Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review
<b>Objectives</b>: To summarize the available literature on using machine learning (ML) for the detection and segmentation of benign tumors of the central nervous system (CNS) and to assess the adherence of published ML/diagnostic accuracy studies to best practice. <b>Methods</b...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/14/11/2676 |
_version_ | 1797493886510170112 |
---|---|
author | Paul Windisch Carole Koechli Susanne Rogers Christina Schröder Robert Förster Daniel R. Zwahlen Stephan Bodis |
author_facet | Paul Windisch Carole Koechli Susanne Rogers Christina Schröder Robert Förster Daniel R. Zwahlen Stephan Bodis |
author_sort | Paul Windisch |
collection | DOAJ |
description | <b>Objectives</b>: To summarize the available literature on using machine learning (ML) for the detection and segmentation of benign tumors of the central nervous system (CNS) and to assess the adherence of published ML/diagnostic accuracy studies to best practice. <b>Methods</b>: The MEDLINE database was searched for the use of ML in patients with any benign tumor of the CNS, and the records were screened according to PRISMA guidelines. <b>Results</b>: Eleven retrospective studies focusing on meningioma (n = 4), vestibular schwannoma (n = 4), pituitary adenoma (n = 2) and spinal schwannoma (n = 1) were included. The majority of studies attempted segmentation. Links to repositories containing code were provided in two manuscripts, and no manuscripts shared imaging data. Only one study used an external test set, which raises the question as to whether some of the good performances that have been reported were caused by overfitting and may not generalize to data from other institutions. <b>Conclusions</b>: Using ML for detecting and segmenting benign brain tumors is still in its infancy. Stronger adherence to ML best practices could facilitate easier comparisons between studies and contribute to the development of models that are more likely to one day be used in clinical practice. |
first_indexed | 2024-03-10T01:26:25Z |
format | Article |
id | doaj.art-089650cd67cc4e17aecdf610b56864b5 |
institution | Directory Open Access Journal |
issn | 2072-6694 |
language | English |
last_indexed | 2024-03-10T01:26:25Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Cancers |
spelling | doaj.art-089650cd67cc4e17aecdf610b56864b52023-11-23T13:49:14ZengMDPI AGCancers2072-66942022-05-011411267610.3390/cancers14112676Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic ReviewPaul Windisch0Carole Koechli1Susanne Rogers2Christina Schröder3Robert Förster4Daniel R. Zwahlen5Stephan Bodis6Department of Radiation Oncology, Kantonsspital Winterthur, 8400 Winterthur, SwitzerlandDepartment of Radiation Oncology, Kantonsspital Winterthur, 8400 Winterthur, SwitzerlandDepartment of Radiation Oncology, Kantonsspital Aarau, 5001 Aarau, SwitzerlandDepartment of Radiation Oncology, Kantonsspital Winterthur, 8400 Winterthur, SwitzerlandDepartment of Radiation Oncology, Kantonsspital Winterthur, 8400 Winterthur, SwitzerlandDepartment of Radiation Oncology, Kantonsspital Winterthur, 8400 Winterthur, SwitzerlandDepartment of Radiation Oncology, Kantonsspital Aarau, 5001 Aarau, Switzerland<b>Objectives</b>: To summarize the available literature on using machine learning (ML) for the detection and segmentation of benign tumors of the central nervous system (CNS) and to assess the adherence of published ML/diagnostic accuracy studies to best practice. <b>Methods</b>: The MEDLINE database was searched for the use of ML in patients with any benign tumor of the CNS, and the records were screened according to PRISMA guidelines. <b>Results</b>: Eleven retrospective studies focusing on meningioma (n = 4), vestibular schwannoma (n = 4), pituitary adenoma (n = 2) and spinal schwannoma (n = 1) were included. The majority of studies attempted segmentation. Links to repositories containing code were provided in two manuscripts, and no manuscripts shared imaging data. Only one study used an external test set, which raises the question as to whether some of the good performances that have been reported were caused by overfitting and may not generalize to data from other institutions. <b>Conclusions</b>: Using ML for detecting and segmenting benign brain tumors is still in its infancy. Stronger adherence to ML best practices could facilitate easier comparisons between studies and contribute to the development of models that are more likely to one day be used in clinical practice.https://www.mdpi.com/2072-6694/14/11/2676machine learningdeep learningbenign brain tumorvestibular schwannomameningiomapituitary adenoma |
spellingShingle | Paul Windisch Carole Koechli Susanne Rogers Christina Schröder Robert Förster Daniel R. Zwahlen Stephan Bodis Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review Cancers machine learning deep learning benign brain tumor vestibular schwannoma meningioma pituitary adenoma |
title | Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review |
title_full | Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review |
title_fullStr | Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review |
title_full_unstemmed | Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review |
title_short | Machine Learning for the Detection and Segmentation of Benign Tumors of the Central Nervous System: A Systematic Review |
title_sort | machine learning for the detection and segmentation of benign tumors of the central nervous system a systematic review |
topic | machine learning deep learning benign brain tumor vestibular schwannoma meningioma pituitary adenoma |
url | https://www.mdpi.com/2072-6694/14/11/2676 |
work_keys_str_mv | AT paulwindisch machinelearningforthedetectionandsegmentationofbenigntumorsofthecentralnervoussystemasystematicreview AT carolekoechli machinelearningforthedetectionandsegmentationofbenigntumorsofthecentralnervoussystemasystematicreview AT susannerogers machinelearningforthedetectionandsegmentationofbenigntumorsofthecentralnervoussystemasystematicreview AT christinaschroder machinelearningforthedetectionandsegmentationofbenigntumorsofthecentralnervoussystemasystematicreview AT robertforster machinelearningforthedetectionandsegmentationofbenigntumorsofthecentralnervoussystemasystematicreview AT danielrzwahlen machinelearningforthedetectionandsegmentationofbenigntumorsofthecentralnervoussystemasystematicreview AT stephanbodis machinelearningforthedetectionandsegmentationofbenigntumorsofthecentralnervoussystemasystematicreview |