Abstract
Background: Efficient and accurate delineation of organs at risk (OARs) is a critical procedure for treatment planning and dose evaluation. Deep learning-based auto-segmentation of OARs has shown promising results and is increasingly being used in radiation therapy. However, existing deep learning-based auto-segmentation approaches face two challenges in clinical practice: generalizability and human-AI interaction. A generalizable and prompt able auto-segmentation model, which segments OARs of multiple disease sites simultaneously and supports on-the-fly human-AI interaction, can significantly enhance the efficiency of radiation therapy treatment planning. Purpose: Meta's segment anything model (SAM) was proposed as a generalizable and prompt able model for next-generation natural image segmentation. We further evaluated the performance of SAM in radiotherapy segmentation. Methods: Computed tomography (CT) images of clinical cases from four disease sites at our institute were collected: prostate, lung, gastrointestinal, and head & neck. For each case, we selected the OARs important in radiotherapy treatment planning. We then compared both the Dice coefficients and Jaccard indices derived from three distinct methods: manual delineation (ground truth), automatic segmentation using SAM's 'segment anything' mode, and automatic segmentation using SAM's 'box prompt' mode that implements manual interaction via live prompts during segmentation. Results: Our results indicate that SAM's segment anything mode can achieve clinically acceptable segmentation results in most OARs with Dice scores higher than 0.7. SAM's box prompt mode further improves Dice scores by 0.1∼0.5. Similar results were observed for Jaccard indices. The results show that SAM performs better for prostate and lung, but worse for gastrointestinal and head & neck. When considering the size of organs and the distinctiveness of their boundaries, SAM shows better performance for large organs with distinct boundaries, such as lung and liver, and worse for smaller organs with less distinct boundaries, like parotid and cochlea. Conclusions: Our results demonstrate SAM's robust generalizability with consistent accuracy in automatic segmentation for radiotherapy. Furthermore, the advanced box-prompt method enables the users to augment auto-segmentation interactively and dynamically, leading to patient-specific auto-segmentation in radiation therapy. SAM's generalizability across different disease sites and different modalities make it feasible to develop a generic auto-segmentation model in radiotherapy.
Recommended Citation
L. Zhang and Z. Liu and L. Zhang and Z. Wu and X. Yu and J. Holmes and H. Feng and H. Dai and X. Li and Q. Li and W. W. Wong and S. A. Vora and D. Zhu and T. Liu and W. Liu, "Technical Note: Generalizable And Promptable Artificial Intelligence Model To Augment Clinical Delineation In Radiation Oncology," Medical Physics, vol. 51, no. 3, pp. 2187 - 2199, Wiley, Mar 2024.
The definitive version is available at https://doi.org/10.1002/mp.16965
Department(s)
Computer Science
Publication Status
Full Access
Keywords and Phrases
artificial intelligence; clinical delineation; generalizable; promptable; radiation oncology; segment anything model
International Standard Serial Number (ISSN)
2473-4209; 0094-2405
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2025 Wiley, All rights reserved.
Publication Date
01 Mar 2024
PubMed ID
38319676
Comments
Arizona Biomedical Research Commission, Grant K25CA168984