基于nnU-Net的乳腺DCE-MR图像中乳房和腺体自动分割
霍璐1,2,胡晓欣3,肖勤3,顾雅佳3,褚旭1,4,姜娈1,*(
)
)
Automatic Segmentation of Breast and Fibroglandular Tissues in DCE-MR Images Based on nnU-Net
Lu HUO1,2,Xiao-xin HU3,Qin XIAO3,Ya-jia GU3,Xu CHU1,4,Luan JIANG1,*()
)
图7. 不同乳腺密度类别的乳腺DCE-MR图像分割结果示例.从上至下，依次为乳腺密度类别Ⅰ、类别Ⅱ、类别Ⅲ和类别Ⅳ的代表性样本（Ⅰ-脂肪： < 25%；Ⅱ-分散：25% ~ 50%；Ⅲ-非均匀致密：50% ~ 75%；Ⅳ-致密： > 75%）.从左至右，分别为原始图像、乳房分割的金标准、乳房分割结果、腺体（FGT）分割的金标准和腺体分割结果
Fig.7. Segmentation examples of four groups with different breast density ratings. From top down: Category I, Category Ⅱ, Category Ⅲ and Category Ⅳ (Ⅰ - fatty: < 25%; Ⅱ - scattered: 25% ~ 50%; Ⅲ - heterogeneously dense: 50% ~ 75%; Ⅳ - dense: > 75%). From left to right: the original image, the ground truth of whole breast, the segmentation mask of whole breast, the ground truth of FGT, and the segmentation mask of FGT
