Skip to main navigation Skip to search Skip to main content

Evaluating Transfer Learning and Multiple Instance Learning for Domain-Specific Endoscopic Video Classification

  • University College of Cork,APC Microbiome Ireland, College of Medicine and Health,Cork,Ireland
  • Universitat Politecnica de Valencia, Instituto de Investigación e Innovación en Bioingeniería, HUMAN-Tech
  • Department of Gastrointestinal Oncological Surgery, Santa Maria del Prato Hospital, Feltre, Italy
  • University Hospitals Leuven,Division of Gastroenterology,Leuven,Belgium

Research output: Contribution to conference › Paper › peer-review

5 Downloads (Pure)

Abstract

Inflammatory Bowel Disease (IBD) is commonly assessed through endoscopy, but manual interpretation suffers from interobserver variability and limited scalability. Deep learning models offer a path toward standardizing evaluations, yet their effectiveness is constrained by limited task-specific data and the complexity of video-based scoring. Transfer learning from large image datasets like ImageNet is often used to address data scarcity, but such general-purpose features may not align well with medical imagery. This paper investigates the effectiveness of domain specific pretraining for endoscopic video classification under weak supervision. We apply a multiple instance learning (MIL) framework to classify inflammation status from endoscopy videos using a range of deep learning architectures pretrained on either ImageNet, general medical images, or the domain-specific GastroNet5M dataset. Our findings show that models pretrained on endoscopy-specific data consistently outperform general-purpose models across both internal and external datasets, achieving superior F1 Score and AUC values. These results highlight the importance of domain-aligned feature representations and weakly supervised learning strategies in medical video analysis.
Original languageEnglish
Publication statusPublished - 24 Nov 2025
Event32nd International Conference on Neural Information Processing - Okinawa Institute of Science and Technology, Okinawa, Japan
Duration: 20 Nov 2025 → 24 Nov 2025
https://iconip2025.apnns.org/

Conference

Conference32nd International Conference on Neural Information Processing
Abbreviated titleICONIP 2025
Country/TerritoryJapan
CityOkinawa
Period20/11/25 → 24/11/25
Internet address

Cite this