Cargando…

Semi-supervised learning in cancer diagnostics

In cancer diagnostics, a considerable amount of data is acquired during routine work-up. Recently, machine learning has been used to build classifiers that are tasked with cancer detection and aid in clinical decision-making. Most of these classifiers are based on supervised learning (SL) that needs...

Descripción completa

Detalles Bibliográficos
Autores principales: Eckardt, Jan-Niklas, Bornhäuser, Martin, Wendt, Karsten, Middeke, Jan Moritz
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9329803/
https://www.ncbi.nlm.nih.gov/pubmed/35912249
http://dx.doi.org/10.3389/fonc.2022.960984
_version_ 1784758004227244032
author Eckardt, Jan-Niklas
Bornhäuser, Martin
Wendt, Karsten
Middeke, Jan Moritz
author_facet Eckardt, Jan-Niklas
Bornhäuser, Martin
Wendt, Karsten
Middeke, Jan Moritz
author_sort Eckardt, Jan-Niklas
collection PubMed
description In cancer diagnostics, a considerable amount of data is acquired during routine work-up. Recently, machine learning has been used to build classifiers that are tasked with cancer detection and aid in clinical decision-making. Most of these classifiers are based on supervised learning (SL) that needs time- and cost-intensive manual labeling of samples by medical experts for model training. Semi-supervised learning (SSL), however, works with only a fraction of labeled data by including unlabeled samples for information abstraction and thus can utilize the vast discrepancy between available labeled data and overall available data in cancer diagnostics. In this review, we provide a comprehensive overview of essential functionalities and assumptions of SSL and survey key studies with regard to cancer care differentiating between image-based and non-image-based applications. We highlight current state-of-the-art models in histopathology, radiology and radiotherapy, as well as genomics. Further, we discuss potential pitfalls in SSL study design such as discrepancies in data distributions and comparison to baseline SL models, and point out future directions for SSL in oncology. We believe well-designed SSL models to strongly contribute to computer-guided diagnostics in malignant disease by overcoming current hinderances in the form of sparse labeled and abundant unlabeled data.
format Online
Article
Text
id pubmed-9329803
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-93298032022-07-29 Semi-supervised learning in cancer diagnostics Eckardt, Jan-Niklas Bornhäuser, Martin Wendt, Karsten Middeke, Jan Moritz Front Oncol Oncology In cancer diagnostics, a considerable amount of data is acquired during routine work-up. Recently, machine learning has been used to build classifiers that are tasked with cancer detection and aid in clinical decision-making. Most of these classifiers are based on supervised learning (SL) that needs time- and cost-intensive manual labeling of samples by medical experts for model training. Semi-supervised learning (SSL), however, works with only a fraction of labeled data by including unlabeled samples for information abstraction and thus can utilize the vast discrepancy between available labeled data and overall available data in cancer diagnostics. In this review, we provide a comprehensive overview of essential functionalities and assumptions of SSL and survey key studies with regard to cancer care differentiating between image-based and non-image-based applications. We highlight current state-of-the-art models in histopathology, radiology and radiotherapy, as well as genomics. Further, we discuss potential pitfalls in SSL study design such as discrepancies in data distributions and comparison to baseline SL models, and point out future directions for SSL in oncology. We believe well-designed SSL models to strongly contribute to computer-guided diagnostics in malignant disease by overcoming current hinderances in the form of sparse labeled and abundant unlabeled data. Frontiers Media S.A. 2022-07-14 /pmc/articles/PMC9329803/ /pubmed/35912249 http://dx.doi.org/10.3389/fonc.2022.960984 Text en Copyright © 2022 Eckardt, Bornhäuser, Wendt and Middeke https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Eckardt, Jan-Niklas
Bornhäuser, Martin
Wendt, Karsten
Middeke, Jan Moritz
Semi-supervised learning in cancer diagnostics
title Semi-supervised learning in cancer diagnostics
title_full Semi-supervised learning in cancer diagnostics
title_fullStr Semi-supervised learning in cancer diagnostics
title_full_unstemmed Semi-supervised learning in cancer diagnostics
title_short Semi-supervised learning in cancer diagnostics
title_sort semi-supervised learning in cancer diagnostics
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9329803/
https://www.ncbi.nlm.nih.gov/pubmed/35912249
http://dx.doi.org/10.3389/fonc.2022.960984
work_keys_str_mv AT eckardtjanniklas semisupervisedlearningincancerdiagnostics
AT bornhausermartin semisupervisedlearningincancerdiagnostics
AT wendtkarsten semisupervisedlearningincancerdiagnostics
AT middekejanmoritz semisupervisedlearningincancerdiagnostics