期刊
BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2021, PT II
卷 12963, 期 -, 页码 173-186出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-09002-8_16
关键词
Brain tumor segmentation; Deep learning; nn-UNet
This paper presents the author's contribution to the brain tumor segmentation challenge in 2021, with modifications to the nn-UNet model resulting in first place in the final ranking for unseen test data, achieving high dice scores for different tumor regions.
Brain tumor segmentation is essential for the diagnosis and prognosis of patients with gliomas. The brain tumor segmentation challenge has provided an abundant and high-quality data source to develop automatic algorithms for the task. This paper describes our contribution to the 2021 competition. We developed our methods based on nn-UNet, the winning entry of last year's competition. We experimented with several modifications, including using a larger network, replacing batch normalization with group normalization and utilizing axial attention in the decoder. Internal 5-fold cross-validation and online evaluation from the organizers showed a minor improvement in quantitative metrics compared to the baseline. The proposed models won first place in the final ranking on unseen test data, achieving a dice score of 88.35%, 88.78%, 93.19% for the enhancing tumor, the tumor core, and the whole tumor, respectively. The codes, pretrained weights, and docker image for the winning submission are publicly available.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据