High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNet
Rice is a staple food for nearly half the global population and, with rising living standards, the demand for high-quality grain is increasing. Chalkiness, a key determinant of appearance quality, requires accurate detection for effective quality evaluation. While traditional 2D imaging has been use...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/2/450 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849723101754949632 |
|---|---|
| author | Zhiqi Cai Yangjun Deng Xinghui Zhu Bo Li Chenglin Xu Donghui Li |
| author_facet | Zhiqi Cai Yangjun Deng Xinghui Zhu Bo Li Chenglin Xu Donghui Li |
| author_sort | Zhiqi Cai |
| collection | DOAJ |
| description | Rice is a staple food for nearly half the global population and, with rising living standards, the demand for high-quality grain is increasing. Chalkiness, a key determinant of appearance quality, requires accurate detection for effective quality evaluation. While traditional 2D imaging has been used for chalkiness detection, its inherent inability to capture complete 3D morphology limits its suitability for precision agriculture and breeding. Although micro-CT has shown promise in 3D chalk phenotype analysis, high-throughput automated 3D detection for multiple grains remains a challenge, hindering practical applications. To address this, we propose a high-throughput 3D chalkiness detection method using micro-CT and VSE-UNet. Our method begins with non-destructive 3D imaging of grains using micro-CT. For the accurate segmentation of kernels and chalky regions, we propose VSE-UNet, an improved VGG-UNet with an SE attention mechanism for enhanced feature learning. Through comprehensive training optimization strategies, including the Dice focal loss function and dropout technique, the model achieves robust and accurate segmentation of both kernels and chalky regions in continuous CT slices. To enable high-throughput 3D analysis, we developed a unified 3D detection framework integrating isosurface extraction, point cloud conversion, DBSCAN clustering, and Poisson reconstruction. This framework overcomes the limitations of single-grain analysis, enabling simultaneous multi-grain detection. Finally, 3D morphological indicators of chalkiness are calculated using triangular mesh techniques. Experimental results demonstrate significant improvements in both 2D segmentation (7.31% improvement in chalkiness IoU, 2.54% in mIoU, 2.80% in mPA) and 3D phenotypic measurements, with VSE-UNet achieving more accurate volume and dimensional measurements compared with the baseline. These improvements provide a reliable foundation for studying chalkiness formation and enable high-throughput phenotyping. |
| format | Article |
| id | doaj-art-399a059af3124efdb7bd15159401ea78 |
| institution | DOAJ |
| issn | 2073-4395 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-399a059af3124efdb7bd15159401ea782025-08-20T03:11:07ZengMDPI AGAgronomy2073-43952025-02-0115245010.3390/agronomy15020450High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNetZhiqi Cai0Yangjun Deng1Xinghui Zhu2Bo Li3Chenglin Xu4Donghui Li5College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Computer Science and Technology, Hengyang Normal University, Hengyang 421002, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaRice is a staple food for nearly half the global population and, with rising living standards, the demand for high-quality grain is increasing. Chalkiness, a key determinant of appearance quality, requires accurate detection for effective quality evaluation. While traditional 2D imaging has been used for chalkiness detection, its inherent inability to capture complete 3D morphology limits its suitability for precision agriculture and breeding. Although micro-CT has shown promise in 3D chalk phenotype analysis, high-throughput automated 3D detection for multiple grains remains a challenge, hindering practical applications. To address this, we propose a high-throughput 3D chalkiness detection method using micro-CT and VSE-UNet. Our method begins with non-destructive 3D imaging of grains using micro-CT. For the accurate segmentation of kernels and chalky regions, we propose VSE-UNet, an improved VGG-UNet with an SE attention mechanism for enhanced feature learning. Through comprehensive training optimization strategies, including the Dice focal loss function and dropout technique, the model achieves robust and accurate segmentation of both kernels and chalky regions in continuous CT slices. To enable high-throughput 3D analysis, we developed a unified 3D detection framework integrating isosurface extraction, point cloud conversion, DBSCAN clustering, and Poisson reconstruction. This framework overcomes the limitations of single-grain analysis, enabling simultaneous multi-grain detection. Finally, 3D morphological indicators of chalkiness are calculated using triangular mesh techniques. Experimental results demonstrate significant improvements in both 2D segmentation (7.31% improvement in chalkiness IoU, 2.54% in mIoU, 2.80% in mPA) and 3D phenotypic measurements, with VSE-UNet achieving more accurate volume and dimensional measurements compared with the baseline. These improvements provide a reliable foundation for studying chalkiness formation and enable high-throughput phenotyping.https://www.mdpi.com/2073-4395/15/2/450rice chalkinessmicro-CTdeep learning3D reconstruction |
| spellingShingle | Zhiqi Cai Yangjun Deng Xinghui Zhu Bo Li Chenglin Xu Donghui Li High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNet Agronomy rice chalkiness micro-CT deep learning 3D reconstruction |
| title | High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNet |
| title_full | High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNet |
| title_fullStr | High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNet |
| title_full_unstemmed | High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNet |
| title_short | High-Throughput 3D Rice Chalkiness Detection Based on Micro-CT and VSE-UNet |
| title_sort | high throughput 3d rice chalkiness detection based on micro ct and vse unet |
| topic | rice chalkiness micro-CT deep learning 3D reconstruction |
| url | https://www.mdpi.com/2073-4395/15/2/450 |
| work_keys_str_mv | AT zhiqicai highthroughput3dricechalkinessdetectionbasedonmicroctandvseunet AT yangjundeng highthroughput3dricechalkinessdetectionbasedonmicroctandvseunet AT xinghuizhu highthroughput3dricechalkinessdetectionbasedonmicroctandvseunet AT boli highthroughput3dricechalkinessdetectionbasedonmicroctandvseunet AT chenglinxu highthroughput3dricechalkinessdetectionbasedonmicroctandvseunet AT donghuili highthroughput3dricechalkinessdetectionbasedonmicroctandvseunet |