TY - JOUR
T1 - Cascade U-ResNets for Simultaneous Liver and Lesion Segmentation
AU - Xi, Xue Feng
AU - Wang, Lei
AU - Sheng, Victor S.
AU - Cui, Zhiming
AU - Fu, Baochuan
AU - Hu, Fuyuan
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020
Y1 - 2020
N2 - In recent years, several deep learning networks are proposed to segment 2D or 3D bio-medical images. However, in liver and lesion segmentation, the proportion of interested tissues and lesions are tiny when contrasting to the image background. That is, the objects to be segmented are highly imbalanced in terms of the frequency of occurrences. This makes existing deep learning networks prone to predict pixels of livers and lesions as background. To address this imbalance issue, several loss functions are proposed. Since no researches are having made a comparison among those proposed loss functions, we are curious about that which loss function is the best among them? At the same time, we also want to investigate whether the combination of several different loss functions is effective for liver and lesion segmentation. Firstly, we propose a novel deep learning network (cascade U-ResNets) to produce liver and lesion segmentation simultaneously. Then, we investigate the performance of 5 selected loss functions, WCE (Weighted Cross Entropy), DL (Dice Loss), WDL (Weighted Dice Loss), TL (Teverskry Loss), WTL (Weighted Teversky Loss), with our cascade U-ResNets. We further assemble all cascade U-ResNets trained with different loss functions together to segment livers and lesions jointly on the liver CT (Computed Tomography) volume. Experimental results on the LiTS dataset1 showed our ensemble model can achieve much better results than every individual model for liver segmentation.1http://competitions.codalab.org/competitions/17094#
AB - In recent years, several deep learning networks are proposed to segment 2D or 3D bio-medical images. However, in liver and lesion segmentation, the proportion of interested tissues and lesions are tiny when contrasting to the image background. That is, the objects to be segmented are highly imbalanced in terms of the frequency of occurrences. This makes existing deep learning networks prone to predict pixels of livers and lesions as background. To address this imbalance issue, several loss functions are proposed. Since no researches are having made a comparison among those proposed loss functions, we are curious about that which loss function is the best among them? At the same time, we also want to investigate whether the combination of several different loss functions is effective for liver and lesion segmentation. Firstly, we propose a novel deep learning network (cascade U-ResNets) to produce liver and lesion segmentation simultaneously. Then, we investigate the performance of 5 selected loss functions, WCE (Weighted Cross Entropy), DL (Dice Loss), WDL (Weighted Dice Loss), TL (Teverskry Loss), WTL (Weighted Teversky Loss), with our cascade U-ResNets. We further assemble all cascade U-ResNets trained with different loss functions together to segment livers and lesions jointly on the liver CT (Computed Tomography) volume. Experimental results on the LiTS dataset1 showed our ensemble model can achieve much better results than every individual model for liver segmentation.1http://competitions.codalab.org/competitions/17094#
KW - Data imbalance
KW - deep learning
KW - ensemble learning
KW - lesion segmentation
KW - liver segmentation
KW - medical image segmentation
UR - http://www.scopus.com/inward/record.url?scp=85083969403&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.2985671
DO - 10.1109/ACCESS.2020.2985671
M3 - Article
AN - SCOPUS:85083969403
SN - 2169-3536
VL - 8
SP - 68944
EP - 68952
JO - IEEE Access
JF - IEEE Access
M1 - 9057545
ER -