Rethinking deep active learning for medical image segmentation: A diffusion and angle-based framework
Lists
Only you see this
Abstract
Highlights•Introduce DifABAL, a one-shot active learning framework for medical image segmentation.•Utilize diffusion model-based autoencoders to extract features from unlabeled samples.•Develop a novel angle-based query strategy that is robust to parameter changes.•Demonstrate remarkable performance on pathology, chest X-ray, and dermatology images.
BibTeX
@article{qu2024rethinking,
author = {Linhao Qu and Qiuye Jin and Kexue Fu and Manning Wang and Zhijian Song},
title = {{Rethinking deep active learning for medical image segmentation: A diffusion and angle-based framework}},
journal = {Biomedical Signal Processing and Control},
year = {2024},
doi = {10.1016/j.bspc.2024.106493},
}Loading related content...