Multicenter Evaluation of a Deep Learning Model for Automatic Contouring of Cardiac Substructures in Adults
- Journal
- Practical radiation oncology (Q1)
- Published
- 12 October 2026
- Study design
- Unclassified
- Evidence level
- Level 5, Expert Opinion (CEBM 5)
- Authors
- Alexandra Moignier, Axel Licha, Felix Felici, Loig Duverge, Martin Lange, Loic Ah-Thiane, et al.
- PMID
- 42863810
- DOI
- 10.1016/j.prro.2026.10.002
Why clinicians should know about it
- Picked for Medical Physics (top studies of the week, 18 October 2026): Deep learning auto‑contouring of cardiac substructures
Abstract
PURPOSE: Efficient delineation of cardiac substructures is essential for assessing radiation-induced cardiac toxicity in thoracic radiotherapy. We clinically evaluated a deep learning model designed for automated segmentation of these structures. METHODS AND MATERIALS: The model built in collaboration with XXX (XXX) generated 21 cardiac substructures (whole heart, chambers, coronary arteries, valves, and great vessels). Five radiation oncologists rated raw contours on thirty contrast-enhanced CTs from two institutions using a 4-point Likert scale (3 = no correction, 2 = minor/moderate correction, 1 = major correction, 0 = not performed) and applied corrections when needed. Dice Similarity Coefficients (DSC) and 95th-percentile Hausdorff distances (HD95) were computed to compare model versus reference contours, clinician-corrected versus reference contours, and model versus STAPLE contours. RESULTS: Of 630 structures, 93.8% were scored either 3 or ≥2, and 6.2% received 1 by at least one clinician. For the coronary arteries (210 structures), 88.5% were scored either 3 or ≥ 2. Contour generation took approximately 1 min, with a median review and correction time of 7.0 min per CT (IQR, 5.8-9.8). The median DSC between the model and reference contours was 1.0 across all structures, while it ranged from 0.92 to 1.0 for clinician-corrected versus reference contours. Overall, HD95 was below 5 mm, for both clinicians versus reference and model versus STAPLE. CONCLUSIONS: The deep learning model provided satisfactory segmentation of cardiac substructures on contrast-enhanced CT, including coronary arteries. Its integration into a widely adopted treatment planning system lays the foundation for broad clinical implementation.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.