Less Is More: A Comparison of Active Learning Strategies for 3D Medical Image Segmentation
This work provides a benchmarking framework for researchers to evaluate active learning methods in medical image segmentation, though it is incremental as it compares existing strategies without introducing a new method.
The paper compared active learning strategies for 3D medical image segmentation to reduce labeling costs, finding that random and strided sampling serve as strong baselines across three datasets from the Medical Segmentation Decathlon.
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.