2022/07/02 by Josafat-Mattias Burmeister, Marcel Fernandez Rosas, Burmeister, Josafat-Mattias +13
Computer Science · Medicine · #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #I.2.10 #I.4.6 #J.3 #Machine Learning (cs.LG) #Machine Learning and Algorithms
paper · pdf · doi:10.48550/arxiv.2207.00845
openalex publication_date 2022/07/02 · openalex created_date 2022/07/07 · openalex updated_date 2026/07/28
Since labeling medical image data is a costly and labor-intensive process, active learning has gained much popularity in the medical image segmentation domain in recent years. A variety of active learning strategies have been proposed in the literature, but their effectiveness is highly dependent on the dataset and training scenario. To facilitate the comparison of existing strategies and provide a baseline for evaluating novel strategies, we evaluate the performance of several well-known active learning strategies on three datasets from the Medical Segmentation Decathlon. Additionally, we consider a strided sampling strategy specifically tailored to 3D image data. We demonstrate that both random and strided sampling act as strong baselines and discuss the advantages and disadvantages of the studied methods. To allow other researchers to compare their work to our results, we provide an open-source framework for benchmarking active learning strategies on a variety of medical segmentation datasets.