Research

30 pages, 36396 KiB

Open AccessEditor’s ChoiceArticle

A Soft Label Deep Learning to Assist Breast Cancer Target Therapy and Thyroid Cancer Diagnosis

by Ching-Wei Wang, Kuan-Yu Lin, Yi-Jia Lin, Muhammad-Adil Khalil, Kai-Lin Chu and Tai-Kuang Chao

Cancers 2022, 14(21), 5312; https://doi.org/10.3390/cancers14215312 - 28 Oct 2022

Cited by 8 | Viewed by 2060

Abstract

According to the World Health Organization Report 2022, cancer is the most common cause of death contributing to nearly one out of six deaths worldwide. Early cancer diagnosis and prognosis have become essential in reducing the mortality rate. On the other hand, cancer [...] Read more.

According to the World Health Organization Report 2022, cancer is the most common cause of death contributing to nearly one out of six deaths worldwide. Early cancer diagnosis and prognosis have become essential in reducing the mortality rate. On the other hand, cancer detection is a challenging task in cancer pathology. Trained pathologists can detect cancer, but their decisions are subjective to high intra- and inter-observer variability, which can lead to poor patient care owing to false-positive and false-negative results. In this study, we present a soft label fully convolutional network (SL-FCN) to assist in breast cancer target therapy and thyroid cancer diagnosis, using four datasets. To aid in breast cancer target therapy, the proposed method automatically segments human epidermal growth factor receptor 2 (HER2) amplification in fluorescence in situ hybridization (FISH) and dual in situ hybridization (DISH) images. To help in thyroid cancer diagnosis, the proposed method automatically segments papillary thyroid carcinoma (PTC) on Papanicolaou-stained fine needle aspiration and thin prep whole slide images (WSIs). In the evaluation of segmentation of HER2 amplification in FISH and DISH images, we compare the proposed method with thirteen deep learning approaches, including U-Net, U-Net with InceptionV5, Ensemble of U-Net with Inception-v4, Inception-Resnet-v2 encoder, and ResNet-34 encoder, SegNet, FCN, modified FCN, YOLOv5, CPN, SOLOv2, BCNet, and DeepLabv3+ with three different backbones, including MobileNet, ResNet, and Xception, on three clinical datasets, including two DISH datasets on two different magnification levels and a FISH dataset. The result on DISH breast dataset 1 shows that the proposed method achieves high accuracy of 87.77 ± 14.97%, recall of 91.20 ± 7.72%, and F1-score of 81.67 ± 17.76%, while, on DISH breast dataset 2, the proposed method achieves high accuracy of 94.64 ± 2.23%, recall of 83.78 ± 6.42%, and F1-score of 85.14 ± 6.61% and, on the FISH breast dataset, the proposed method achieves high accuracy of 93.54 ± 5.24%, recall of 83.52 ± 13.15%, and F1-score of 86.98 ± 9.85%, respectively. Furthermore, the proposed method outperforms most of the benchmark approaches by a significant margin (p

< 0.001

). In evaluation of segmentation of PTC on Papanicolaou-stained WSIs, the proposed method is compared with three deep learning methods, including Modified FCN, U-Net, and SegNet. The experimental result demonstrates that the proposed method achieves high accuracy of 99.99 ± 0.01%, precision of 92.02 ± 16.6%, recall of 90.90 ± 14.25%, and F1-score of 89.82 ± 14.92% and significantly outperforms the baseline methods, including U-Net and FCN (p

< 0.001

). With the high degree of accuracy, precision, and recall, the results show that the proposed method could be used in assisting breast cancer target therapy and thyroid cancer diagnosis with faster evaluation and minimizing human judgment errors. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

19 pages, 2239 KiB

Open AccessArticle

Circulating Cell-Free DNA Assessment in Biofluids from Children with Neuroblastoma Demonstrates Feasibility and Potential for Minimally Invasive Molecular Diagnostics

by Marco Lodrini, Jasmin Wünschel, Theresa M. Thole-Kliesch, Maddalena Grimaldi, Annika Sprüssel, Rasmus B. Linke, Jan F. Hollander, Daniela Tiburtius, Annette Künkele, Johannes H. Schulte, Erwin Lankes, Thomas Elgeti, Patrick Hundsdörfer, Kathy Astrahantseff, Thorsten Simon, Angelika Eggert and Hedwig E. Deubzer

Cancers 2022, 14(9), 2080; https://doi.org/10.3390/cancers14092080 - 21 Apr 2022

Cited by 6 | Viewed by 2403

Abstract

Liquid biopsy strategies in pediatric patients are challenging due to low body weight. This study investigated cfDNA size distribution and concentration in blood, bone marrow, cerebrospinal fluid, and urine from 84 patients with neuroblastoma classified as low (n = 28), intermediate ( [...] Read more.

Liquid biopsy strategies in pediatric patients are challenging due to low body weight. This study investigated cfDNA size distribution and concentration in blood, bone marrow, cerebrospinal fluid, and urine from 84 patients with neuroblastoma classified as low (n = 28), intermediate (n = 6), or high risk (n = 50) to provide key data for liquid biopsy biobanking strategies. The average volume of blood and bone marrow plasma provided ranged between 1 and 2 mL. Analysis of 637 DNA electropherograms obtained by Agilent TapeStation measurement revealed five different major profiles and characteristic DNA size distribution patterns for each of the biofluids. The proportion of samples containing primarily cfDNA was, at 85.5%, the highest for blood plasma. The median cfDNA concentration amounted to 6.28 ng/mL (blood plasma), 58.2 ng/mL (bone marrow plasma), 0.08 ng/mL (cerebrospinal fluid), and 0.49 ng/mL (urine) in samples. Meta-analysis of the dataset demonstrated that multiple cfDNA-based assays employing the same biofluid sample optimally require sampling volumes of 1 mL for blood and bone marrow plasma, 2 mL for cerebrospinal fluid, and as large as possible for urine samples. A favorable response to treatment was associated with a rapid decrease in blood-based cfDNA concentration in patients with high-risk neuroblastoma. Blood-based cfDNA concentration was not sufficient as a single parameter to indicate high-risk disease recurrence. We provide proof of concept that monitoring neuroblastoma-specific markers in very small blood volumes from infants is feasible. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

18 pages, 12647 KiB

Open AccessArticle

TLR4 and pSTAT3 Expression on Circulating Tumor Cells (CTCs) and Immune Cells in the Peripheral Blood of Breast Cancer Patients: Prognostic Implications

by Maria A. Papadaki, Alexia Monastirioti, Christina A. Apostolopoulou, Despoina Aggouraki, Chara Papadaki, Kleita Michaelidou, Maria Vassilakopoulou, Katerina Alexakou, Dimitrios Mavroudis and Sofia Agelaki

Cancers 2022, 14(4), 1053; https://doi.org/10.3390/cancers14041053 - 18 Feb 2022

Cited by 6 | Viewed by 2300

Abstract

TLR4 and pSTAT3 are key players in cancer inflammation and immune evasion; however, their role in the peripheral blood (PB) is largely unexplored. Herein we evaluated their expression in the circulating tumor cells (CTCs) and peripheral-blood mononuclear cells (PBMCs) of patients with early [...] Read more.

TLR4 and pSTAT3 are key players in cancer inflammation and immune evasion; however, their role in the peripheral blood (PB) is largely unexplored. Herein we evaluated their expression in the circulating tumor cells (CTCs) and peripheral-blood mononuclear cells (PBMCs) of patients with early (n = 99) and metastatic (n = 100) breast cancer (BC). PB samples obtained prior to adjuvant and first-line therapy, were immunofluorescently stained for Cytokeratins/TLR4/pSTAT3/DAPI and analyzed via Ariol microscopy. TLR4+ CTCs were detected in 50% and 68% of early and metastatic CTC-positive patients, respectively, and pSTAT3+ CTCs in 83% and 68%, respectively. In metastatic patients, CTC detection was associated with a high risk of death (HR: 1.764, p = 0.038), while TLR4+ CTCs correlated with a high risk of disease progression (HR: 1.964, p = 0.030). Regarding PBMCs, TLR4 expression prevailed in metastatic disease (p = 0.029), while pSTAT3 expression was more frequent in early disease (p = 0.014). In early BC, TLR4 expression on PBMCs independently predicted for high risk of relapse (HR: 3.549; p = 0.009), whereas in metastatic BC, TLR4+/pSTAT3− PBMCs independently predicted for high risk of death (HR: 2.925; p = 0.012). These results suggest that TLR4/pSTAT3 signaling on tumor- and immune-cell compartments in the PB could play a role in BC progression, and may hold independent prognostic implications for BC patients. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

24 pages, 2202 KiB

Open AccessArticle

Locus-Specific Methylation of GSTP1, RNF219, and KIAA1539 Genes with Single Molecule Resolution in Cell-Free DNA from Healthy Donors and Prostate Tumor Patients: Application in Diagnostics

by Olga Bryzgunova, Anna Bondar, Pavel Ruzankin, Petr Laktionov, Anton Tarasenko, Alexander Kurilshikov, Rostislav Epifanov, Marat Zaripov, Marsel Kabilov and Pavel Laktionov

Cancers 2021, 13(24), 6234; https://doi.org/10.3390/cancers13246234 - 12 Dec 2021

Cited by 7 | Viewed by 3062

Abstract

The locus-specific methylation of three genes (GSTP1, RNF219, and KIAA1539 (also known as FAM214B)) in the blood plasma cell-free DNA (cfDNA) of 20 patients with prostate cancer (PCa), 18 healthy donors (HDs), and 17 patients with benign prostatic hyperplasia (BPH) was studied via [...] Read more.

The locus-specific methylation of three genes (GSTP1, RNF219, and KIAA1539 (also known as FAM214B)) in the blood plasma cell-free DNA (cfDNA) of 20 patients with prostate cancer (PCa), 18 healthy donors (HDs), and 17 patients with benign prostatic hyperplasia (BPH) was studied via the MiSeq platform. The methylation status of two CpGs within the same loci were used as the diagnostic feature for discriminating the patient groups. Many variables had good diagnostic characteristics, e.g., each of the variables GSTP1.C3.C9, GSTP1.C9, and GSTP1.C9.T17 demonstrated an 80% sensitivity at a 100% specificity for PCa patients vs. the others comparison. The analysis of RNF219 gene loci methylation allowed discriminating BPH patients with absolute sensitivity and specificity. The data on the methylation of the genes GSTP1 and RNF219 allowed discriminating PCa patients, as well as HDs, with absolute sensitivity and specificity. Thus, the data on the locus-specific methylation of cfDNA (with single-molecule resolution) combined with a diagnostic approach considering the simultaneous methylation of several CpGs in one locus enabled the discrimination of HD, BPH, and PCa patients. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

Review

Jump to: Research, Other

17 pages, 1133 KiB

Open AccessReview

Circulating Virus–Host Chimera DNAs in the Clinical Monitoring of Virus-Related Cancers

by Chiao-Ling Li, Shiou-Hwei Yeh and Pei-Jer Chen

Cancers 2022, 14(10), 2531; https://doi.org/10.3390/cancers14102531 - 20 May 2022

Cited by 3 | Viewed by 2164

Abstract

The idea of using tumor-specific cell-free DNA (ctDNA) as a tumor biomarker has been widely tested and validated in various types of human cancers and different clinical settings. ctDNA can reflect the presence or size of tumors in a real-time manner and can [...] Read more.

The idea of using tumor-specific cell-free DNA (ctDNA) as a tumor biomarker has been widely tested and validated in various types of human cancers and different clinical settings. ctDNA can reflect the presence or size of tumors in a real-time manner and can enable longitudinal monitoring with minimal invasiveness, allowing it to be applied in treatment response assessment and recurrence monitoring for cancer therapies. However, tumor detection by ctDNA remains a great challenge due to the difficulty in enriching ctDNA from a large amount of homologous non-tumor cell-free DNA (cfDNA). Only ctDNA with nonhuman sequences (or rearrangements) can be selected from the background of cfDNA from nontumor DNAs. This is possible for several virus-related cancers, such as hepatitis B virus (HBV)-related HCC or human papillomavirus (HPV)-related cervical or head and neck cancers, which frequently harbor randomly integrated viral DNA. The junction fragments of the integrations, namely virus–host chimera DNA (vh-DNA), can represent the signatures of individual tumors and are released into the blood. Such ctDNA can be enriched by capture with virus-specific probes and therefore exploited as a circulating biomarker to track virus-related cancers in clinical settings. Here, we review virus integrations in virus-related cancers to evaluate the feasibility of vh-DNA as a cell-free tumor marker and update studies on the development of detection and applications. vh-DNA may be a solution to the development of specific markers to manage virus-related cancers in the future. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

33 pages, 5085 KiB

Open AccessEditor’s ChoiceReview

Current and Developing Liquid Biopsy Techniques for Breast Cancer

by Hsing-Ju Wu and Pei-Yi Chu

Cancers 2022, 14(9), 2052; https://doi.org/10.3390/cancers14092052 - 19 Apr 2022

Cited by 20 | Viewed by 5787

Abstract

Breast cancer is the most commonly diagnosed cancer and leading cause of cancer mortality among woman worldwide. The techniques of diagnosis, prognosis, and therapy monitoring of breast cancer are critical. Current diagnostic techniques are mammography and tissue biopsy; however, they have limitations. With [...] Read more.

Breast cancer is the most commonly diagnosed cancer and leading cause of cancer mortality among woman worldwide. The techniques of diagnosis, prognosis, and therapy monitoring of breast cancer are critical. Current diagnostic techniques are mammography and tissue biopsy; however, they have limitations. With the development of novel techniques, such as personalized medicine and genetic profiling, liquid biopsy is emerging as the less invasive tool for diagnosing and monitoring breast cancer. Liquid biopsy is performed by sampling biofluids and extracting tumor components, such as circulating tumor cells (CTCs), circulating tumor DNA (ctDNA), cell-free mRNA (cfRNA) and microRNA (miRNA), proteins, and extracellular vehicles (EVs). In this review, we summarize and focus on the recent discoveries of tumor components and biomarkers applied in liquid biopsy and novel development of detection techniques, such as surface-enhanced Raman spectroscopy (SERS) and microfluidic devices. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

22 pages, 859 KiB

Open AccessReview

The Liquid Biopsy for Lung Cancer: State of the Art, Limitations and Future Developments

by Daniel Di Capua, Dara Bracken-Clarke, Karine Ronan, Anne-Marie Baird and Stephen Finn

Cancers 2021, 13(16), 3923; https://doi.org/10.3390/cancers13163923 - 04 Aug 2021

Cited by 34 | Viewed by 7756

Abstract

Lung cancer is a leading cause of cancer-related deaths, contributing to 18.4% of cancer deaths globally. Treatment of non-small cell lung carcinoma has seen rapid progression with targeted therapies tailored to specific genetic drivers. However, identifying genetic alterations can be difficult due to [...] Read more.

Lung cancer is a leading cause of cancer-related deaths, contributing to 18.4% of cancer deaths globally. Treatment of non-small cell lung carcinoma has seen rapid progression with targeted therapies tailored to specific genetic drivers. However, identifying genetic alterations can be difficult due to lack of tissue, inaccessible tumors and the risk of complications for the patient with serial tissue sampling. The liquid biopsy provides a minimally invasive method which can obtain circulating biomarkers shed from the tumor and could be a safer alternative to tissue biopsy. While tissue biopsy remains the gold standard, liquid biopsies could be very beneficial where serial sampling is required, such as monitoring disease progression or development of resistance mutations to current targeted therapies. Liquid biopsies also have a potential role in identifying patients at risk of relapse post treatment and as a component of future lung cancer screening protocols. Rapid developments have led to multiple platforms for isolating circulating tumor cells (CTCs) and detecting circulating tumor DNA (ctDNA); however, standardization is lacking, especially in lung carcinoma. Additionally, clonal hematopoiesis of uncertain clinical significance must be taken into consideration in genetic sequencing, as it introduces the potential for false positives. Various biomarkers have been investigated in liquid biopsies; however, in this review, we will concentrate on the current use of ctDNA and CTCs, focusing on the clinical relevance, current and possible future applications and limitations of each. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

Other

Jump to: Research, Review

16 pages, 483 KiB

Open AccessStudy Protocol

Prospective Evaluation of Radiotherapy-Induced Immunologic and Genetic Effects in Colorectal Cancer Oligo-Metastatic Patients with Lung-Limited Disease: The PRELUDE-1 Study

by Alessandro Ottaiano, Angela Petito, Mariachiara Santorsola, Valerio Gigantino, Maurizio Capuozzo, Daniela Fontanella, Rossella Di Franco, Valentina Borzillo, Sergio Buonopane, Vincenzo Ravo, Esmeralda Scipilliti, Giuseppe Totaro, Marcello Serra, Gianluca Ametrano, Roberta Penta, Fabiana Tatangelo, Giosuè Scognamiglio, Annabella Di Mauro, Maurizio Di Bonito, Maria Napolitano, Stefania Scala, Giuseppina Rea, Sara Santagata, Angela Lombardi, Anna Grimaldi, Carlo Caputo, Anna Crispo, Egidio Celentano, Gianfranco De Feo, Luisa Circelli, Giovanni Savarese, Raffaella Ruggiero, Francesco Perri, Vincenza Granata, Gerardo Botti, Michele Caraglia, Guglielmo Nasti and Paolo Muto Show full author list Hide full author list

Cancers 2021, 13(16), 4236; https://doi.org/10.3390/cancers13164236 - 23 Aug 2021

Cited by 8 | Viewed by 2477

Abstract

Background: in recent years, the management of advanced colorectal cancer (CRC) has been greatly improved with integrated strategies including stereotactic radiation therapy (SRT). The administration of SRT has been demonstrated, particularly in oligo-metastatic (om) CRC, to be a safe and effective option. Interestingly, [...] Read more.

Background: in recent years, the management of advanced colorectal cancer (CRC) has been greatly improved with integrated strategies including stereotactic radiation therapy (SRT). The administration of SRT has been demonstrated, particularly in oligo-metastatic (om) CRC, to be a safe and effective option. Interestingly, it has been demonstrated that SRT can induce regression of tumors in non-irradiated regions (“abscopal effect”) through stimulation of anti-tumor immune effects (“radiation-induced immunity”). We have recently shown that lung-limited omCRC is characterized by regression of tumor clones bearing specific key driver gene mutations. Aims: to assess the genetic evolution on tumor cancer cells induced by SRT in lung-limited omCRC. Secondary objectives included descriptions of the abscopal effect, responses’ duration, toxicity, and progression-free survival. A translational research will be performed to evaluate tumor genetic evolution (through liquid biopsies and Next Generation Sequencing), HLA class I repertoire, peripheral immune cells, and cytokine dynamics. Methods: PRELUDE-1 is a prospective translational study. SRT will be administered only to the largest nodule (with a maximum diameter ≤ 25 mm) in omCRC with two or three radiologically evident lesions. The sample size is based on the innovative hypothesis that radiation-induced immunity could induce regression of tumor clones bearing KRAS oncogene mutations. According to the binomial test, considering the frequency of KRAS mutations and assuming a probability of mutant KRAS→wild type KRAS of p₀ = 0.0077, with α = 0.05 and 1-β = 0.60, the final sample size is 25 patients. Full article

(This article belongs to the Special Issue Clinical Perspective and Translational Oncology of Liquid Biopsy)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Clinical Perspective and Translational Oncology of Liquid Biopsy

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI