Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors
The liver is an irreplaceable organ in the human body, maintaining life activities and metabolism. Malignant tumors of the liver have a high mortality rate at present. Computer-aided segmentation of the liver and tumors has significant effects on clinical diagnosis and treatment. There are still man...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/11/10/1044 |
| _version_ | 1797514097318690816 |
|---|---|
| author | Yan Zhu Aihong Yu Huan Rong Dongqing Wang Yuqing Song Zhe Liu Victor S. Sheng |
| author_facet | Yan Zhu Aihong Yu Huan Rong Dongqing Wang Yuqing Song Zhe Liu Victor S. Sheng |
| author_sort | Yan Zhu |
| collection | DOAJ |
| description | The liver is an irreplaceable organ in the human body, maintaining life activities and metabolism. Malignant tumors of the liver have a high mortality rate at present. Computer-aided segmentation of the liver and tumors has significant effects on clinical diagnosis and treatment. There are still many challenges in the segmentation of the liver and liver tumors simultaneously, such as, on the one hand, that convolutional kernels with fixed geometric structures do not match complex, irregularly shaped targets; on the other, pooling during convolution results in a loss of spatial contextual information of images. In this work, we designed a cascaded U-ADenseNet with coarse-to-fine processing for addressing the above issues of fully automatic segmentation. This work contributes multi-resolution input images and multi-layered channel attention combined with atrous spatial pyramid pooling densely connected in the fine segmentation. The proposed model was evaluated by a public dataset of the Liver Tumor Segmentation Challenge (LiTS). Our approach attained competitive liver and tumor segmentation scores that exceeded other methods across a wide range of metrics. |
| first_indexed | 2024-03-10T06:26:48Z |
| format | Article |
| id | doaj.art-4e29d451982b444aafa2fd614d39eaf3 |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-10T06:26:48Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-4e29d451982b444aafa2fd614d39eaf32023-11-22T18:49:48ZengMDPI AGJournal of Personalized Medicine2075-44262021-10-011110104410.3390/jpm11101044Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and TumorsYan Zhu0Aihong Yu1Huan Rong2Dongqing Wang3Yuqing Song4Zhe Liu5Victor S. Sheng6Department of Radiology, Affiliated Hospital of Jiangsu University, Zhenjiang 212001, ChinaSchool of Computer Science and Communications Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaDepartment of Radiology, Affiliated Hospital of Jiangsu University, Zhenjiang 212001, ChinaSchool of Computer Science and Communications Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Computer Science and Communications Engineering, Jiangsu University, Zhenjiang 212013, ChinaDepartment of Computer Science, Texas Tech University, Lubbock, TX 79409, USAThe liver is an irreplaceable organ in the human body, maintaining life activities and metabolism. Malignant tumors of the liver have a high mortality rate at present. Computer-aided segmentation of the liver and tumors has significant effects on clinical diagnosis and treatment. There are still many challenges in the segmentation of the liver and liver tumors simultaneously, such as, on the one hand, that convolutional kernels with fixed geometric structures do not match complex, irregularly shaped targets; on the other, pooling during convolution results in a loss of spatial contextual information of images. In this work, we designed a cascaded U-ADenseNet with coarse-to-fine processing for addressing the above issues of fully automatic segmentation. This work contributes multi-resolution input images and multi-layered channel attention combined with atrous spatial pyramid pooling densely connected in the fine segmentation. The proposed model was evaluated by a public dataset of the Liver Tumor Segmentation Challenge (LiTS). Our approach attained competitive liver and tumor segmentation scores that exceeded other methods across a wide range of metrics.https://www.mdpi.com/2075-4426/11/10/1044CT imagesconvolutional neural networkchannel attentioncascadedliver segmentation |
| spellingShingle | Yan Zhu Aihong Yu Huan Rong Dongqing Wang Yuqing Song Zhe Liu Victor S. Sheng Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors Journal of Personalized Medicine CT images convolutional neural network channel attention cascaded liver segmentation |
| title | Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors |
| title_full | Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors |
| title_fullStr | Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors |
| title_full_unstemmed | Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors |
| title_short | Multi-Resolution Image Segmentation Based on a Cascaded U-ADenseNet for the Liver and Tumors |
| title_sort | multi resolution image segmentation based on a cascaded u adensenet for the liver and tumors |
| topic | CT images convolutional neural network channel attention cascaded liver segmentation |
| url | https://www.mdpi.com/2075-4426/11/10/1044 |
| work_keys_str_mv | AT yanzhu multiresolutionimagesegmentationbasedonacascadeduadensenetfortheliverandtumors AT aihongyu multiresolutionimagesegmentationbasedonacascadeduadensenetfortheliverandtumors AT huanrong multiresolutionimagesegmentationbasedonacascadeduadensenetfortheliverandtumors AT dongqingwang multiresolutionimagesegmentationbasedonacascadeduadensenetfortheliverandtumors AT yuqingsong multiresolutionimagesegmentationbasedonacascadeduadensenetfortheliverandtumors AT zheliu multiresolutionimagesegmentationbasedonacascadeduadensenetfortheliverandtumors AT victorssheng multiresolutionimagesegmentationbasedonacascadeduadensenetfortheliverandtumors |