Key result
Auto-contouring matches expert inter-observer variation for cardiac chambers and major vessels with ~0.88 DSC.
Why the study?
High radiation doses to healthy cardiac substructures in STAR raise concerns about cardio-toxicity, but cardiac substructures are not routinely contoured, hindering the understanding of dose-effect relationships.
Does deep learning-based auto-contouring perform comparably to manual inter-observer variation for delineating cardiac substructures in VT patients undergoing stereotactic arrhythmia radioablation?
Does deep learning-based auto-contouring perform comparably to manual inter-observer variation for delineating cardiac substructures in VT patients undergoing stereotactic arrhythmia radioablation?
Absolute Event Rate: 0.88% vs 0.89%
Deep learning auto-contouring models trained on VT patient data perform comparably to manual inter-observer variation for delineating large cardiac structures, enabling time-efficient organ-at-risk evaluation in stereotactic arrhythmia radioablation.
May support efficient auto-contouring of large cardiac structures in STAR; hypothesis-generating for valves and arteries with prospective validation needed.
BACKGROUND/PURPOSE: High doses to healthy cardiac substructures (CS) in stereotactic arrhythmia radioablation (STAR) raise concerns regarding potential treatment-induced cardio-toxicity. However, CS contours are not routinely created, hindering the understanding of the CS dose-effect relationships. To address this issue, the alignment of CS contouring was initiated within the STOPSTORM consortium. In this study, we developed and evaluated auto-contouring models trained to delineate CS and major vessels in ventricular tachycardia (VT) patients. METHODS: Eight centres provided standard treatment planning computed tomography (CT) and/or contrast-enhanced CT datasets of 55 VT patients, each including 16 CS. Auto-contouring models were trained to contour either large structures or small structures. Dice Similarity Coefficient (DSC), 95 % Hausdorff distance (HD95) and volume ratio (VR) were used to evaluate model performance versus inter-observer variation (IOV) on seven VT patient test cases. Significant differences were tested using the Mann-Whitney U test. RESULTS: The performance on the four chambers and the major vessels (median DSC: 0.88; HD95: 5.8-19.4 mm; VR: 1.09) was similar to the IOV (median DSC: 0.89; HD95: 4.8-14.0 mm; VR: 1.20). For the valves, model performance (median DSC: 0.37; HD95: 11.6 mm; VR: 1.63) was similar to the IOV (median DSC: 0.41; HD95: 12.4 mm; VR: 3.42), but slightly worse for the coronary arteries (median DSC: 0.33 vs 0.42; HD95: 24.4 mm vs 16.9 mm; VR: 1.93 vs 3.30). The IOV for these small structures remains large despite using contouring guidelines. CONCLUSION: CS auto-contouring models trained on VT patient data perform similarly to IOV. This allows for time-efficient evaluation of CS as possible organs-at-risk.
No takes yet. Share an insight, caveat, or question.
Pol et al. (2024) studied Ventricular tachycardia (VT) (n=132). Auto-contouring models for cardiac substructures vs. Inter-observer variation (manual contouring) was evaluated on Dice Similarity Coefficient (DSC) for four cardiac chambers and major vessels. Auto-contouring models trained on VT patient data performed similarly to inter-observer variation for the four cardiac chambers and major vessels (median DSC 0.88 vs 0.89).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: