BriefGPT.xyz
Apr, 2017
使用深度卷积神经网络方法自动进行肝脏病变分割
Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method
HTML
PDF
Xiao Han
TL;DR
利用深度卷积神经网络，以2.5D方式对肝脏CT图像进行分割，并在130个LiTS训练数据集上进行训练，在70个测试CT扫描上取得了平均Dice分数0.67，时隔ISBI2017会议后获得了该领域的第一名。
Abstract
liver lesion segmentation
is an important step for liver cancer diagnosis, treatment planning and treatment evaluation.
lits
(Liver Tumor Segmentation Challenge) provides a common testbed for comparing different
→