[3Win5] Poster session 3

[3Win5-98] Few-Shot Learning with SAM2 in Endoscopic Videos: High-Precision Lesion Detection through Bidirectional Prediction and Weight Control

〇Ryotaro Okazaki¹, Atsushi Ikeda¹, Wonjik Kim², Hirokazu Nosato², Hiroyuki Nishiyama¹ (1.University of Tsukuba, 2.National Institute of Advanced Industrial Science and Technology)

Keywords: Deep Learning, image recognition, Segmentation, Medical Application

In the development of medical image AI, the burden of collecting training data and creating annotations remains a significant challenge. This study proposes a novel approach utilizing SAM2 (Segment Anything Model 2), developed by Meta, as a foundation model to achieve high-precision lesion detection in endoscopic images with minimal annotated data. The proposed method enhances SAM2's superior segmentation capabilities with two key extensions specifically designed for endoscopic video challenges: a bidirectional prediction mechanism and a weight decay system. Through evaluation experiments using cystoscopic videos, we demonstrated that our approach achieves comparable or superior performance to conventional deep learning methods and models trained on large-scale datasets, despite using only a small number of annotations. These findings present a new approach for efficient dataset construction in medical image AI development.