Automatic Segmentation of Liver Tumor in Multiphase CT Images by Mask R-CNN
Ryô Hasegawa, Yutaro Iwamoto, Lanfen Lin, Hongjie Hu, Yen‐Wei Chen · 2020 IEEE 2nd Global Conference on Life Sciences and Technologies (LifeTech) · 2020
In computer-aided diagnosis of liver tumors, tumor detection and segmentation are essential preprocessing steps. In this study, we proposed a method based on mask R-CNN to detect and segment the liver tumor in a multi-phase CT image simultaneously. Triple phase images are used as three different channels just like a color RGB image. The segmentation accuracy (Dice value) is about 0.60 ~ 0.66 for a single phase CT image, while the accuracy can be improved to about 0.73 by using the multi-phase CT image.