Deep learning-based CT model for non-invasive prediction of tertiary lymphoid structures in pancreatic cancer: a multicenter study with prospective validation in an immunochemotherapy cohort
Journal for ImmunoTherapy of Cancer · 2026
DOI: 10.1136/jitc-2026-015705 ↗Kurz gefasst
Klinische Studie (Phase I) in der Zeitschrift Journal for ImmunoTherapy of Cancer, 2026. Verfasst von Haopeng Yu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China. Hauptthemen laut MEDLINE: Carcinoma, Pancreatic Ductal, Deep Learning, Immunotherapy, Pancreatic Neoplasms. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: the 1.3.5 Project for Disciplines of Excellence, West China Hospital, Sichuan University, Sichuan Science and Technology Department Key Research and Development Project, National Key Research and Development Program of China.
Abstract (Originalsprache)
Background
Pancreatic ductal adenocarcinoma (PDAC) remains one of the most lethal malignancies. Tertiary lymphoid structures (TLS) have emerged as key components of the tumor immune microenvironment, associated with improved survival and enhanced immunotherapy response. However, non-invasive detection of TLS remains a significant clinical challenge.
Objective
This multicenter study aimed to develop and validate a deep learning-based CT model to noninvasively predict TLS status and evaluate its prognostic and predictive value across surgical, non-surgical, and prospective immunochemotherapy cohorts. Materials and methods We enrolled 223 surgically resected patients with PDAC from two centers for model development and 82 non-surgical patients for clinical validation. A ResNet50-based deep learning network (DLN) was trained to predict TLS status from preoperative contrast-enhanced CT. The locked model was evaluated in 44 patients from a prospective immunochemotherapy trial (ChiCTR2000032293), with pathology-anchored verification, outcome assessment, and spatial immune profiling via cyclic multiplex tyramide signal amplification.
Results
The DLN achieved area under the curves (AUCs) of 0.987, 0.937, and 0.853 in training, internal, and external validation cohorts. In the non-surgical cohort (n=82), DLN-predicted TLS-positive patients had significantly longer overall survival (OS; median 19 vs 7 months; HR=3.611, p
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China.
- Health and Management Center, General Practice Medical Center, West China Hospital of Sichuan University, Chengdu, Sichuan, China.
- Division of Abdominal Tumor, Department of Medical Oncology, Cancer Center, Laboratory of Abdominal Tumor Immunology and Microenvironment, State Key Laboratory of Biotherapy, West China Hospital of Sichuan University, C…
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.
- Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China.
- Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital of Sichuan University, Chengdu, Sichuan, China.
Förderung
- the 1.3.5 Project for Disciplines of Excellence, West China Hospital, Sichuan University
- Sichuan Science and Technology Department Key Research and Development Project
- National Key Research and Development Program of China
- Sichuan Science and Technology Program
- National Natural Science Foundation of China
Zitieren
APA
Yu, H., Li, X., Cheng, X., Deng, Y., Wang, Y., Li, Y., Liu, B., Huang, Z., & Cao, D. (2026). Deep learning-based CT model for non-invasive prediction of tertiary lymphoid structures in pancreatic cancer: a multicenter study with prospective validation in an immunochemotherapy cohort. Journal for ImmunoTherapy of Cancer. https://doi.org/10.1136/jitc-2026-015705
Vancouver
Yu H, Li X, Cheng X, Deng Y, Wang Y, Li Y, et al. Deep learning-based CT model for non-invasive prediction of tertiary lymphoid structures in pancreatic cancer: a multicenter study with prospective validation in an immunochemotherapy cohort. Journal for ImmunoTherapy of Cancer. 2026. doi:10.1136/jitc-2026-015705
BibTeX
@article{Yu2026,
author = {Yu, Haopeng and Li, Xiaoying and Cheng, Xuan and Deng, Yan and Wang, Yuqi and Li, Yu and Liu, Bingjie and Huang, Zixing and Cao, Dan},
title = {Deep learning-based CT model for non-invasive prediction of tertiary lymphoid structures in pancreatic cancer: a multicenter study with prospective validation in an immunochemotherapy cohort},
journal = {Journal for ImmunoTherapy of Cancer},
year = {2026},
doi = {10.1136/jitc-2026-015705}
}
EUVIMED