Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets

Abstract

Deep learning models are notoriously data-hungry, a fundamental obstacle for specialized medical tasks where annotated data is scarce. We perform a carefully controlled experiment on segmenting the layers of the artery wall from only nine annotated histology images. We compare standard convolutional architectures, pre-trained on a large public histology corpus, against a vision foundation model guided by a systematic and reproducible prompting curriculum.

Download Paper