSS) rate was determined stratified by demographic, neoplastic, temporal, economic, and geographic categories. The associations between time periods and CSM were examined using a multivariable Cox regression model, with reported hazard ratio (HR) and 95% confidence interval (CI). Results: The 5-year CSS rate for bone sarcomas was 58.7%, 69.9%, 71.0%, and 69.2%, in the 1980s, 1990s, 2000s, and 2010s, respectively. Older age, male gender, tumor sites at pelvic bones, sacrum, coccyx and associated joints, as well as vertebral column, osteosarcoma and Ewing tumor, and residence in non-metropolitan areas were independently associated with higher CSM risk. After adjusting for the covariates above, patients in the 1990s (HR = 0.74, 95% CI = 0.68–0.82), 2000s (HR = 0.71, 95% CI = 0.65–0.78), and 2010s (HR = 0.68, 95% CI = 0.62–0.76) had significantly lower CSM risks than patients in the 1980s. However, patients in the 2000s and 2010s did not have lower CSM risks than those in the 1990s (both p > 0.05). Conclusions: Although bone sarcomas survival has significantly improved since 1990, it almost halted over the next three decades. Bone sarcomas survival should improve over time, similar to common cancers. New diagnostic and therapeutic strategies such as emerging immune and targeted agents are warranted to overcome this survival stalemate. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

15 pages, 6391 KiB

Open AccessArticle

Co-Expression with Membrane CMTM6/4 on Tumor Epithelium Enhances the Prediction Value of PD-L1 on Anti-PD-1/L1 Therapeutic Efficacy in Gastric Adenocarcinoma

by Ziqi Wang, Zhi Peng, Qiyao Liu, Zixia Guo, Merey Menatola, Jing Su, Ting Li, Qing Ge, Pingzhang Wang, Lin Shen and Rong Jin

Cancers 2021, 13(20), 5175; https://doi.org/10.3390/cancers13205175 - 15 Oct 2021

Cited by 9 | Viewed by 2071

Abstract

Anti-PD-1/L1 immunotherapy has been intensively used in heavily treated population with advanced gastric adenocarcinoma. However, the immunotherapeutic efficacy is low even in PD-L1 positive patients. We aimed to establish a new strategy based on the co-expression of CMTM6/4 and PD-L1 for patient stratification [...] Read more.

Anti-PD-1/L1 immunotherapy has been intensively used in heavily treated population with advanced gastric adenocarcinoma. However, the immunotherapeutic efficacy is low even in PD-L1 positive patients. We aimed to establish a new strategy based on the co-expression of CMTM6/4 and PD-L1 for patient stratification before immunotherapy. By analyzing the data obtained from TCGA and single-cell RNA sequencing at the mRNA level, and 6-color multiplex immunofluorescence staining of tumor tissues in tissue array and 48-case pre-immunotherapy patients at the protein level, we found that CMTM6/4 and PD-L1 co-expressed in both epithelial and mesenchymal regions of gastric adenocarcinoma. The tumor tissues had higher levels of CMTM6/4 expression than their adjacent ones. A positive correlation was found between the expression of CMTM6/4 and the expression of PD-L1 in tumor epithelium. Epithelial co-expression of CMTM6/4 and PD-L1 in gastric tumor region was associated with shorter overall survival but better short-term response to anti-PD-1/L1 immunotherapy. Thus, we developed a predictive model and three pathological patterns based on the membrane co-expression of CMTM6/4 and PD-L1 in tumor epithelial cells for pre-immunotherapy patient screening in gastric adenocarcinoma. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Graphical abstract

11 pages, 1625 KiB

Open AccessArticle

Predicting Tumor Budding Status in Cervical Cancer Using MRI Radiomics: Linking Imaging Biomarkers to Histologic Characteristics

by Gun Oh Chong, Shin-Hyung Park, Nora Jee-Young Park, Bong Kyung Bae, Yoon Hee Lee, Shin Young Jeong, Jae-Chul Kim, Ji Young Park, Yu Ando and Hyung Soo Han

Cancers 2021, 13(20), 5140; https://doi.org/10.3390/cancers13205140 - 14 Oct 2021

Cited by 5 | Viewed by 1999

Abstract

Background: Our previous study demonstrated that tumor budding (TB) status was associated with inferior overall survival in cervical cancer. The purpose of this study is to evaluate whether radiomic features can predict TB status in cervical cancer patients. Methods: Seventy-four patients with cervical [...] Read more.

Background: Our previous study demonstrated that tumor budding (TB) status was associated with inferior overall survival in cervical cancer. The purpose of this study is to evaluate whether radiomic features can predict TB status in cervical cancer patients. Methods: Seventy-four patients with cervical cancer who underwent preoperative MRI and radical hysterectomy from 2011 to 2015 at our institution were enrolled. The patients were randomly allocated to the training dataset (n = 48) and test dataset (n = 26). Tumors were segmented on axial gadolinium-enhanced T1- and T2-weighted images. A total of 2074 radiomic features were extracted. Four machine learning classifiers, including logistic regression (LR), random forest (RF), support vector machine (SVM), and neural network (NN), were used. The trained models were validated on the test dataset. Results: Twenty radiomic features were selected; all were features from filtered-images and 85% were texture-related features. The area under the curve values and accuracy of the models by LR, RF, SVM and NN were 0.742 and 0.769, 0.782 and 0.731, 0.849 and 0.885, and 0.891 and 0.731, respectively, in the test dataset. Conclusion: MRI-based radiomic features could predict TB status in patients with cervical cancer. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

15 pages, 2005 KiB

Open AccessArticle

Naples Prognostic Score Predicts Tumor Regression Grade in Resectable Gastric Cancer Treated with Preoperative Chemotherapy

by Eva Lieto, Annamaria Auricchio, Giuseppe Tirino, Luca Pompella, Iacopo Panarese, Giovanni Del Sorbo, Francesca Ferraraccio, Ferdinando De Vita, Gennaro Galizia and Francesca Cardella

Cancers 2021, 13(18), 4676; https://doi.org/10.3390/cancers13184676 - 17 Sep 2021

Cited by 12 | Viewed by 2055

Abstract

Despite recent progresses, locally advanced gastric cancer remains a daunting challenge to embrace. Perioperative chemotherapy and D2-gastrectomy depict multimodal treatment of gastric cancer in Europe, shows better results than curative surgery alone in terms of downstaging, micrometastases elimination, and improved long-term survival. Unfortunately, [...] Read more.

Despite recent progresses, locally advanced gastric cancer remains a daunting challenge to embrace. Perioperative chemotherapy and D2-gastrectomy depict multimodal treatment of gastric cancer in Europe, shows better results than curative surgery alone in terms of downstaging, micrometastases elimination, and improved long-term survival. Unfortunately, preoperative chemotherapy is useless in about 50% of cases of non-responder patients, in which no effect is registered. Tumor regression grade (TRG) is directly related to chemotherapy effectiveness, but its understanding is achieved only after surgical operation; accordingly, preoperative chemotherapy is given indiscriminately. Conversely, Naples Prognostic Score (NPS), related to patient immune-nutritional status and easily obtained before taking any therapeutic decision, appeared an independent prognostic variable of TRG. NPS was calculated in 59 consecutive surgically treated gastric cancer patients after neoadjuvant FLOT4-based chemotherapy. 42.2% of positive responses were observed: all normal NPS and half mild/moderate NPS showed significant responses to chemotherapy with TRG 1–3; while only 20% of the worst NPS showed some related benefits. Evaluation of NPS in gastric cancer patients undergoing multimodal treatment may be useful both in selecting patients who will benefit from preoperative chemotherapy and for changing immune-nutritional conditions in order to improve patient’s reaction against the tumor. Full article

(This article belongs to the Topic Application of Big Medical Data in Precision Medicine)

► Show Figures

Figure 1

Topic Menu

Topic Editors

Application of Big Medical Data in Precision Medicine

Topic Information

Keywords

Participating Journals

Published Papers (30 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI