Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study.
This paper introduces an optimized nested UNet model for automated left ventricular segmentation in cardiac function assessment. We utilize the EchoNet-Dynamic dataset, which contains both video data and expert annotations. Unlike conventional methods such as DeepLabv3 that struggle with large model...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0325794 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850108510861262848 |
|---|---|
| author | Kerang Cao Miao Zhao Minghui Geng Shuai Zheng Hoekyung Jung |
| author_facet | Kerang Cao Miao Zhao Minghui Geng Shuai Zheng Hoekyung Jung |
| author_sort | Kerang Cao |
| collection | DOAJ |
| description | This paper introduces an optimized nested UNet model for automated left ventricular segmentation in cardiac function assessment. We utilize the EchoNet-Dynamic dataset, which contains both video data and expert annotations. Unlike conventional methods such as DeepLabv3 that struggle with large model sizes and imprecise segmentation, Our proposed model introduces a deeper feature extraction module to effectively capture multi-scale features and reduce computational overhead. By integrating the CBAM (Attention module) attention mechanism and a lightweight SimAM (Simple Attention Module) module, we enhance feature selectivity and minimize redundancy. To further stabilize training and address gradient issues, we combine binary cross-entropy and Dice loss functions. Experimental results reveal that our model significantly outperforms existing methods, achieving a 1.05% increase in the Dice coefficient and reducing model size to 15% of the original. These improvements not only enhance the accuracy of cardiac function assessments but also provide a more efficient solution for automated diagnosis in clinical practice. |
| format | Article |
| id | doaj-art-d6f0a2d26c134b699a31e11bf627e709 |
| institution | OA Journals |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-d6f0a2d26c134b699a31e11bf627e7092025-08-20T02:38:21ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01206e032579410.1371/journal.pone.0325794Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study.Kerang CaoMiao ZhaoMinghui GengShuai ZhengHoekyung JungThis paper introduces an optimized nested UNet model for automated left ventricular segmentation in cardiac function assessment. We utilize the EchoNet-Dynamic dataset, which contains both video data and expert annotations. Unlike conventional methods such as DeepLabv3 that struggle with large model sizes and imprecise segmentation, Our proposed model introduces a deeper feature extraction module to effectively capture multi-scale features and reduce computational overhead. By integrating the CBAM (Attention module) attention mechanism and a lightweight SimAM (Simple Attention Module) module, we enhance feature selectivity and minimize redundancy. To further stabilize training and address gradient issues, we combine binary cross-entropy and Dice loss functions. Experimental results reveal that our model significantly outperforms existing methods, achieving a 1.05% increase in the Dice coefficient and reducing model size to 15% of the original. These improvements not only enhance the accuracy of cardiac function assessments but also provide a more efficient solution for automated diagnosis in clinical practice.https://doi.org/10.1371/journal.pone.0325794 |
| spellingShingle | Kerang Cao Miao Zhao Minghui Geng Shuai Zheng Hoekyung Jung Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study. PLoS ONE |
| title | Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study. |
| title_full | Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study. |
| title_fullStr | Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study. |
| title_full_unstemmed | Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study. |
| title_short | Left ventricular segmentation method based on optimized UNet and improved CBAM: ESV and EDV tracking study. |
| title_sort | left ventricular segmentation method based on optimized unet and improved cbam esv and edv tracking study |
| url | https://doi.org/10.1371/journal.pone.0325794 |
| work_keys_str_mv | AT kerangcao leftventricularsegmentationmethodbasedonoptimizedunetandimprovedcbamesvandedvtrackingstudy AT miaozhao leftventricularsegmentationmethodbasedonoptimizedunetandimprovedcbamesvandedvtrackingstudy AT minghuigeng leftventricularsegmentationmethodbasedonoptimizedunetandimprovedcbamesvandedvtrackingstudy AT shuaizheng leftventricularsegmentationmethodbasedonoptimizedunetandimprovedcbamesvandedvtrackingstudy AT hoekyungjung leftventricularsegmentationmethodbasedonoptimizedunetandimprovedcbamesvandedvtrackingstudy |