Predictive Accuracy-Based Active Learning for Medical Image Segmentation

arXiv:2405.00452v1 Announce Type: new
Abstract: Active learning is considered a viable solution to alleviate the contradiction between the high dependency of deep learning-based segmentation methods on annotated data and the expensive pixel-level annotation cost of medical images. However, most existing methods suffer from unreliable uncertainty assessment and the struggle to balance diversity and informativeness, leading to poor performance in segmentation tasks. In response, we propose an efficient Predictive Accuracy-based Active Learning (PAAL) method for medical image segmentation, first introducing predictive …

accuracy active learning arxiv cs.cv image medical predictive segmentation type