Segment anything model (SAM)-driven prompt-guided interactive delineation of gross tumor volume for rectal cancer neoadjuvant radiotherapy.
Authors
Affiliations (5)
Affiliations (5)
- Institute of Medical Technology, Peking University Health Science Center, Beijing, China.
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Radiation Oncology, Peking University Cancer Hospital & Institute, Beijing, China.
- MedMind Technology Co., Ltd, Beijing, China.
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China.
- Inner Mongolia Engineering Center of Digital-Intelligent Integrated Prevention and Screening of Malignant Tumors, Proton Center & Department of Radiation Oncology, Peking University Cancer Hospital (Inner Mongolia Campus)/Affiliated Cancer Hospital of Inner Mongolia Medical University, Hohhot, China.
Abstract
Segment Anything Model (SAM), a prompt-guided foundation model, exhibits substantial potential for medical image segmentation by incorporating prior knowledge through user-defined prompts. However, the application of SAM in radiotherapy target delineation remains limited. This study proposes a feasible prompt-guided interactive delineation workflow driven by an optimized SAM. A total of 100 rectal cancer neoadjuvant radiotherapy cases were collected (60 for training and 40 for testing). This study utilized bounding-box prompts to guide SAM for GTV segmentation. Physicians manually draw box prompts on certain slices, while box prompts for the remaining slices are automatically generated using an interpolation strategy. Four fine-tuning strategies for SAM training were evaluated, and the impact of prompt numbers and placements was assessed as well. The performance of the finalized workflow with optimized SAM was compared with five state-of-the-art (SOTA) models, and its robustness to prompt variations in middle-slice selection and box-prompt margins was analyzed. Compared to other fine-tuning methods, freezing the image encoder obtained the most stable performance. Prompts on only 3 slices achieved accuracy comparable to prompts on all slices. The placement of the middle-slice prompt exhibited negligible impact (p > 0.05). The finalized SAM-driven workflow outperformed end-to-end baseline models both visually and quantitatively (3D DSC: 0.92 vs 0.80; 3D HD95: 2.73 vs 12.70; IoU: 0.86 vs 0.67; Sensitivity: 91.20% vs 85.98%; Precision: 93.65% vs 79.23%), while maintaining stable performance across certain prompt variations. The proposed SAM-driven interactive workflow with as few as 3 box prompts achieves favorable accuracy of GTV segmentation for rectal cancer neoadjuvant radiotherapy.