Less Is More: A Comparison of Active Learning Strategies for 3D Medical Image Segmentation
Less Is More: A Comparison of Active Learning Strategies for 3D Medical Image Segmentation
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.
Johannes Hagemann、Benjamin Bergner、Christoph Lippert、Simon Shabo、Josafat-Mattias Burmeister、Jonas Kordt、Marcel Fernandez Rosas、Jasper Blum
Digital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, GermanyDigital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, GermanyDigital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, GermanyDigital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, GermanyDigital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, GermanyDigital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, GermanyDigital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, GermanyDigital Health & Machine Learning, Hasso Plattner Institute, University of Potsdam, Germany
医学研究方法生物科学理论、生物科学方法计算技术、计算机技术
Johannes Hagemann,Benjamin Bergner,Christoph Lippert,Simon Shabo,Josafat-Mattias Burmeister,Jonas Kordt,Marcel Fernandez Rosas,Jasper Blum.Less Is More: A Comparison of Active Learning Strategies for 3D Medical Image Segmentation[EB/OL].(2022-07-02)[2025-07-25].https://arxiv.org/abs/2207.00845.点此复制
评论