Validation of a Fully Automated Hybrid Deep Learning Cardiac Substructure Segmentation Tool for Contouring and Dose Evaluation in Lung Cancer Radiotherapy.
Automatic segmentation
cardiac substructures
deep learning
dose validation
lung cancer
radiotherapy
Journal
Clinical oncology (Royal College of Radiologists (Great Britain))
ISSN: 1433-2981
Titre abrégé: Clin Oncol (R Coll Radiol)
Pays: England
ID NLM: 9002902
Informations de publication
Date de publication:
06 2023
06 2023
Historique:
received:
05
10
2022
revised:
05
01
2023
accepted:
07
03
2023
medline:
9
5
2023
pubmed:
25
3
2023
entrez:
24
3
2023
Statut:
ppublish
Résumé
Accurate and consistent delineation of cardiac substructures is challenging. The aim of this work was to validate a novel segmentation tool for automatic delineation of cardiac structures and subsequent dose evaluation, with potential application in clinical settings and large-scale radiation-related cardiotoxicity studies. A recently developed hybrid method for automatic segmentation of 18 cardiac structures, combining deep learning, multi-atlas mapping and geometric segmentation of small challenging substructures, was independently validated on 30 lung cancer cases. These included anatomical and imaging variations, such as tumour abutting heart, lung collapse and metal artefacts. Automatic segmentations were compared with manual contours of the 18 structures using quantitative metrics, including Dice similarity coefficient (DSC), mean distance to agreement (MDA) and dose comparisons. A comparison of manual and automatic contours across all cases showed a median DSC of 0.75-0.93 and a median MDA of 2.09-3.34 mm for whole heart and chambers. The median MDA for great vessels, coronary arteries, cardiac valves, sinoatrial and atrioventricular conduction nodes was 3.01-8.54 mm. For the 27 cases treated with curative intent (planned target volume dose ≥50 Gy), the median dose difference was -1.12 to 0.57 Gy (absolute difference of 1.13-3.25%) for the mean dose to heart and chambers; and -2.25 to 4.45 Gy (absolute difference of 0.94-6.79%) for the mean dose to substructures. The novel hybrid automatic segmentation tool reported high accuracy and consistency over a validation set with challenging anatomical and imaging variations. This has promising applications in substructure dose calculations of large-scale datasets and for future studies on long-term cardiac toxicity.
Sections du résumé
BACKGROUND AND PURPOSE
Accurate and consistent delineation of cardiac substructures is challenging. The aim of this work was to validate a novel segmentation tool for automatic delineation of cardiac structures and subsequent dose evaluation, with potential application in clinical settings and large-scale radiation-related cardiotoxicity studies.
MATERIALS AND METHODS
A recently developed hybrid method for automatic segmentation of 18 cardiac structures, combining deep learning, multi-atlas mapping and geometric segmentation of small challenging substructures, was independently validated on 30 lung cancer cases. These included anatomical and imaging variations, such as tumour abutting heart, lung collapse and metal artefacts. Automatic segmentations were compared with manual contours of the 18 structures using quantitative metrics, including Dice similarity coefficient (DSC), mean distance to agreement (MDA) and dose comparisons.
RESULTS
A comparison of manual and automatic contours across all cases showed a median DSC of 0.75-0.93 and a median MDA of 2.09-3.34 mm for whole heart and chambers. The median MDA for great vessels, coronary arteries, cardiac valves, sinoatrial and atrioventricular conduction nodes was 3.01-8.54 mm. For the 27 cases treated with curative intent (planned target volume dose ≥50 Gy), the median dose difference was -1.12 to 0.57 Gy (absolute difference of 1.13-3.25%) for the mean dose to heart and chambers; and -2.25 to 4.45 Gy (absolute difference of 0.94-6.79%) for the mean dose to substructures.
CONCLUSION
The novel hybrid automatic segmentation tool reported high accuracy and consistency over a validation set with challenging anatomical and imaging variations. This has promising applications in substructure dose calculations of large-scale datasets and for future studies on long-term cardiac toxicity.
Identifiants
pubmed: 36964031
pii: S0936-6555(23)00112-7
doi: 10.1016/j.clon.2023.03.005
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
370-381Informations de copyright
Copyright © 2023. Published by Elsevier Ltd.