EUVIMEDSkopri EUVIMED
Multizentrische Studie

Prior‐guided automatic delineation of post‐radiotherapy gross tumor volume for esophageal cancer

Hongfei Sun, Ziqi An, Wei Huang, Qifeng Wang, Yufen Liu, Zihan Shi, Jie Li, Fan Meng, Jie Gong, Lina Zhao

Medical Physics · 2025

DOI: 10.1002/mp.70005 ↗

At a glance

Multizentrische Studie in Medical Physics, 2025. Written by Hongfei Sun and 9 co-authors. Institution: Department of Radiation Oncology, Xijing Hospital, Fourth Military Medical University, Xi'an, China. Major MEDLINE topics: Esophageal Neoplasms, Tumor Burden, Radiotherapy, Image-Guided. Cited 1 times so far (Crossref); 43 references. Funded by: National Natural Science Foundation of China.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Integrating post‐radiotherapy (RT) CT into longitudinal esophageal cancer response models substantially improves predictive accuracy. However, manual delineation of gross tumor volume (GTV) on post‐RT CT is both labor‐intensive and time‐consuming.

Purpose

We propose a novel deep learning–based framework that integrates medical physics priors—pre‐RT GTV contours and radiotherapy dose distributions—to automatically delineate post‐RT GTV.

Methods

A multicenter retrospective cohort of 294 EC patients (225 training, 45 internal validation, 24 external validation) was assembled. Pre‐RT CT scans, GTV contours, and dose map were co‐registered and cropped to 256 × 256. We implemented an nnU‐Net v2 backbone, incorporating high dose region and pre‐RT GTV priors via element‐wise multiplication and element‐wise addition to guide feature extraction. Performance was evaluated using anatomical (Dice, IoU, HD95, ASSD, Precision, Recall) and radiomics analyses (ICC, Pearson correlation, LASSO‐Cox, C‐index) across internal and external cohorts.

Results

In cross‐validation, the optimal fold achieved DSC = 0.7809 ± 0.1310, IoU = 0.6486 ± 0.1507, HD95 = 3.6321 ± 2.0942, and ASSD = 1.9673 ± 1.0352 ( p < 0.0167 vs. state‐of‐the‐art models). Ablation studies demonstrated that combining two types of medical physics priors outperformed single‐prior or no‐prior models (internal: DSC = 0.7723 ± 0.1290; external: DSC = 0.7545 ± 0.1058). Radiomic features extracted from automated contours exhibited high reproducibility (78.6% with ICC > 0.75) and strong concordance with manual features ( R > 0.8), yielding comparable prognostic performance (C‐index Δ nonsignificant).

Conclusion

By embedding medical physics priors into a self‐configuring nnU‐Net v2, our method achieves accurate and robust automated delineation of post‐ RT GTV in EC across multiple centers. This approach has potential to facilitate the construction of treatment response prediction models.

Subjects

MeSH terms (MEDLINE)

Esophageal NeoplasmsTumor BurdenRadiotherapy, Image-GuidedHumansRetrospective StudiesAutomationDeep LearningTomography, X-Ray ComputedRadiotherapy Planning, Computer-AssistedMaleFemale

Author keywords

automated delineationesophageal cancermedical physicsradiomicsradiotherapy

Authors and institutions

  • Department of Radiation Oncology, Xijing Hospital, Fourth Military Medical University, Xi'an, China.
  • Department of Radiation Oncology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China.
  • Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China.

Funding

  • National Natural Science Foundation of China

Cite

APA

Sun, H., An, Z., Huang, W., Wang, Q., Liu, Y., Shi, Z., Li, J., Meng, F., Gong, J., & Zhao, L. (2025). Prior‐guided automatic delineation of post‐radiotherapy gross tumor volume for esophageal cancer. Medical Physics. https://doi.org/10.1002/mp.70005

Vancouver

Sun H, An Z, Huang W, Wang Q, Liu Y, Shi Z, et al. Prior‐guided automatic delineation of post‐radiotherapy gross tumor volume for esophageal cancer. Medical Physics. 2025. doi:10.1002/mp.70005

BibTeX
@article{Sun2025,
  author = {Sun, Hongfei and An, Ziqi and Huang, Wei and Wang, Qifeng and Liu, Yufen and Shi, Zihan and Li, Jie and Meng, Fan and Gong, Jie and Zhao, Lina},
  title = {Prior‐guided automatic delineation of post‐radiotherapy gross tumor volume for esophageal cancer},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.70005}
}
Start for free →