Predicting Intratumoral Heterogeneity and Stratifying Prognostic Risk in Gastric Cancer Using a Histology–Based Pathomics-Deep Learning Fusion Model
Modern Pathology · 2026
DOI: 10.1016/j.modpat.2026.101057 ↗Kurz gefasst
Fachartikel in der Zeitschrift Modern Pathology, 2026. Verfasst von Shulun Nie und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Oncology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China. Hauptthemen laut MEDLINE: Stomach Neoplasms, Deep Learning. Die Arbeit nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Intratumoral heterogeneity (ITH) is a fundamental driver of clonal evolution and therapeutic resistance in gastric cancer (GC). However, the clinical assessment of ITH remains limited by the high cost and technical complexity of multiregion and single-cell sequencing. This study aimed to develop a pathomics-deep learning (DL) fusion model for estimating ITH directly from routine hematoxylin and eosin-stained whole-slide images in GC. We retrospectively collected 893 whole-slide images from 773 patients in 3 independent cohorts. ITH was quantified using 8 algorithms, and the optimal prognostic indicator was identified by Cox regression analysis. Pathomics features were extracted using CellProfiler, whereas DL features were generated using ResNet50 combined with 2 multiple instance learning pipelines. A pathology-driven stacking ensemble model integrating pathomics and DL features was then constructed. A total of 239, 103, 135, and 30 patients were included in the training, internal validation, and 2 external test cohorts, respectively. The mutant-allele tumor heterogeneity (MATH) score was identified as an independent prognostic factor for overall survival (hazard ratio, 1.840; 95% CI, 1.144-2.957; P =.012). Biological relevance analysis showed that high-MATH tumors were characterized by increased chromosomal instability and an immunosuppressive microenvironment, whereas low-MATH tumors were associated with immune-active phenotypes. The pathology-driven stacking ensemble model showed favorable performance in predicting MATH-defined ITH status, with areas under the curve of 0.852 to 0.956 across the training, validation, and test cohorts. Moreover, the model-derived ITH risk score was an independent prognostic factor and effectively stratified patients into high- and low-risk groups with significantly distinct overall survival outcomes (all P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Medical Oncology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China.
- Department of Pathology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China.
- Department of Pathology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, Qingdao, Shandong, China.
- Department of Medical Oncology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, China. Electronic address: lianliu@sdu.edu.cn.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Nie, S., Shi, D., Song, S., Xu, Q., Ma, M., Xia, B., Hu, J., Xu, L., Li, S., & Liu, L. (2026). Predicting Intratumoral Heterogeneity and Stratifying Prognostic Risk in Gastric Cancer Using a Histology–Based Pathomics-Deep Learning Fusion Model. Modern Pathology. https://doi.org/10.1016/j.modpat.2026.101057
Vancouver
Nie S, Shi D, Song S, Xu Q, Ma M, Xia B, et al. Predicting Intratumoral Heterogeneity and Stratifying Prognostic Risk in Gastric Cancer Using a Histology–Based Pathomics-Deep Learning Fusion Model. Modern Pathology. 2026. doi:10.1016/j.modpat.2026.101057
BibTeX
@article{Nie2026,
author = {Nie, Shulun and Shi, Duanbo and Song, Shuyi and Xu, Qian and Ma, Mingchi and Xia, Beian and Hu, Jin and Xu, Lixiu and Li, Song and Liu, Lian},
title = {Predicting Intratumoral Heterogeneity and Stratifying Prognostic Risk in Gastric Cancer Using a Histology–Based Pathomics-Deep Learning Fusion Model},
journal = {Modern Pathology},
year = {2026},
doi = {10.1016/j.modpat.2026.101057}
}
EUVIMED