Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning
Background and purpose: Peer-review of Target Volume (TV) and Organ at Risk (OAR) contours in radiotherapy planning are typically conducted visually; this can be time consuming and subject to interobserver variation. This study investigated automatic evaluation of contouring using conformity indices...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2020-10-01
|
Series: | Physics and Imaging in Radiation Oncology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405631620300713 |
id |
doaj-98f7f30f006246a08e4a0c96106ccbaf |
---|---|
record_format |
Article |
spelling |
doaj-98f7f30f006246a08e4a0c96106ccbaf2020-12-19T05:09:24ZengElsevierPhysics and Imaging in Radiation Oncology2405-63162020-10-0116149155Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learningSamsara Terparia0Romaana Mir1Yat Tsang2Catharine H Clark3Rushil Patel4Radiotherapy Physics, Mount Vernon Cancer Centre, Northwood, UK; Corresponding author.NIHR Radiotherapy Trials Quality Assurance Group, Mount Vernon Cancer Centre, Northwood, UKRadiotherapy Physics, Mount Vernon Cancer Centre, Northwood, UK; NIHR Radiotherapy Trials Quality Assurance Group, Mount Vernon Cancer Centre, Northwood, UKNIHR Radiotherapy Trials Quality Assurance Group, Mount Vernon Cancer Centre, Northwood, UK; Radiotherapy Physics, University College London Hospital, London, UK; National Physical Laboratory, Teddington, UKNIHR Radiotherapy Trials Quality Assurance Group, Mount Vernon Cancer Centre, Northwood, UKBackground and purpose: Peer-review of Target Volume (TV) and Organ at Risk (OAR) contours in radiotherapy planning are typically conducted visually; this can be time consuming and subject to interobserver variation. This study investigated automatic evaluation of contouring using conformity indices and supervised machine learning. Methods: A total of 393 contours from 253 Stereotactic Ablative Body Radiotherapy (SABR) benchmark cases (adrenal gland, liver, pelvic lymph node and spine), delineated by 132 clinicians from 25 centres, were visually evaluated for conformity against gold standard contours. Contours were scored as “pass” or “fail” on visual peer review and six Conformity Indices (CIs) were applied. CI values were mapped to pass/fail scores for each contour and used to train supervised machine learning models. A 5-fold cross validation method was employed to determine the predictive accuracies of each model. Results: The stomach structure produced models with the highest predictive accuracy overall (96% using Support Vector Machine and Ensemble models), whilst the liver GTV produced models with the lowest predictive accuracy (76% using Logistic Regression). Predictive accuracies across all models ranged from 68–96% (68–87% for TV and 71–96% for OARs). Conclusions: Although a final visual review by an experienced clinician is still required, the automatic contour evaluation method could reduce the time for benchmark case reviews by identifying gross contouring errors. This method could be successfully implemented to support departmental training and the continuous assessment of outlining for clinical staff in the peer-review process, to reduce interobserver variability in contouring and improve interpretation of radiological anatomy.http://www.sciencedirect.com/science/article/pii/S2405631620300713Machine learningConformity indexQuality assuranceInterobserver variationDelineationSABR |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Samsara Terparia Romaana Mir Yat Tsang Catharine H Clark Rushil Patel |
spellingShingle |
Samsara Terparia Romaana Mir Yat Tsang Catharine H Clark Rushil Patel Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning Physics and Imaging in Radiation Oncology Machine learning Conformity index Quality assurance Interobserver variation Delineation SABR |
author_facet |
Samsara Terparia Romaana Mir Yat Tsang Catharine H Clark Rushil Patel |
author_sort |
Samsara Terparia |
title |
Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning |
title_short |
Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning |
title_full |
Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning |
title_fullStr |
Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning |
title_full_unstemmed |
Automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning |
title_sort |
automatic evaluation of contours in radiotherapy planning utilising conformity indices and machine learning |
publisher |
Elsevier |
series |
Physics and Imaging in Radiation Oncology |
issn |
2405-6316 |
publishDate |
2020-10-01 |
description |
Background and purpose: Peer-review of Target Volume (TV) and Organ at Risk (OAR) contours in radiotherapy planning are typically conducted visually; this can be time consuming and subject to interobserver variation. This study investigated automatic evaluation of contouring using conformity indices and supervised machine learning. Methods: A total of 393 contours from 253 Stereotactic Ablative Body Radiotherapy (SABR) benchmark cases (adrenal gland, liver, pelvic lymph node and spine), delineated by 132 clinicians from 25 centres, were visually evaluated for conformity against gold standard contours. Contours were scored as “pass” or “fail” on visual peer review and six Conformity Indices (CIs) were applied. CI values were mapped to pass/fail scores for each contour and used to train supervised machine learning models. A 5-fold cross validation method was employed to determine the predictive accuracies of each model. Results: The stomach structure produced models with the highest predictive accuracy overall (96% using Support Vector Machine and Ensemble models), whilst the liver GTV produced models with the lowest predictive accuracy (76% using Logistic Regression). Predictive accuracies across all models ranged from 68–96% (68–87% for TV and 71–96% for OARs). Conclusions: Although a final visual review by an experienced clinician is still required, the automatic contour evaluation method could reduce the time for benchmark case reviews by identifying gross contouring errors. This method could be successfully implemented to support departmental training and the continuous assessment of outlining for clinical staff in the peer-review process, to reduce interobserver variability in contouring and improve interpretation of radiological anatomy. |
topic |
Machine learning Conformity index Quality assurance Interobserver variation Delineation SABR |
url |
http://www.sciencedirect.com/science/article/pii/S2405631620300713 |
work_keys_str_mv |
AT samsaraterparia automaticevaluationofcontoursinradiotherapyplanningutilisingconformityindicesandmachinelearning AT romaanamir automaticevaluationofcontoursinradiotherapyplanningutilisingconformityindicesandmachinelearning AT yattsang automaticevaluationofcontoursinradiotherapyplanningutilisingconformityindicesandmachinelearning AT catharinehclark automaticevaluationofcontoursinradiotherapyplanningutilisingconformityindicesandmachinelearning AT rushilpatel automaticevaluationofcontoursinradiotherapyplanningutilisingconformityindicesandmachinelearning |
_version_ |
1724377669342068736 |