Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.4
5.2
Journals
Cancers
Special Issues
Unlocking the Potential of AI and Big Data in Cancer...
share announcement

Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications

A special issue of Cancers (ISSN 2072-6694). This special issue belongs to the section "Cancer Informatics and Big Data".

Deadline for manuscript submissions: closed (20 December 2023) | Viewed by 13347

Special Issue Editors

Dr. Federico Mastroleo

E-Mail Website
Guest Editor
1. Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy
2. Department of Translational Medicine, University of Piemonte Orientale (UPO), Via Solaroli 17, 28100 Novara, Italy
Interests: radiotherapy; artificial intelligence; machine learning; process mining; radiomics
Special Issues, Collections and Topics in MDPI journals
Dr. Giulia Marvaso

E-Mail Website
Guest Editor
Department of Radiotherapy, European Institute of Oncology (IEO) IRCCS, 20141 Milan, Italy
Interests: urological malignancies; radiation oncology; new fractionation protocols; treatment accuracy; patient’s quality of life; prognostic and predictive factors; SBRT hypofractionation; oligometastatic disease
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

AI and big data have the potential to revolutionize cancer research by providing new insights and enabling more accurate diagnoses and treatments supported by an increasing number of data. The sheer volume of data generated by modern medical technology, such as that in the field of omics sciences, presents a unique opportunity to apply advanced machine learning techniques to uncover previously hidden patterns and relationships.

By analyzing large amounts of data from imaging scans and other diagnostic tests, machine learning algorithms can be trained to identify subtle signs of disease that may be missed by human radiologists and pathologists. This can lead to earlier diagnoses and better outcomes for patients.

Another area where AI and big data can play a role is in the development of personalized medicine. Furthermore, by analyzing large amounts of data from patient records and genomic sequencing, AI algorithms can identify patterns and markers that are unique to an individual patient. This information can be used to tailor treatment plans to the specific needs of each patient, leading to more effective and less toxic therapies.

Big data can also be used to improve the understanding of the underlying mechanisms of cancer, which can help in the discovery of new targets for drug development. By analyzing large amounts of data from patient records, genomic sequencing, and preclinical studies, researchers can identify new potential therapeutic targets and biomarkers.

This Special Issue will focus on the latest developments and applications of AI and big data in cancer research, highlighting the potential of these technologies to improve patient outcomes and accelerate the discovery of new treatments.

Potential topics include, but are not limited to:

  • The use of AI and machine learning algorithms for the early detection of cancer from imaging scans and diagnostic tests;     
  • Personalized medicine and precision oncology using AI-driven analysis of patient records and genomic data;
  • Identifying new therapeutic targets and biomarkers for cancer using big data analysis;
  • AI-assisted drug discovery and development using large-scale data analysis of preclinical studies;
  • Predictive modeling and risk assessment of cancer using AI and big data;
  • The ethical and societal implications of using AI and big data in cancer research and treatment;
  • The use of AI and big data in clinical trials, including patient selection, drug dosing, and trial design;
  • Integrating AI and big data with electronic health records (EHRs) to improve patient outcomes and care coordination;
  • The use of AI and big data for real-time monitoring and surveillance of cancer patients to detect early signs of recurrence or resistance to treatment;
  • Developing and evaluating AI-driven decision support systems for cancer diagnosis and treatment planning.

Dr. Federico Mastroleo
Dr. Giulia Marvaso
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Cancers is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • oncology
  • artificial intelligence
  • machine learning
  • radiology
  • radiotherapy
  • genomics
  • transcriptomics
  • data analysis
  • data science
  • deep learning
  • autosegmentation

Published Papers (10 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

20 pages, 3154 KiB  
Article
Ontology-Based AI Design Patterns and Constraints in Cancer Registry Data Validation
by Nicholas Nicholson, Francesco Giusti and Carmen Martos
Cancers 2023, 15(24), 5812; https://doi.org/10.3390/cancers15245812 - 12 Dec 2023
Viewed by 771
Abstract
Data validation in cancer registration is a critical operation but is resource-intensive and has traditionally depended on proprietary software. Ontology-based AI is a novel approach utilising machine reasoning based on axioms formally described in description logic. This is a different approach from deep [...] Read more.
Data validation in cancer registration is a critical operation but is resource-intensive and has traditionally depended on proprietary software. Ontology-based AI is a novel approach utilising machine reasoning based on axioms formally described in description logic. This is a different approach from deep learning AI techniques but not exclusive of them. The advantage of the ontology approach lies in its ability to address a number of challenges concurrently. The disadvantages relate to computational costs, which increase with language expressivity and the size of data sets, and class containment restrictions imposed by description logics. Both these aspects would benefit from the availability of design patterns, which is the motivation behind this study. We modelled the European cancer registry data validation rules in description logic using a number of design patterns and showed the viability of the approach. Reasoning speeds are a limiting factor for large cancer registry data sets comprising many hundreds of thousands of records, but these can be offset to a certain extent by developing the ontology in a modular way. Data validation is also a highly parallelisable process. Important potential future work in this domain would be to identify and optimise reusable design patterns, paying particular attention to avoiding any unintended reasoning efficiency hotspots. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

13 pages, 2771 KiB  
Article
More than Five Decades of Proton Therapy: A Bibliometric Overview of the Scientific Literature
by Maria Giulia Vincini, Mattia Zaffaroni, Marco Schwarz, Giulia Marvaso, Federico Mastroleo, Stefania Volpe, Luca Bergamaschi, Giovanni Carlo Mazzola, Giulia Corrao, Roberto Orecchia, Barbara Alicja Jereczek-Fossa and Daniela Alterio
Cancers 2023, 15(23), 5545; https://doi.org/10.3390/cancers15235545 - 23 Nov 2023
Cited by 1 | Viewed by 1047
Abstract
Background: The therapeutic potential of proton therapy (PT) was first recognized in 1946 by Robert Wilson, and nowadays, over 100 proton centers are in operation worldwide, and more than 60 are under construction or planned. Bibliometric data can be used to perform a [...] Read more.
Background: The therapeutic potential of proton therapy (PT) was first recognized in 1946 by Robert Wilson, and nowadays, over 100 proton centers are in operation worldwide, and more than 60 are under construction or planned. Bibliometric data can be used to perform a structured analysis of large amounts of scientific data to provide new insights, e.g., to assess the growth and development of the field and to identify research trends and hot topics. The aim of this study is to provide a comprehensive bibliometric analysis of the current status and trends in scientific literature in the PT field. Methods: The literature on PT until the 31st December 2022 in the Scopus database was searched, including the following keywords: proton AND radiotherapy AND cancer/tumor in title, abstract, and/or keywords. The open-source R Studio’s Bibliometrix package and Biblioshiny software (version 2.0) were used to perform the analysis. Results: A total of 7335 documents, mainly articles (n = 4794, 65%) and reviews (n = 1527, 21%), were collected from 1946 to 2022 from 1054 sources and 21,696 authors. Of these, roughly 84% (n = 6167) were produced in the last 15 years (2008–2022), in which the mean annual growth rate was 13%. Considering the corresponding author’s country, 79 countries contributed to the literature; the USA was the top contributor, with 2765 (38%) documents, of whom 84% were single-country publications (SCP), followed by Germany and Japan, with 535 and 531 documents of whom 66% and 93% were SCP. Considering the themes subanalysis (2002–2022), a total of 7192 documents were analyzed; among all keywords used by authors, the top three were radiotherapy (n = 1394, 21% of documents), intensity-modulated radiotherapy (n = 301, 5%), and prostate cancer (n = 301, 5%). Among disease types, prostate cancer is followed by chordoma, head and neck, and breast cancer. The change in trend themes demonstrated the fast evolution of hotspots in PT; among the most recent trends, the appearance of flash, radiomics, relative biological effectiveness (RBE), and linear energy transfer (LET) deserve to be highlighted. Conclusions: The results of the present bibliometric analysis showed that PT is an active and rapidly increasing field of research. Themes of the published works encompass the main aspects of its application in clinical practice, such as the comparison with the actual photon-based standard of care technique and the continuing technological advances. This analysis gives an overview of past scientific production and, most importantly, provides a useful point of view on the future directions of the research activities. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

13 pages, 2037 KiB  
Article
Reproducible Bioinformatics Analysis Workflows for Detecting IGH Gene Fusions in B-Cell Acute Lymphoblastic Leukaemia Patients
by Ashlee J. Thomson, Jacqueline A. Rehn, Susan L. Heatley, Laura N. Eadie, Elyse C. Page, Caitlin Schutz, Barbara J. McClure, Rosemary Sutton, Luciano Dalla-Pozza, Andrew S. Moore, Matthew Greenwood, Rishi S. Kotecha, Chun Y. Fong, Agnes S. M. Yong, David T. Yeung, James Breen and Deborah L. White
Cancers 2023, 15(19), 4731; https://doi.org/10.3390/cancers15194731 - 26 Sep 2023
Viewed by 1368
Abstract
B-cell acute lymphoblastic leukaemia (B-ALL) is characterised by diverse genomic alterations, the most frequent being gene fusions detected via transcriptomic analysis (mRNA-seq). Due to its hypervariable nature, gene fusions involving the Immunoglobulin Heavy Chain (IGH) locus can be difficult to detect [...] Read more.
B-cell acute lymphoblastic leukaemia (B-ALL) is characterised by diverse genomic alterations, the most frequent being gene fusions detected via transcriptomic analysis (mRNA-seq). Due to its hypervariable nature, gene fusions involving the Immunoglobulin Heavy Chain (IGH) locus can be difficult to detect with standard gene fusion calling algorithms and significant computational resources and analysis times are required. We aimed to optimize a gene fusion calling workflow to achieve best-case sensitivity for IGH gene fusion detection. Using Nextflow, we developed a simplified workflow containing the algorithms FusionCatcher, Arriba, and STAR-Fusion. We analysed samples from 35 patients harbouring IGH fusions (IGH::CRLF2 n = 17, IGH::DUX4 n = 15, IGH::EPOR n = 3) and assessed the detection rates for each caller, before optimizing the parameters to enhance sensitivity for IGH fusions. Initial results showed that FusionCatcher and Arriba outperformed STAR-Fusion (85–89% vs. 29% of IGH fusions reported). We found that extensive filtering in STAR-Fusion hindered IGH reporting. By adjusting specific filtering steps (e.g., read support, fusion fragments per million total reads), we achieved a 94% reporting rate for IGH fusions with STAR-Fusion. This analysis highlights the importance of filtering optimization for IGH gene fusion events, offering alternative workflows for difficult-to-detect high-risk B-ALL subtypes. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

12 pages, 797 KiB  
Article
Chronic Periodontitis and the Potential Likelihood of Gastric Cancer: A Nested Case-Control Study in the Korean Population Utilizing a National Health Sample Cohort
by Mi Jung Kwon, Ho Suk Kang, Min-Jeong Kim, Nan Young Kim, Hyo Geun Choi and Hyun Lim
Cancers 2023, 15(15), 3974; https://doi.org/10.3390/cancers15153974 - 04 Aug 2023
Cited by 1 | Viewed by 891
Abstract
There is limited information regarding the potential association between chronic periodontitis (CP) and gastric cancer, especially in the Korean population. This study aimed to explore this relationship. This nested case–control study analyzed data from 10,174 patients with gastric cancer and 40,696 controls from [...] Read more.
There is limited information regarding the potential association between chronic periodontitis (CP) and gastric cancer, especially in the Korean population. This study aimed to explore this relationship. This nested case–control study analyzed data from 10,174 patients with gastric cancer and 40,696 controls from the Korean National Health Insurance Service–National Sample Cohort using propensity score matching. Standardized differences were used to compare baseline characteristics between study groups. Logistic regression analyses adjusted for confounders were conducted to assess the association between history of CP and gastric cancer occurrence. CP histories and comprehensive subgroup analyses in the 1- and 2-year periods preceding the index date were evaluated. Individuals with a history of CP within the 1-year and 2-year periods showed an increased likelihood of developing gastric cancer. Subgroup analyses consistently supported these findings in male participants aged <65 years and individuals with various income levels or living in residential areas. However, no significant associations were observed among participants aged ≥65 years. In conclusion, CP may be a potential risk factor for gastric cancer development in the Korean population. Regular screening for gastric cancer may be necessary for high-risk individuals, specifically men aged <65 years with a history of CP. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

25 pages, 4067 KiB  
Article
Vessel Delineation Using U-Net: A Sparse Labeled Deep Learning Approach for Semantic Segmentation of Histological Images
by Lukas Glänzer, Husam E. Masalkhi, Anjali A. Roeth, Thomas Schmitz-Rode and Ioana Slabu
Cancers 2023, 15(15), 3773; https://doi.org/10.3390/cancers15153773 - 25 Jul 2023
Viewed by 1043
Abstract
Semantic segmentation is an important imaging analysis method enabling the identification of tissue structures. Histological image segmentation is particularly challenging, having large structural information while providing only limited training data. Additionally, labeling these structures to generate training data is time consuming. Here, we [...] Read more.
Semantic segmentation is an important imaging analysis method enabling the identification of tissue structures. Histological image segmentation is particularly challenging, having large structural information while providing only limited training data. Additionally, labeling these structures to generate training data is time consuming. Here, we demonstrate the feasibility of a semantic segmentation using U-Net with a novel sparse labeling technique. The basic U-Net architecture was extended by attention gates, residual and recurrent links, and dropout regularization. To overcome the high class imbalance, which is intrinsic to histological data, under- and oversampling and data augmentation were used. In an ablation study, various architectures were evaluated, and the best performing model was identified. This model contains attention gates, residual links, and a dropout regularization of 0.125. The segmented images show accurate delineations of the vascular structures (with a precision of 0.9088 and an AUC-ROC score of 0.9717), and the segmentation algorithm is robust to images containing staining variations and damaged tissue. These results demonstrate the feasibility of sparse labeling in combination with the modified U-Net architecture. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

19 pages, 1984 KiB  
Article
Pareto-Optimized Non-Negative Matrix Factorization Approach to the Cleaning of Alaryngeal Speech Signals
by Rytis Maskeliūnas, Robertas Damaševičius, Audrius Kulikajevas, Kipras Pribuišis, Nora Ulozaitė-Stanienė and Virgilijus Uloza
Cancers 2023, 15(14), 3644; https://doi.org/10.3390/cancers15143644 - 16 Jul 2023
Viewed by 1146
Abstract
The problem of cleaning impaired speech is crucial for various applications such as speech recognition, telecommunication, and assistive technologies. In this paper, we propose a novel approach that combines Pareto-optimized deep learning with non-negative matrix factorization (NMF) to effectively reduce noise in impaired [...] Read more.
The problem of cleaning impaired speech is crucial for various applications such as speech recognition, telecommunication, and assistive technologies. In this paper, we propose a novel approach that combines Pareto-optimized deep learning with non-negative matrix factorization (NMF) to effectively reduce noise in impaired speech signals while preserving the quality of the desired speech. Our method begins by calculating the spectrogram of a noisy voice clip and extracting frequency statistics. A threshold is then determined based on the desired noise sensitivity, and a noise-to-signal mask is computed. This mask is smoothed to avoid abrupt transitions in noise levels, and the modified spectrogram is obtained by applying the smoothed mask to the signal spectrogram. We then employ a Pareto-optimized NMF to decompose the modified spectrogram into basis functions and corresponding weights, which are used to reconstruct the clean speech spectrogram. The final noise-reduced waveform is obtained by inverting the clean speech spectrogram. Our proposed method achieves a balance between various objectives, such as noise suppression, speech quality preservation, and computational efficiency, by leveraging Pareto optimization in the deep learning model. The experimental results demonstrate the effectiveness of our approach in cleaning alaryngeal speech signals, making it a promising solution for various real-world applications. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

10 pages, 912 KiB  
Communication
Statin Medication Improves Five-Year Survival Rates in Patients with Head and Neck Cancer: A Retrospective Case-Control Study of about 100,000 Patients
by Jonas Wüster, Max Heiland, Susanne Nahles, Robert Preissner and Saskia Preissner
Cancers 2023, 15(12), 3093; https://doi.org/10.3390/cancers15123093 - 07 Jun 2023
Cited by 1 | Viewed by 1164
Abstract
Introduction: The overall survival among head and neck cancer patients is still low, even in a time of new therapy regimes. Regarding cancer patients’ survival, statin use has already proven to be associated with favorable survival outcomes. Our objective was to investigate the [...] Read more.
Introduction: The overall survival among head and neck cancer patients is still low, even in a time of new therapy regimes. Regarding cancer patients’ survival, statin use has already proven to be associated with favorable survival outcomes. Our objective was to investigate the influence of statin medication on the overall survival of head and neck cancer patients. Methods: Retrospective clinical data of patients diagnosed with head and neck cancer (International Classification of Diseases codes: C00–C14) were retrieved from a real-world evidence database. The initial cohort was divided into patients with statin medication, who were assigned to building cohort I, and subjects without statin medication, who were assigned to cohort II, both matched by age, gender, and risk factors (nicotine and alcohol abuse/dependence). Subsequently, Kaplan–Meier and risk analyses were performed, and odds and hazard ratios were calculated. Results: After matching, each cohort contained 48,626 patients (cohort I = females: 15,409; (31.7%), males 33,212 (68.3%); mean age ± standard deviation (SD) at diagnosis 66.3 ± 11.4 years; cohort II = females: 15,432; (31.7%), males 33,187 (68.2%); mean age ± standard deviation (SD) at diagnosis 66.4 ± 11.5 years). Five-year survival was found to be significantly higher for cohort I, with 75.19%, respectively 70.48% for cohort II. These findings were correlated significantly with a risk of death of 15.9% (cohort I) and 17.2% (cohort II); the odds ratio was 0.91 (95% CI: 0.881–0.942) and the hazard ratio 0.80 (0.777–0.827). Conclusions: The results indicate that the five-year survival of head and neck cancer patients is significantly improved by statin medication. As this study was conducted retrospectively, our data must be interpreted with caution, especially since other potential influencing factors and the initial tumor stage were not available. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

16 pages, 4881 KiB  
Article
Predicting Lymph Node Metastasis Status from Primary Muscle-Invasive Bladder Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter Study
by Qingyuan Zheng, Jun Jian, Jingsong Wang, Kai Wang, Junjie Fan, Huazhen Xu, Xinmiao Ni, Song Yang, Jingping Yuan, Jiejun Wu, Panpan Jiao, Rui Yang, Zhiyuan Chen, Xiuheng Liu and Lei Wang
Cancers 2023, 15(11), 3000; https://doi.org/10.3390/cancers15113000 - 31 May 2023
Cited by 1 | Viewed by 1569
Abstract
Background: Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep [...] Read more.
Background: Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep learning model to predict LNM status from digitized histopathological slides in MIBC. Methods: We trained a multiple instance learning model with an attention mechanism (namely SBLNP) from a cohort of 323 patients in the TCGA cohort. In parallel, we collected corresponding clinical information to construct a logistic regression model. Subsequently, the score predicted by the SBLNP was incorporated into the logistic regression model. In total, 417 WSIs from 139 patients in the RHWU cohort and 230 WSIs from 78 patients in the PHHC cohort were used as independent external validation sets. Results: In the TCGA cohort, the SBLNP achieved an AUROC of 0.811 (95% confidence interval [CI], 0.771–0.855), the clinical classifier achieved an AUROC of 0.697 (95% CI, 0.661–0.728) and the combined classifier yielded an improvement to 0.864 (95% CI, 0.827–0.906). Encouragingly, the SBLNP still maintained high performance in the RHWU cohort and PHHC cohort, with an AUROC of 0.762 (95% CI, 0.725–0.801) and 0.746 (95% CI, 0.687–0.799), respectively. Moreover, the interpretability of SBLNP identified stroma with lymphocytic inflammation as a key feature of predicting LNM presence. Conclusions: Our proposed weakly-supervised deep learning model can predict the LNM status of MIBC patients from routine WSIs, demonstrating decent generalization performance and holding promise for clinical implementation. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Graphical abstract

13 pages, 1436 KiB  
Article
Excitement and Concerns of Young Radiation Oncologists over Automatic Segmentation: A French Perspective
by Vincent Bourbonne, Adrien Laville, Nicolas Wagneur, Youssef Ghannam and Audrey Larnaudie
Cancers 2023, 15(7), 2040; https://doi.org/10.3390/cancers15072040 - 29 Mar 2023
Cited by 1 | Viewed by 1277
Abstract
Introduction: Segmentation of organs at risk (OARs) and target volumes need time and precision but are highly repetitive tasks. Radiation oncology has known tremendous technological advances in recent years, the latest being brought by artificial intelligence (AI). Despite the advantages brought by AI [...] Read more.
Introduction: Segmentation of organs at risk (OARs) and target volumes need time and precision but are highly repetitive tasks. Radiation oncology has known tremendous technological advances in recent years, the latest being brought by artificial intelligence (AI). Despite the advantages brought by AI for segmentation, some concerns were raised by academics regarding the impact on young radiation oncologists’ training. A survey was thus conducted on young french radiation oncologists (ROs) by the SFjRO (Société Française des jeunes Radiothérapeutes Oncologues). Methodology: The SFjRO organizes regular webinars focusing on anatomical localization, discussing either segmentation or dosimetry. Completion of the survey was mandatory for registration to a dosimetry webinar dedicated to head and neck (H & N) cancers. The survey was generated in accordance with the CHERRIES guidelines. Quantitative data (e.g., time savings and correction needs) were not measured but determined among the propositions. Results: 117 young ROs from 35 different and mostly academic centers participated. Most centers were either already equipped with such solutions or planning to be equipped in the next two years. AI segmentation software was mostly useful for H & N cases. While for the definition of OARs, participants experienced a significant time gain using AI-proposed delineations, with almost 35% of the participants saving between 50–100% of the segmentation time, time gained for target volumes was significantly lower, with only 8.6% experiencing a 50–100% gain. Contours still needed to be thoroughly checked, especially target volumes for some, and edited. The majority of participants suggested that these tools should be integrated into the training so that future radiation oncologists do not neglect the importance of radioanatomy. Fully aware of this risk, up to one-third of them even suggested that AI tools should be reserved for senior physicians only. Conclusions: We believe this survey on automatic segmentation to be the first to focus on the perception of young radiation oncologists. Software developers should focus on enhancing the quality of proposed segmentations, while young radiation oncologists should become more acquainted with these tools. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

Review

Jump to: Research

14 pages, 2756 KiB  
Review
Automatic Segmentation with Deep Learning in Radiotherapy
by Lars Johannes Isaksson, Paul Summers, Federico Mastroleo, Giulia Marvaso, Giulia Corrao, Maria Giulia Vincini, Mattia Zaffaroni, Francesco Ceci, Giuseppe Petralia, Roberto Orecchia and Barbara Alicja Jereczek-Fossa
Cancers 2023, 15(17), 4389; https://doi.org/10.3390/cancers15174389 - 01 Sep 2023
Viewed by 1600
Abstract
This review provides a formal overview of current automatic segmentation studies that use deep learning in radiotherapy. It covers 807 published papers and includes multiple cancer sites, image types (CT/MRI/PET), and segmentation methods. We collect key statistics about the papers to uncover commonalities, [...] Read more.
This review provides a formal overview of current automatic segmentation studies that use deep learning in radiotherapy. It covers 807 published papers and includes multiple cancer sites, image types (CT/MRI/PET), and segmentation methods. We collect key statistics about the papers to uncover commonalities, trends, and methods, and identify areas where more research might be needed. Moreover, we analyzed the corpus by posing explicit questions aimed at providing high-quality and actionable insights, including: “What should researchers think about when starting a segmentation study?”, “How can research practices in medical image segmentation be improved?”, “What is missing from the current corpus?”, and more. This allowed us to provide practical guidelines on how to conduct a good segmentation study in today’s competitive environment that will be useful for future research within the field, regardless of the specific radiotherapeutic subfield. To aid in our analysis, we used the large language model ChatGPT to condense information. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI and Big Data in Cancer Research: Advances and Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-10
Back to TopTop