.png){kind=icon}
.png){kind=icon}
Return
A comprehensive multifaceted technical evaluation framework for implementation of auto-segmentation models in radiotherapy
.png){kind=icon}
OA
AI
DOI：10.1038/s43856-025-01048-6.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Manual contouring of organs at risk in radiotherapy is time-consuming, taking 1-4 hours per case. Automatic segmentation using deep learning has emerged as a promising solution, with many commercial options now available. However, these methods require rigorous validation before clinical use, and current evaluation approaches lack consistency and comprehensive assessment across publications. We developed the Comprehensive Multifaceted Technical Evaluation framework, which integrates four key assessment components: quantitative geometric measures, qualitative expert evaluation, time efficiency analysis, and dosimetric evaluation. We demonstrated this framework using an in-house automatic segmentation model for brain organs at risk, trained on 100 cases and evaluated by 8 radiation oncology experts from 4 institutions. The evaluation included geometric accuracy measurements, expert ratings of clinical acceptability, time-saving assessments, and dosimetric impact analysis comparing treatment plans. Here we show that our automatic segmentation model achieved an overall geometric accuracy of 0.78 and outperformed manual inter-rater variability. Expert evaluation revealed that 88% of automatically segmented structures were clinically acceptable with only minor adjustments needed. The evaluation and adjustment process averaged 22 minutes compared to 69 minutes for manual contouring. Dosimetric analysis showed minimal impact on treatment plans, with average dose differences of 0.30 Gray for mean dose and 0.23 Gray for maximum dose. The framework provides a robust method for validating automatic segmentation models in radiotherapy. However, establishing standardized benchmarks and consensus guidelines within the radiotherapy community remains essential for proper clinical implementation and comparison of different segmentation tools. Radiotherapy requires careful outlining of both tumors and nearby healthy organs to ensure safe and effective treatment. To reduce the time and effort involved, artificial intelligence (AI), especially deep learning, is increasingly used to automatically generate these outlines—a process called auto-segmentation. However, it is essential to properly evaluate these systems before they are used in clinical care. This study introduces COMMUTE, a comprehensive framework designed to guide the evaluation of such AI tools. The framework was tested on an in-house developed model for outlining organs at risk in the brain. The results showed good accuracy, high expert approval, and significant time savings. COMMUTE supports safer and faster implementation of AI in radiotherapy by promoting higher-quality models and enabling fair comparisons between different tools. Poel et al. introduce the COMMUTE framework for evaluating automatic segmentation models in radiotherapy by combining geometric accuracy, expert assessment, time efficiency, and dosimetric analysis. Results show standardized benchmarks and consensus guidelines are needed to properly assess the clinical readiness of AI segmentation tools.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
1.8K
Citations:
2.6K
Organization
View more organizations