TY - JOUR
T1 - Automatic liver segmentation from abdominal CT volumes using improved convolution neural networks
AU - Liu, Zhe
AU - Han, Kai
AU - Wang, Zhaohui
AU - Zhang, Jing
AU - Song, Yuqing
AU - Yao, Xu
AU - Yuan, Deqi
AU - Sheng, Victor S.
N1 - Publisher Copyright:
© 2020, Springer-Verlag GmbH Germany, part of Springer Nature.
PY - 2021/2
Y1 - 2021/2
N2 - Segmentation of the liver from abdominal CT images is an essential step for computer-aided diagnosis and surgery planning. The U-Net architecture is one of the most well-known CNN architectures which achieved remarkable successes in both medical and biological image segmentation domain. However, it does not perform well when the target area is small or partitioned. In this paper, we propose a novel architecture, called dense feature selection U-Net (DFS U-Net), which addresses this challenging problem. Specifically, The Hounsfield unit values were windowed in a range to exclude irrelevant organs, and then use the pre-processed data to train our proposed DFS U-Net model. To further improve the segmentation accuracy of the small region and disconnected regions of interests with limited training datasets, we improve the loss function by adding a parameter to the formula. With respect to the ground truth, the Dice score ratio can reach over 94.9% for the liver. Our experimental results demonstrate its potential in clinical usage with high effectiveness, robustness and efficiency.
AB - Segmentation of the liver from abdominal CT images is an essential step for computer-aided diagnosis and surgery planning. The U-Net architecture is one of the most well-known CNN architectures which achieved remarkable successes in both medical and biological image segmentation domain. However, it does not perform well when the target area is small or partitioned. In this paper, we propose a novel architecture, called dense feature selection U-Net (DFS U-Net), which addresses this challenging problem. Specifically, The Hounsfield unit values were windowed in a range to exclude irrelevant organs, and then use the pre-processed data to train our proposed DFS U-Net model. To further improve the segmentation accuracy of the small region and disconnected regions of interests with limited training datasets, we improve the loss function by adding a parameter to the formula. With respect to the ground truth, the Dice score ratio can reach over 94.9% for the liver. Our experimental results demonstrate its potential in clinical usage with high effectiveness, robustness and efficiency.
KW - Automatic liver segmentation
KW - DFS U-Net
KW - Feature selection
KW - Threshold deconvolution
UR - http://www.scopus.com/inward/record.url?scp=85095716611&partnerID=8YFLogxK
U2 - 10.1007/s00530-020-00709-x
DO - 10.1007/s00530-020-00709-x
M3 - Article
AN - SCOPUS:85095716611
SN - 0942-4962
VL - 27
SP - 111
EP - 124
JO - Multimedia Systems
JF - Multimedia Systems
IS - 1
ER -