Fully automated 3D multi-modal deep learning model for preoperative T-stage prediction of colorectal cancer using 18F-FDG PET/CT
European Journal of Nuclear Medicine and Molecular Imaging · 2026-01 · 53 (2) · 910-920
DOI: 10.1007/s00259-025-07450-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, online erschienen am 28.07.2025. Verfasst von Mobei Zhang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering, School of Electronic Engineering, Xidian University, Xi'an, Shaanxi Province, China. Hauptthemen laut MEDLINE: Positron Emission Tomography Computed Tomography, Deep Learning, Fluorodeoxyglucose F18, Colorectal Neoplasms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: National Natural Science Foundation, Basic and Applied Basic Research Foundation of Guangdong Province, Nanfang Hospital Talent Introduction Foundation of Southern Medical University.
Abstract (Originalsprache)
PURPOSE: This study aimed to develop a fully automated 3D multi-modal deep learning model using preoperative 18F-FDG PET/CT to predict the T-stage of colorectal cancer (CRC) and evaluate its clinical utility. METHODS: A retrospective cohort of 474 CRC patients was included, with 400 patients for internal cohort and 74 patients for external cohort. Patients were classified into early T-stage (T1-T2) and advanced T-stage (T3-T4) groups. Automatic segmentation of the volume of interest (VOI) was achieved based on TotalSegmentator. A 3D ResNet18-based deep learning model integrated with a cross-multi-head attention mechanism was developed. Five models (CT + PET + Clinic (CPC), CT + PET (CP), PET (P), CT (C), Clinic) and two radiologists' assessment were compared. Performance was evaluated using Area Under the Curve (AUC). Grad-CAM was employed to provide visual interpretability of decision-critical regions. RESULTS: The automated segmentation achieved Dice scores of 0.884 (CT) and 0.888 (PET). The CPC and CP models achieved superior performance, with AUCs of 0.869 and 0.869 in the internal validation cohort, respectively, outperforming single-modality models (P: 0.832; C: 0.809; Clinic: 0.728) and the radiologists (AUC: 0.627, P < 0.05 for all models vs. radiologists, except for the Clinical model). External validation exhibited a similar trend, with AUCs of 0.814, 0.812, 0.763, 0.714, 0.663 and 0.704, respectively. Grad-CAM visualization highlighted tumor-centric regions for early T-stage and peri-tumoral tissue infiltration for advanced T-stage. CONCLUSION: The fully automated multimodal, fusing PET/CT with cross-multi-head-attention, improved T-stage prediction in CRC, surpassing the single-modality models and radiologists, offering a time-efficient tool to aid clinical decision-making.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Electronic Engineering, School of Electronic Engineering, Xidian University, Xi'an, Shaanxi Province, China.
- Nanfang PET Center, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.
- GDMPA Key Laboratory for Quality Control and Evaluation of Radiopharmaceuticals, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.
- Department of Nuclear Medicine, State Key Laboratory of Complex Severe and Rare Diseases, Beijing Key Laboratory of Molecular Targeted Diagnosis and Therapy in Nuclear Medicine, Peking Union Medical College Hospital, Ch…
- Nanfang PET Center, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China. wuhbym@163.com.
- GDMPA Key Laboratory for Quality Control and Evaluation of Radiopharmaceuticals, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China. wuhbym@163.com.
ORCID-Profile: Yinfeng Li
Förderung
- National Natural Science Foundation
- Basic and Applied Basic Research Foundation of Guangdong Province
- Nanfang Hospital Talent Introduction Foundation of Southern Medical University
- President Foundation of Nanfang Hospital, Southern Medical University
Zitieren
APA
Zhang, M., Li, Y., Zheng, C., Xie, F., Zhao, Z., Dai, F., Wang, J., Wu, H., Zhu, Z., Liu, Q., & Li, Y. (2026). Fully automated 3D multi-modal deep learning model for preoperative T-stage prediction of colorectal cancer using 18F-FDG PET/CT. European Journal of Nuclear Medicine and Molecular Imaging, 53(2), 910-920. https://doi.org/10.1007/s00259-025-07450-5
Vancouver
Zhang M, Li Y, Zheng C, Xie F, Zhao Z, Dai F, et al. Fully automated 3D multi-modal deep learning model for preoperative T-stage prediction of colorectal cancer using 18F-FDG PET/CT. European Journal of Nuclear Medicine and Molecular Imaging. 2026;53(2):910-920. doi:10.1007/s00259-025-07450-5
BibTeX
@article{Zhang2026,
author = {Zhang, Mobei and Li, Yufan and Zheng, Chunhong and Xie, Fei and Zhao, Zhenwei and Dai, Fahao and Wang, Jiarou and Wu, Hubing and Zhu, Zhaohui and Liu, Qingxing and Li, Yinfeng},
title = {Fully automated 3D multi-modal deep learning model for preoperative T-stage prediction of colorectal cancer using 18F-FDG PET/CT},
journal = {European Journal of Nuclear Medicine and Molecular Imaging},
year = {2026},
volume = {53},
number = {2},
pages = {910--920},
doi = {10.1007/s00259-025-07450-5}
}
EUVIMED