Deep learning-based fusion of nuclear segmentation features for microsatellite instability and tumor mutational burden prediction in digestive tract cancers: a multicenter validation study
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf580 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Yanping Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Physics, Hebei University of Engineering, 19 Taiji Road, Handan 056038, China. Hauptthemen laut MEDLINE: Deep Learning, Microsatellite Instability, Mutation, Stomach Neoplasms. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National High Level Hospital Clinical Research Funding, Elite Medical Professionals Project of China-Japan Friendship Hospital, Beijing Chaoyang Digital Health Proof of Concept Project.
Abstract (Originalsprache)
Microsatellite instability (MSI) and tumor mutational burden (TMB) are crucial biomarkers in gastric (GC) and colorectal cancer (CRC), yet their conventional sequencing-based detection is costly and time-consuming. Since only ~20% of patients are MSI-high or TMB-high and likely to benefit from immunotherapy, expensive genomic testing is often unjustified. This study developed a deep learning framework to predict MSI and TMB status directly from routinely available Hematoxylin and Eosin (H&E)-stained whole-slide images, leveraging fused nuclear segmentation features to improve accuracy. Using samples from TCGA (350 GC and 376 CRC for MSI; 400 GC and 387 CRC for TMB), image features were extracted with CLAM and nuclear features with Hover-Net. These features were combined via Multimodal Compact Bilinear Pooling and utilized in six distinct deep learning models. By fusing the nucleus segmentation features, the model increased area under the receiver operating characteristic curve (AUC) by 1%–3% and recall by 5%–11% in five-fold cross-validation, significantly outperforming models that relied solely on image features. External validation on a CRC dataset from the China-Japan Friendship hospital further validated the model's robustness, achieving an AUC of 0.81 and a recall of 0.80 for MSI prediction. Additionally, notable differences in cellular composition were observed across cancer types and clinical groups, emphasizing the pivotal role of cellular features in cancer development. These findings highlight the advantages of integrating H&E-stained image features with nuclear segmentation data and advanced deep learning techniques to improve predictive accuracy and reduce the cost of MSI/TMB testing, potentially advancing personalized cancer treatment strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Mathematics and Physics, Hebei University of Engineering, 19 Taiji Road, Handan 056038, China.
- Department of Pathology, China-Japan Friendship Hospital, 2 East Yinghuayuan Street, Beijing 100029, China.
- Geneis Beijing Co., Ltd., 31 Xinbei Road, Beijing 100102, China.
- Academician Workstation, Changsha Medical University, 1501 Leifeng Road, Changsha 410219, China.
ORCID-Profile: Jiaying Han, Jialiang Yang
Förderung
- National High Level Hospital Clinical Research Funding
- Elite Medical Professionals Project of China-Japan Friendship Hospital
- Beijing Chaoyang Digital Health Proof of Concept Project
Zitieren
APA
Zhang, Y., Han, J., Chen, H., Hu, F., Huang, Y., Tian, G., Zhong, D., & Yang, J. (2025). Deep learning-based fusion of nuclear segmentation features for microsatellite instability and tumor mutational burden prediction in digestive tract cancers: a multicenter validation study. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf580
Vancouver
Zhang Y, Han J, Chen H, Hu F, Huang Y, Tian G, et al. Deep learning-based fusion of nuclear segmentation features for microsatellite instability and tumor mutational burden prediction in digestive tract cancers: a multicenter validation study. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf580
BibTeX
@article{Zhang2025,
author = {Zhang, Yanping and Han, Jiaying and Chen, Huang and Hu, Fengyuan and Huang, Yaping and Tian, Geng and Zhong, Dingrong and Yang, Jialiang},
title = {Deep learning-based fusion of nuclear segmentation features for microsatellite instability and tumor mutational burden prediction in digestive tract cancers: a multicenter validation study},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf580}
}
EUVIMED