Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet
Cardiovascular diseases are reported as the leading cause of death around the world. Automatic segmentation of the left ventricle (LV) from magnetic resonance (MR) images is essential for an early diagnosis. An enhanced ResUnet is proposed in this paper to improve the performance of extracting LV en...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2022/8669305 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558325033598976 |
|---|---|
| author | Shengzhou Xu Haoran Lu Shiyu Cheng Chengdan Pei |
| author_facet | Shengzhou Xu Haoran Lu Shiyu Cheng Chengdan Pei |
| author_sort | Shengzhou Xu |
| collection | DOAJ |
| description | Cardiovascular diseases are reported as the leading cause of death around the world. Automatic segmentation of the left ventricle (LV) from magnetic resonance (MR) images is essential for an early diagnosis. An enhanced ResUnet is proposed in this paper to improve the performance of extracting LV endocardium and epicardium from MR images, improving the accuracy of the model by introducing a medium skip connection for the contracting path and a short skip connection for the residual unit. Also, a depth-wise separable convolution replaces the typical convolution operation to improve training efficiency. In the MICCAI 2009 LV segmentation challenge test dataset, the percentages of “good” contours, dice metric, and average perpendicular distance of endocardium (epicardium) are 99.12%±2.29%100%±0%,0.93±0.02 0.96±0.01,and 1.60±0.42 mm 1.37±0.23 mm, respectively. Experimental results demonstrate that the proposed model obtains promising performance and outperforms state-of-the-art methods. By incorporating these various skip connections, the segmentation accuracy of the model is significantly improved, while the depth-wise separable convolution also improves the model efficiency. |
| format | Article |
| id | doaj-art-7ef87fa8fe7f4e549936b4e794deda65 |
| institution | Kabale University |
| issn | 1687-4196 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-7ef87fa8fe7f4e549936b4e794deda652025-02-03T01:32:36ZengWileyInternational Journal of Biomedical Imaging1687-41962022-01-01202210.1155/2022/8669305Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnetShengzhou Xu0Haoran Lu1Shiyu Cheng2Chengdan Pei3College of Computer ScienceCollege of Computer ScienceCollege of Computer ScienceNetwork Information CenterCardiovascular diseases are reported as the leading cause of death around the world. Automatic segmentation of the left ventricle (LV) from magnetic resonance (MR) images is essential for an early diagnosis. An enhanced ResUnet is proposed in this paper to improve the performance of extracting LV endocardium and epicardium from MR images, improving the accuracy of the model by introducing a medium skip connection for the contracting path and a short skip connection for the residual unit. Also, a depth-wise separable convolution replaces the typical convolution operation to improve training efficiency. In the MICCAI 2009 LV segmentation challenge test dataset, the percentages of “good” contours, dice metric, and average perpendicular distance of endocardium (epicardium) are 99.12%±2.29%100%±0%,0.93±0.02 0.96±0.01,and 1.60±0.42 mm 1.37±0.23 mm, respectively. Experimental results demonstrate that the proposed model obtains promising performance and outperforms state-of-the-art methods. By incorporating these various skip connections, the segmentation accuracy of the model is significantly improved, while the depth-wise separable convolution also improves the model efficiency.http://dx.doi.org/10.1155/2022/8669305 |
| spellingShingle | Shengzhou Xu Haoran Lu Shiyu Cheng Chengdan Pei Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet International Journal of Biomedical Imaging |
| title | Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet |
| title_full | Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet |
| title_fullStr | Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet |
| title_full_unstemmed | Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet |
| title_short | Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet |
| title_sort | left ventricle segmentation in cardiac mr images via an improved resunet |
| url | http://dx.doi.org/10.1155/2022/8669305 |
| work_keys_str_mv | AT shengzhouxu leftventriclesegmentationincardiacmrimagesviaanimprovedresunet AT haoranlu leftventriclesegmentationincardiacmrimagesviaanimprovedresunet AT shiyucheng leftventriclesegmentationincardiacmrimagesviaanimprovedresunet AT chengdanpei leftventriclesegmentationincardiacmrimagesviaanimprovedresunet |