Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapy

For 18 months following clinical introduction of deep-learning auto-segmentation (DLAS), an audit of organ at risk (OAR) contour editing was performed, including 1255 patients from a single institution and the majority of tumour sites. Mean surface-Dice similarity coefficient increased from 0.87 to...

Full description

Saved in:
Bibliographic Details
Main Authors: Josh Mason, Jack Doherty, Sarah Robinson, Meagan de la Bastide, Jack Miskell, Ruth McLauchlan
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Physics and Imaging in Radiation Oncology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405631625000211
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832557523318603776
author Josh Mason
Jack Doherty
Sarah Robinson
Meagan de la Bastide
Jack Miskell
Ruth McLauchlan
author_facet Josh Mason
Jack Doherty
Sarah Robinson
Meagan de la Bastide
Jack Miskell
Ruth McLauchlan
author_sort Josh Mason
collection DOAJ
description For 18 months following clinical introduction of deep-learning auto-segmentation (DLAS), an audit of organ at risk (OAR) contour editing was performed, including 1255 patients from a single institution and the majority of tumour sites. Mean surface-Dice similarity coefficient increased from 0.87 to 0.97, the number of unedited OARs increased from 21.5 % to 40 %. The audit identified changes in editing corresponding to vendor model changes, adaption of local contouring practice and reduced editing in areas of no clinical significance. The audit allowed assessment of the level and frequency of editing and identification of outlier cases.
format Article
id doaj-art-7dc607102a94478ba4f1c2c46a755773
institution Kabale University
issn 2405-6316
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Physics and Imaging in Radiation Oncology
spelling doaj-art-7dc607102a94478ba4f1c2c46a7557732025-02-03T04:16:47ZengElsevierPhysics and Imaging in Radiation Oncology2405-63162025-01-0133100716Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapyJosh Mason0Jack Doherty1Sarah Robinson2Meagan de la Bastide3Jack Miskell4Ruth McLauchlan5Corresponding author.; Department of Radiobiology and Radiation Physics, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Fulham Palace Road W6 8RF London, UKDepartment of Radiobiology and Radiation Physics, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Fulham Palace Road W6 8RF London, UKDepartment of Radiobiology and Radiation Physics, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Fulham Palace Road W6 8RF London, UKDepartment of Radiobiology and Radiation Physics, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Fulham Palace Road W6 8RF London, UKDepartment of Radiobiology and Radiation Physics, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Fulham Palace Road W6 8RF London, UKDepartment of Radiobiology and Radiation Physics, Imperial College Healthcare NHS Trust, Charing Cross Hospital, Fulham Palace Road W6 8RF London, UKFor 18 months following clinical introduction of deep-learning auto-segmentation (DLAS), an audit of organ at risk (OAR) contour editing was performed, including 1255 patients from a single institution and the majority of tumour sites. Mean surface-Dice similarity coefficient increased from 0.87 to 0.97, the number of unedited OARs increased from 21.5 % to 40 %. The audit identified changes in editing corresponding to vendor model changes, adaption of local contouring practice and reduced editing in areas of no clinical significance. The audit allowed assessment of the level and frequency of editing and identification of outlier cases.http://www.sciencedirect.com/science/article/pii/S2405631625000211Clinical auditDeep learning auto-segmentation
spellingShingle Josh Mason
Jack Doherty
Sarah Robinson
Meagan de la Bastide
Jack Miskell
Ruth McLauchlan
Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapy
Physics and Imaging in Radiation Oncology
Clinical audit
Deep learning auto-segmentation
title Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapy
title_full Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapy
title_fullStr Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapy
title_full_unstemmed Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapy
title_short Auditing the clinical usage of deep-learning based organ-at-risk auto-segmentation in radiotherapy
title_sort auditing the clinical usage of deep learning based organ at risk auto segmentation in radiotherapy
topic Clinical audit
Deep learning auto-segmentation
url http://www.sciencedirect.com/science/article/pii/S2405631625000211
work_keys_str_mv AT joshmason auditingtheclinicalusageofdeeplearningbasedorganatriskautosegmentationinradiotherapy
AT jackdoherty auditingtheclinicalusageofdeeplearningbasedorganatriskautosegmentationinradiotherapy
AT sarahrobinson auditingtheclinicalusageofdeeplearningbasedorganatriskautosegmentationinradiotherapy
AT meagandelabastide auditingtheclinicalusageofdeeplearningbasedorganatriskautosegmentationinradiotherapy
AT jackmiskell auditingtheclinicalusageofdeeplearningbasedorganatriskautosegmentationinradiotherapy
AT ruthmclauchlan auditingtheclinicalusageofdeeplearningbasedorganatriskautosegmentationinradiotherapy