Multiple instance learning approach for automated gallbladder cancer detection using ultrasound imaging: multi-center validation of a deep learning model
The Lancet Regional Health - Southeast Asia · 2026-04 · 47 · 100737
DOI: 10.1016/j.lansea.2026.100737 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Lancet Regional Health - Southeast Asia, 2026-04. Verfasst von Pankaj Gupta und 22 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiodiagnosis, Postgraduate Institute of Medical Education and Research, Chandigarh, 160012, India. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background
Gallbladder cancer (GBC) diagnosis is challenging due to overlapping imaging features. We developed and validated a multiple instance learning (MIL) model for automated GBC detection using a large-scale multi-center ultrasound dataset and benchmarked it against state-of-the-art architectures.
Methods
This was a retrospective and prospective multi-center cohort study. We trained a gated attention MIL (GAIA-MIL) model on the prospective AURORA-GB dataset (August 2022-July 2024) and two public datasets. The model was evaluated on a temporally independent internal test set (August 2024-December 2024) and three retrospective external cohorts. The area under curve (AUC), sensitivity, and specificity of GAIA-MIL was compared to Clustering-constrained Attention MIL (CLAM), Dual-Stream MIL (DS-MIL), and Transformer-based MIL (TransMIL).
Findings
The datasets comprised 11,012 images from 1151 patients. Cross-validation achieved a mean AUC of 0.874 (95% CI 0.846-0.902). On the internal test set (n = 97), GAIA-MIL achieved 87.7% sensitivity (78.9-95.1%), 86.2% specificity (72.4-96.9%), and an AUC of 0.883 (0.786-0.963). Pooled external validation (n = 122) showed an AUC of 0.778 (0.698-0.852). Performance varied by external center (AUCs: 0.722, 0.950, and 0.749). In comparative benchmarking, while TransMIL excelled internally (AUC 0.871), its performance degraded significantly in external validation (Pooled AUC 0.654). GAIA-MIL demonstrated superior stability, maintaining robust sensitivity (78.2%), specificity (73.4%), and AUC (0.778) pooled across all diverse external centers where complex transformers struggled. Interpretability analysis confirmed the model focused on clinically relevant features like wall thickening.
Interpretation
While complex architectures like TransMIL perform well internally, GAIA-MIL offers the optimal balance of performance and generalizability for multi-center deployment. The AURORA-GB benchmark dataset is publicly released to advance research. Funding: None.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiodiagnosis, Postgraduate Institute of Medical Education and Research, Chandigarh, 160012, India.
- Department of Clinical Hematology and Medical Oncology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160012, India.
- Department of GI Surgery, HBP and Liver Transplantation, Postgraduate Institute of Medical Education and Research, Chandigarh, 160012, India.
- Department of General Surgery, Postgraduate Institute of Medical Education and Research, Chandigarh, 160012, India.
- Division of Radiation Oncology, Postgraduate Institute of Medical Education and Research, Chandigarh, 160012, India.
- Department of Radiodiagnosis, Tata Memorial Hospital, Mumbai, 40012, India.
Zitieren
APA
Gupta, P., Bose, K., Mudgil, P., Dutta, N., Gulati, A., Prakash, G., Yadav, T. D., Kaman, L., Irrinki, S., Singh, H., Khosla, D., Unde, H., Shetty, N., Kumar, I., Chalapati, V., Verma, A., Pruthi, H., Bansal, H., Sen, J., …, & Dutta, U. (2026). Multiple instance learning approach for automated gallbladder cancer detection using ultrasound imaging: multi-center validation of a deep learning model. The Lancet Regional Health - Southeast Asia, 47, 100737. https://doi.org/10.1016/j.lansea.2026.100737
Vancouver
Gupta P, Bose K, Mudgil P, Dutta N, Gulati A, Prakash G, et al. Multiple instance learning approach for automated gallbladder cancer detection using ultrasound imaging: multi-center validation of a deep learning model. The Lancet Regional Health - Southeast Asia. 2026;47:100737. doi:10.1016/j.lansea.2026.100737
BibTeX
@article{Gupta2026,
author = {Gupta, Pankaj and Bose, Kartik and Mudgil, Priya and Dutta, Niharika and Gulati, Ajay and Prakash, Gaurav and Yadav, Thakur Deen and Kaman, Lileswar and Irrinki, Santosh and Singh, Harjeet and Khosla, Divya and Unde, Himangi and Shetty, Nitin and Kumar, Ishan and Chalapati, Viswaja and Verma, Ashish and Pruthi, Himanshu and Bansal, Himika and Sen, Jyotsna and Kapoor, Rakesh and Gupta, Rajesh and Arora, Chetan and Dutta, Usha},
title = {Multiple instance learning approach for automated gallbladder cancer detection using ultrasound imaging: multi-center validation of a deep learning model},
journal = {The Lancet Regional Health - Southeast Asia},
year = {2026},
volume = {47},
pages = {100737},
doi = {10.1016/j.lansea.2026.100737}
}
EUVIMED