Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature
Abstract Background Rice is a major staple food crop for more than half the world’s population. As the global population is expected to reach 9.7 billion by 2050, increasing the production of high-quality rice is needed to meet the anticipated increased demand. However, global environmental changes,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-01-01
|
| Series: | Plant Methods |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13007-022-00839-5 |
| _version_ | 1798016334572814336 |
|---|---|
| author | Chaoxin Wang Doina Caragea Nisarga Kodadinne Narayana Nathan T. Hein Raju Bheemanahalli Impa M. Somayanda S. V. Krishna Jagadish |
| author_facet | Chaoxin Wang Doina Caragea Nisarga Kodadinne Narayana Nathan T. Hein Raju Bheemanahalli Impa M. Somayanda S. V. Krishna Jagadish |
| author_sort | Chaoxin Wang |
| collection | DOAJ |
| description | Abstract Background Rice is a major staple food crop for more than half the world’s population. As the global population is expected to reach 9.7 billion by 2050, increasing the production of high-quality rice is needed to meet the anticipated increased demand. However, global environmental changes, especially increasing temperatures, can affect grain yield and quality. Heat stress is one of the major causes of an increased proportion of chalkiness in rice, which compromises quality and reduces the market value. Researchers have identified 140 quantitative trait loci linked to chalkiness mapped across 12 chromosomes of the rice genome. However, the available genetic information acquired by employing advances in genetics has not been adequately exploited due to a lack of a reliable, rapid and high-throughput phenotyping tool to capture chalkiness. To derive extensive benefit from the genetic progress achieved, tools that facilitate high-throughput phenotyping of rice chalkiness are needed. Results We use a fully automated approach based on convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM) to detect chalkiness in rice grain images. Specifically, we train a CNN model to distinguish between chalky and non-chalky grains and subsequently use Grad-CAM to identify the area of a grain that is indicative of the chalky class. The area identified by the Grad-CAM approach takes the form of a smooth heatmap that can be used to quantify the degree of chalkiness. Experimental results on both polished and unpolished rice grains using standard instance classification and segmentation metrics have shown that Grad-CAM can accurately identify chalky grains and detect the chalkiness area. Conclusions We have successfully demonstrated the application of a Grad-CAM based tool to accurately capture high night temperature induced chalkiness in rice. The models trained will be made publicly available. They are easy-to-use, scalable and can be readily incorporated into ongoing rice breeding programs, without rice researchers requiring computer science or machine learning expertise. |
| first_indexed | 2024-04-11T15:49:08Z |
| format | Article |
| id | doaj.art-632623e389c04304b27533de057e6ea9 |
| institution | Directory Open Access Journal |
| issn | 1746-4811 |
| language | English |
| last_indexed | 2024-04-11T15:49:08Z |
| publishDate | 2022-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Plant Methods |
| spelling | doaj.art-632623e389c04304b27533de057e6ea92022-12-22T04:15:26ZengBMCPlant Methods1746-48112022-01-0118112310.1186/s13007-022-00839-5Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperatureChaoxin Wang0Doina Caragea1Nisarga Kodadinne Narayana2Nathan T. Hein3Raju Bheemanahalli4Impa M. Somayanda5S. V. Krishna Jagadish6Department of Computer Science, Kansas State UniversityDepartment of Computer Science, Kansas State UniversityInstitute for Genomics, Biocomputing and Biotechnology, Mississippi State UniversityDepartment of Agronomy, Kansas State UniversityDepartment of Plant and Soil Sciences, Mississippi State UniversityDepartment of Agronomy, Kansas State UniversityDepartment of Agronomy, Kansas State UniversityAbstract Background Rice is a major staple food crop for more than half the world’s population. As the global population is expected to reach 9.7 billion by 2050, increasing the production of high-quality rice is needed to meet the anticipated increased demand. However, global environmental changes, especially increasing temperatures, can affect grain yield and quality. Heat stress is one of the major causes of an increased proportion of chalkiness in rice, which compromises quality and reduces the market value. Researchers have identified 140 quantitative trait loci linked to chalkiness mapped across 12 chromosomes of the rice genome. However, the available genetic information acquired by employing advances in genetics has not been adequately exploited due to a lack of a reliable, rapid and high-throughput phenotyping tool to capture chalkiness. To derive extensive benefit from the genetic progress achieved, tools that facilitate high-throughput phenotyping of rice chalkiness are needed. Results We use a fully automated approach based on convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM) to detect chalkiness in rice grain images. Specifically, we train a CNN model to distinguish between chalky and non-chalky grains and subsequently use Grad-CAM to identify the area of a grain that is indicative of the chalky class. The area identified by the Grad-CAM approach takes the form of a smooth heatmap that can be used to quantify the degree of chalkiness. Experimental results on both polished and unpolished rice grains using standard instance classification and segmentation metrics have shown that Grad-CAM can accurately identify chalky grains and detect the chalkiness area. Conclusions We have successfully demonstrated the application of a Grad-CAM based tool to accurately capture high night temperature induced chalkiness in rice. The models trained will be made publicly available. They are easy-to-use, scalable and can be readily incorporated into ongoing rice breeding programs, without rice researchers requiring computer science or machine learning expertise.https://doi.org/10.1186/s13007-022-00839-5Rice grain chalkiness detectionImage segmentationConvolutional neural networksGradient-weighted class activation mappingHigh night temperature |
| spellingShingle | Chaoxin Wang Doina Caragea Nisarga Kodadinne Narayana Nathan T. Hein Raju Bheemanahalli Impa M. Somayanda S. V. Krishna Jagadish Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature Plant Methods Rice grain chalkiness detection Image segmentation Convolutional neural networks Gradient-weighted class activation mapping High night temperature |
| title | Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature |
| title_full | Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature |
| title_fullStr | Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature |
| title_full_unstemmed | Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature |
| title_short | Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature |
| title_sort | deep learning based high throughput phenotyping of chalkiness in rice exposed to high night temperature |
| topic | Rice grain chalkiness detection Image segmentation Convolutional neural networks Gradient-weighted class activation mapping High night temperature |
| url | https://doi.org/10.1186/s13007-022-00839-5 |
| work_keys_str_mv | AT chaoxinwang deeplearningbasedhighthroughputphenotypingofchalkinessinriceexposedtohighnighttemperature AT doinacaragea deeplearningbasedhighthroughputphenotypingofchalkinessinriceexposedtohighnighttemperature AT nisargakodadinnenarayana deeplearningbasedhighthroughputphenotypingofchalkinessinriceexposedtohighnighttemperature AT nathanthein deeplearningbasedhighthroughputphenotypingofchalkinessinriceexposedtohighnighttemperature AT rajubheemanahalli deeplearningbasedhighthroughputphenotypingofchalkinessinriceexposedtohighnighttemperature AT impamsomayanda deeplearningbasedhighthroughputphenotypingofchalkinessinriceexposedtohighnighttemperature AT svkrishnajagadish deeplearningbasedhighthroughputphenotypingofchalkinessinriceexposedtohighnighttemperature |