Accelerating Wild Rice Disease-Resistant Germplasm Exploration: Artificial Intelligence (AI)-Powered Wild Rice Blast Disease Level Evaluation and Disease-Resistance Identification
Received date: 2025-03-19
Accepted date: 2025-05-26
Online published: 2025-06-30
Accurate evaluation of disease levels in wild rice germplasm and identification of disease resistance are critical for developing rice varieties resistant to blast disease. However, existing evaluation methods face limitations that hinder progress in breeding. To address these challenges, we proposed an AI-powered method for evaluating blast disease levels and identifying resistance in wild rice. A lightweight segmentation model for diseased leaves and lesions was developed, incorporating an improved federated learning approach to enhance robustness and adaptability. Based on the segmentation results and resistance identification technical specifications, wild rice materials were evaluated into 10 disease levels (L0 to L9), further enabling disease-resistance identification through multiple replicates of the same materials. The method was successfully implemented on augmented reality glasses for real-time, first-person evaluation. Additionally, high-speed scanners and edge computing devices were integrated to enable continuous, precise, and dynamic evaluation. Experimental results demonstrate the outstanding performance of the proposed method, achieving effective segmentation of diseased leaves and lesions with only 0.22 M parameters and 5.3 G floating-point operations per second (FLOPs), with a mean average precision (mAP@0.5) of 96.3%. The accuracy of disease level evaluation and disease-resistance identification reached 99.7%, with a practical test accuracy of 99.0%, successfully identifying three highly resistant wild rice materials. This method provides strong technical support for efficiently identifying wild rice materials resistant to blast disease and advancing resistance breeding efforts.
Pan Pan, Guo Wenlong, Li Hengbo, Shao Yifan, Guo Zhihao, Jin Ye, Cheng Yanrong, Yu Guoping, Fu Zhenshi, Hu Lin, Zheng Xiaoming, Zhou Guomin, Zhang Jianhua . Accelerating Wild Rice Disease-Resistant Germplasm Exploration: Artificial Intelligence (AI)-Powered Wild Rice Blast Disease Level Evaluation and Disease-Resistance Identification[J]. Rice Science, 2025 , 32(5) : 727 -746 . DOI: 10.1016/j.rsci.2025.05.005
| [1] | Abràmoff M D, Magalhães P J, Ram S J. 2004. Image processing with ImageJ. In: Biophotonics International. Pittsfield, Massachusetts, USA: Laurin Publishing Co. Inc.: 36-42. |
| [2] | Cai X H, Lai Q X, Wang Y W, et al. 2024. Poly kernel inception network for remote sensing detection. arXiv e-prints: 2403.06258. https://arxiv.org/abs/2403.06258v2. |
| [3] | Campo S, Martín-Cardoso H, Olivé M, et al. 2020. Effect of root colonization by arbuscular mycorrhizal fungi on growth, productivity and blast resistance in rice. Rice, 13(1): 42. |
| [4] | Chen H, Sun K Y, Tian Z, et al. 2020. BlendMask: Top-down meets bottom-up for instance segmentation. arXiv e-prints: 2001.00309. https://arxiv.org/abs/2001.00309v3. |
| [5] | Chen J R, Kao S H, He H, et al. 2023. Run, don’t walk: Chasing higher FLOPS for faster neural networks. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 17-24, 2023, Vancouver, BC, Canada: IEEE: 12021-12031. |
| [6] | Chen Y, Liu Z Q, Meng S, et al. 2023. OsCERK1 contributes to cupric oxide nanoparticles induced phytotoxicity and basal resistance against blast by regulating the anti-oxidant system in rice. J Fungi, 9(1): 36. |
| [7] | Chen Y F, Zhang C Y, Chen B, et al. 2024. Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases. Comput Biol Med, 170: 107917. |
| [8] | Chen Z X, He Z W, Lu Z M. 2024. DEA-net: Single image dehazing based on detail-enhanced convolution and content-guided attention. IEEE Trans Image Process, 33: 1002-1015. |
| [9] | Cheng T H, Wang X G, Chen S Y, et al. 2022. Sparse instance activation for real-time instance segmentation. arXiv e-prints: 2203.12827. https://arxiv.org/abs/2203.12827v1. |
| [10] | Culjak I, Abram D, Pribanic T, et al. 2012. A brief introduction to OpenCV. In: Proceedings of the 35th International Convention MIPRO. 21-25 May 2012, Opatija, Croatia: IEEE: 1725-1730. |
| [11] | Das A, Soubam D, Singh P K, et al. 2012. A novel blast resistance gene, Pi54rh cloned from wild species of rice, Oryza rhizomatis confers broad spectrum resistance to Magnaporthe oryzae. Funct Integr Genomics, 12(2): 215-228. |
| [12] | Devi S J S R, Singh K, Umakanth B, et al. 2015. Development and identification of novel rice blast resistant sources and their characterization using molecular markers. Rice Sci, 22(6): 300-308. |
| [13] | Fahad S, Adnan M, Noor M, et al. 2019. Major constraints for global rice production. In: Hasanuzzaman M, Fujita M, Nahar K, et al. Advances in Rice Research for Abiotic Stress Tolerance. Amsterdam, the Netherlands: Elsevier: 1-22. |
| [14] | Fernandez J, Lopez V, Kinch L, et al. 2021. Role of two metacaspases in development and pathogenicity of the rice blast fungus Magnaporthe oryzae. mBio, 12(1): e03471-20. |
| [15] | Han Q, Fan Z J, Dai Q, et al. 2021. On the connection between local attention and dynamic depth-wise convolution. arXiv e-prints: 2106.04263. https://arxiv.org/abs/2106.04263v5. |
| [16] | He J J, Li P Y, Geng Y F, et al. 2023. FastInst: A simple query-based model for real-time instance segmentation. arXiv e-prints: 2303. 08594. https://arxiv.org/abs/2303.08594v2. |
| [17] | He K M, Gkioxari G, Dollár P, et al. 2018. Mask R-CNN. IEEE Trans Pattern Anal Mach Intell, 42(2): 386-397. |
| [18] | Huang C L, Hwang S Y, Chiang Y C, et al. 2008. Molecular evolution of the Pi-ta gene resistant to rice blast in wild rice (Oryza rufipogon). Genetics, 179(3): 1527-1538. |
| [19] | Laha G S, Singh R, Ladhalakshmi D, et al. 2017. Importance and management of rice diseases: A global perspective. In: Chauhan B S, Jabran K, Mahajan Gulshan. Rice Production Worldwide. Cham: Springer International Publishing: 303-360. |
| [20] | Lamba S, Kukreja V, Baliyan A, et al. 2023. A novel hybrid severity prediction model for blast paddy disease using machine learning. Sustainability, 15(2): 1502. |
| [21] | Lee J, Park S, Mo S, et al. 2020. Layer-adaptive sparsity for the magnitude-based pruning. arXiv e-prints: 2010.07611. https://arxiv.org/abs/2010.07611v2. |
| [22] | Li W, Zhang M C, Yang Y L, et al. 2024. Molecular evolution of rice blast resistance gene bsr-d1. Rice Sci, 31(6): 700-711. |
| [23] | Li W T, Chern M, Yin J J, et al. 2019. Recent advances in broad-spectrum resistance to the rice blast disease. Curr Opin Plant Biol, 50: 114-120. |
| [24] | Liang Y, Yi Z F, Zhuang W, et al. 2025. Optimizing hybrid with improved resistance to rice blast and superior ratooning ability. Rice Sci, 32(3): 292-297. |
| [25] | Lin S D, Yao Y, Li J Y, et al. 2023. Application of UAV-based imaging and deep learning in assessment of rice blast resistance. Rice Sci, 30(6): 652-660. |
| [26] | Liu W D, Wang G L. 2016. Plant innate immunity in rice: A defense against pathogen infection. Natl Sci Rev, 3(3): 295-308. |
| [27] | Liu Y B, Lei B, Hu L, et al. 2020. The grading determination of rice blast: HSV color space method based on machine vision. J Agric, 10(10): 83-90. (in Chinese with English abstract) |
| [28] | Liu Y L, Feng N J, Zhong F T. 2022. First report of Pyricularia oryzae causing blast in wild rice (Oryza rufipogon) in China. Plant Dis, 106(11): 2997. |
| [29] | Meng F, He Y G, Chen J, et al. 2021. Analysis of natural variation of the rice blast resistance gene Pike and identification of a novel allele Pikg. Mol Genet Genomics, 296(4): 939-952. |
| [30] | Ministry of Agriculture of the People’s Republic of China. 2014. Technical specification for identification and evaluation of blast resistance in rice variety regional test: NY-T 2646-2014. Beijing, China: China Standards Press. [2025-02-25]. (in Chinese) |
| [31] | Pan P, Zhang J H, Zheng X M, et al. 2023a. Research progress of deep learning in intelligent identification of disease resistance of crops and their related species. Acta Agric Zhejiang, 35(8): 1993-2012. (in Chinese with English abstract) |
| [32] | Pan P, Guo W, Zheng X, et al. 2023b. Xoo-YOLO: A detection method for wild rice bacterial blight in the field from the perspective of unmanned aerial vehicles. Front Plant Sci, 14: 1256545. |
| [33] | Pan P, Yao Q, Shen J, et al. 2024a. CVW-etr: A high-precision method for estimating the severity level of cotton verticillium wilt disease. Plants-Basel, 13(21): 2960. |
| [34] | Pan P, Shao M, He P, et al. 2024b. Lightweight cotton diseases real-time detection model for resource-constrained devices in natural environments. Front Plant Sci, 15: 1383863. |
| [35] | Patil R R, Kumar S, Chiwhane S, et al. 2023. An artificial-intelligence-based novel rice grade model for severity estimation of rice diseases. Agriculture, 13(1): 47. |
| [36] | Qu S H, Liu G F, Zhou B, et al. 2006. The broad-spectrum blast resistance gene Pi9 encodes a nucleotide-binding site-leucine-rich repeat protein and is a member of a multigene family in rice. Genetics, 172(3): 1901-1914. |
| [37] | Ritharson P I, Raimond K, Mary X A, et al. 2024. DeepRice: A deep learning and deep feature based classification of rice leaf disease subtypes. Artif Intell Agric, 11: 34-49. |
| [38] | Russell B C, Torralba A, Murphy K P, et al. 2008. LabelMe: A database and web-based tool for image annotation. Int J Comput Vis, 77(1): 157-173. |
| [39] | Shen Q, Li Y, Zhang Y X, et al. 2025. CSW-YOLO: A traffic sign small target detection algorithm based on YOLOv8. PLoS One, 20(3): e0315334. |
| [40] | Sheng C, Yu D, Li X, et al. 2022. OsAPX1 positively contributes to rice blast resistance. Front Plant Sci, 13: 843271. |
| [41] | Shi D. 2023. TransNeXt: Robust foveal visual perception for vision transformers. arXiv e-prints: 2311.17132. https://arxiv.org/abs/2311.17132v3. |
| [42] | Tang Y H, Han K, Guo J Y, et al. 2022. GhostNetV2: Enhance cheap operation with long-range attention. arXiv e-prints: 2211.12905. https://arxiv.org/abs/2211.12905v1. |
| [43] | Terensan S, Salgadoe A S A, Kottearachchi N S, et al. 2024. Proximally sensed RGB images and colour indices for distinguishing rice blast and brown spot diseases by k-means clustering: Towards a mobile application solution. Smart Agric Technol, 9: 100532. |
| [44] | Tian Z, Shen C H, Chen H, et al. 2020. Conditional convolutions for instance segmentation. arXiv e-prints: 2003.05664. https://arxiv.org/abs/2003.05664v4. |
| [45] | Wing R A, Purugganan M D, Zhang Q F. 2018. The rice genome revolution: From an ancient grain to Green Super Rice. Nat Rev Genet, 19(8): 505-517. |
| [46] | Yang Z Y, Xu Z J, Yang Q W, et al. 2022. Conservation and utilization of genetic resources of wild rice in China. Rice Sci, 29(3): 216-224. |
| [47] | Zheng X M, Peng Y L, Qiao J Y, et al. 2024. Wild rice: Unlocking the future of rice breeding. Plant Biotechnol J, 22(11): 3218-3226. |
| [48] | Zhu X M, Li L, Wang J Y, et al. 2021. Vacuolar protein-sorting receptor MoVps13 regulates conidiation and pathogenicity in rice blast fungus Magnaporthe oryzae. J Fungi, 7(12): 1084. |
/
| 〈 |
|
〉 |