EUVIMEDOpdag EUVIMED
Crossref

A segmentation method with a large vision model for magnetic resonance imaging‐guided adaptive radiotherapy

Kuo Men, Bining Yang, Yuxiang Liu, Yuan Tang, Ningning Lu, Jianrong Dai

Medical Physics · 2026-02 · 53 (2)

DOI: 10.1002/mp.70257 ↗

At a glance

Journal article in Medical Physics, published online on 2026-01-30. Written by Kuo Men and 5 co-authors. Institution: National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical Col…. Major MEDLINE topics: Radiotherapy, Image-Guided, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Cited 2 times so far (Crossref); 59 references. Funded by: National Natural Science Foundation of China, Beijing Natural Science Foundation, Beijing Hope Run Special Fund of Cancer Foundation of China.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Segmentation is the most effort‐consuming step for magnetic resonance imaging guided adaptive radiotherapy (MRIgART). Although the segment anything model (SAM) exhibits impressive capabilities, its application in medical imaging necessitates clicks, bounding boxes, or providing mask prompts on each target image, which would still require complex human interactions.

Purpose

This study introduces SAM‐ART, a large vision model that integrates personalized information to enhance the segmentation accuracy of MRIgART.

Methods

This study utilized planning computed tomography (pCT), approved contours, and daily MRI (dMRI) from 38 patients with prostate cancer and 10 patients with rectal cancer. SAM‐ART comprises an image encoder, a prompt encoder, and a mask decoder. Using mask and box prompts, SAM‐ART propagates contours from pCT to dMRI using deformable image registration (DIR) and employs them as mask prompts, providing patient‐specific information. The box prompts are used in slices prone to false negative (FN) predictions. A 5‐fold cross‐validation was then conducted, comparing SAM‐ART with DIR, traditional deep learning (tDL), and SAM‐ART using other manual prompts (point or box).

Results

The proposed SAM‐ART exhibited a mean dice similarity coefficient of 0.934 ± 0.023 for the regions of interest, surpassing DIR (0.873 ± 0.063) and tDL (0.887 ± 0.056). Moreover, the proposed mask/box prompts also outperformed the other modes (point: 0.910 ± 0.027, and box: 0.921 ± 0.025). Mask/box prompts effectively mitigated FN predictions with minimal manual intervention. The ratio of acceptable slices (using the criteria of dice ≥ 0.85, 95th percentile of Hausdorff distance ≤ 5 mm, and mean distance to agreement ≤ 1.5 mm) was 89.38% with the proposed method, which means that the segmentations on about 90% of the slices did not require manual modification.

Conclusions

This study proposed a novel method that integrates personalized information and manual prompts into a SAM‐based segmentation model. It outperformed the baseline methods, with only a few contours needing to be revised for clinical use.

Subjects

MeSH terms (MEDLINE)

Radiotherapy, Image-GuidedMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansMaleProstatic Neoplasms

Author keywords

MRI‐guided adaptive radiotherapydeep learninglarge vision modelsegment anything modelsegmentation

Authors and institutions

  • National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.

Funding

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Beijing Hope Run Special Fund of Cancer Foundation of China
  • CAMS Innovation Fund for Medical Sciences
  • Summit Plan of Precise Tumor Radiation Treatment
  • Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences, Longevity and Health Project
  • Natural Science Foundation of Beijing Municipality

Cite

APA

Men, K., Yang, B., Liu, Y., Tang, Y., Lu, N., & Dai, J. (2026). A segmentation method with a large vision model for magnetic resonance imaging‐guided adaptive radiotherapy. Medical Physics, 53(2). https://doi.org/10.1002/mp.70257

Vancouver

Men K, Yang B, Liu Y, Tang Y, Lu N, Dai J. A segmentation method with a large vision model for magnetic resonance imaging‐guided adaptive radiotherapy. Medical Physics. 2026;53(2). doi:10.1002/mp.70257

BibTeX
@article{Men2026,
  author = {Men, Kuo and Yang, Bining and Liu, Yuxiang and Tang, Yuan and Lu, Ningning and Dai, Jianrong},
  title = {A segmentation method with a large vision model for magnetic resonance imaging‐guided adaptive radiotherapy},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {2},
  doi = {10.1002/mp.70257}
}
Start for free →