Cascaded atrous dual attention U-Net for tumor segmentation
- PDF / 5,510,334 Bytes
- 25 Pages / 439.642 x 666.49 pts Page_size
- 65 Downloads / 212 Views
Cascaded atrous dual attention U-Net for tumor segmentation Yu-Cheng Liu1 · Mohammad Shahid1 · Wannaporn Sarapugdi1 · Yong-Xiang Lin1 · Jyh-Cheng Chen2 · Kai-Lung Hua3 Received: 8 April 2020 / Revised: 25 September 2020 / Accepted: 13 October 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Automatic segmentation of the organ’s tumor and lesion on biomedical imaging is an essential initiative towards clinical study, treatment planning and digital biomedical research. However, precise tumor segmentation on medical imaging is still an open challenge due to the presence of noise in the imaging sequence, the similar tumor pixel intensity with its neighboring tissues, and heterogeneity among human anatomy. Although most of the stateof-the-art algorithms are architecturally dependent on deep convolution networks (DCNs), like 2D and 3D U-Net, they act as a foundation for many biomedical image segmentation. However, 2D DCNs are incompetent to leverage context information from inter-slice completely. At the same time, 3D DCNs can accumulate inter-slice contextual information over the sizeable receptive texture in the organ, but it consumes a considerable amount of GPU memory and burdens with the high execution cost. In order to achieve a promising solution, we proposed a segmentation network called Cascaded Atrous Dual-Attention UNet. First, our network structure concatenates features from 3D liver segmentation to 2D tumor segmentation for preserving volumetric information as well as enlarging resolution with segmentation accuracy. Second, we embedded dual attention gate in each skip connection layer of the 2D segmentation model, which determines to concentrate on certain discriminative features in order to find tumor segmentation in different organs. Finally, we adopted atrous encoder which extracts wider context features from computed tomography as compared to normal encoder. Furthermore, we tested the proposed method on four different datasets, including liver tumor segmentation benchmark (LiTS), MSD liver, pancreas tumor segmentation and Kidney tumor segmentation (KiTS). Experimental results were compared with the other state-of-the-art segmentation methods. Our proposed approach performs remarkably better than existing methods with around 4 ∼ 6% improvement on each benchmark. Keywords CT image segmentation · Tumor segmentation · Atrous encoder · Attention gate
Jyh-Cheng Chen
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
1 Introduction Cancer is one of the most prevalent reasons for death in the world each year [51]. Hepatocellular carcinoma, a class of liver tumor, is considered to be the sixth-largest malignant cancer in the world and the third-largest deadly disease. The most prominent method used for diagnosing specific cancers (e.g. liver) is multi-planar MRI scans or computed tomography (CT) scans. Such techniques of biomedical imaging help medical practitioners and researchers to examine densit
Data Loading...
