Abstract
The growing global demand for food production, coupled with the increasing threat of plant diseases, necessitates advanced and automated solutions for crop health monitoring. Among various crops, pome fruits such as apples and pears are widely cultivated yet highly susceptible to multiple diseases that can significantly reduce yield and quality. Existing approaches for disease detection and severity classification are often limited by their dependency on manual inspection and their inability to handle complex real-world imagery, especially when multiple diseases coexist on a single leaf. To address these limitations, this research introduces a novel dual-model deep learning framework for multi-disease severity detection and classification in pome fruit leaves. A fine-tuned MobileNetV2 backbone is employed to extract high-level discriminative features from a specialized pome leaf dataset annotated with multiple disease types and severity levels. The proposed system integrates a lightweight Lite-U-Net for semantic segmentation to isolate diseased regions and an enhanced Lite-YOLACT for instance segmentation using a linear combination of prototype masks and mask coefficients. Moreover, a new multi-disease severity scale is proposed to quantify the impact of multiple coexisting infections on a single leaf, an aspect not addressed in previous studies. To enhance interpretability, an improved Grad-CAM technique generates visual heatmaps highlighting the most influential regions in the model’s decision-making process, providing transparency and validation for agricultural experts. Experimental evaluations demonstrate that the proposed framework achieves 95% accuracy in disease severity estimation, effectively identifying and grading multiple infections simultaneously. This study represents a significant step forward in precision agriculture, offering an efficient, interpretable, and scalable deep learning solution for real-world crop health monitoring and management. The source code and trained models are publicly available at: https://github.com/mqasim0787/Multi-Disease-Severity.
Similar content being viewed by others
Data availability
The datasets analyzed during the current study are available publicly in the Kaggle repository, DiaMOS dataset (1) and PlantVillage Dataset (2) 0.1. [https://www.kaggle.com/datasets/alexandraneagu101/diamos-plant-dataset](https:/www.kaggle.com/datasets/alexandraneagu101/diamos-plant-dataset)2. **https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset**.
References
Wheelis, M., Casagrande, R. & Madden, L. V. Biological attack on agriculture: low-tech, high-impact bioterrorism: because bioterrorist attack requires relatively little specialized expertise and technology, it is a serious threat to US agriculture and can have very large economic repercussions. BioScience 52 (7), 569–576. https://doi.org/10.1641/0006-3568(2002)052[0569:BAOALT]2.0.CO;2 (2002).
Ali, M. et al. El Sabagh, Biosynthesis and multifaceted roles of reactive species in plant defense mechanisms during environmental cues. Plant. Stress 101102. https://doi.org/10.1016/j.stress.2025.101102 (2025).
Ali, M. et al. Auxin biodynamics and its integral role in enhancing plant resilience to environmental cues. Physiol. Plant. 177 (2), e70165. https://doi.org/10.1111/ppl.70165 (2025).
Qasim, M. et al. PCA-based advanced local octa-directional pattern (ALODP-PCA): a texture feature descriptor for image retrieval. Electronics 11 (2), 202. https://doi.org/10.3390/electronics11020202 (2022).
Vesković, S. Natural Food Preservation: Controlling Loss, Advancing Safety https://doi.org/10.1007/978-3-031-85089-9 (Springer, 2025).
Hidayatullah, A. F. & Shafik, W. Revolutionizing agriculture with automated plant disease detection: techniques, applications, challenges, future directions, and sustainability impacts. In Artificial Intelligence and Data Science for Sustainability: Applications and Methods. 267–296. https://doi.org/10.4018/979-8-3693-6829-9.ch009 (IGI Global Scientific Publishing, 2025).
Demilie, W. B. Plant disease detection and classification techniques: a comparative study of the performances. J. Big Data 11 (1) 5. https://doi.org/10.1186/s40537-023-00863-9 (2024).
Hang, J., Zhang, D., Chen, P., Zhang, J. & Wang, B. Classification of plant leaf diseases based on improved convolutional neural network. Sensors 19 (19), 4161. https://doi.org/10.3390/s19194161 (2019).
Liang, Q. et al. PD2SE-Net: Computer-assisted plant disease diagnosis and severity estimation network. Comput. Electron. Agric. 157, 518–529. https://doi.org/10.1016/j.compag.2019.01.034 (2019).
Nanehkaran, Y., Zhang, D., Chen, J., Tian, Y. & Al-Nabhan, N. Recognition of plant leaf diseases based on computer vision. J. Ambient Intell. Humaniz. Comput. 1–18. https://doi.org/10.1007/s12652-020-02505-x (2020).
Ji, M., Zhang, K., Wu, Q. & Deng, Z. Multi-label learning for crop leaf diseases recognition and severity estimation based on convolutional neural networks. Soft. Comput. 24, 15327–15340. https://doi.org/10.1007/s00500-020-04866-z (2020).
Hu, G., Wang, H., Zhang, Y. & Wan, M. Detection and severity analysis of tea leaf blight based on deep learning. Comput. Electr. Eng. 90, 107023. https://doi.org/10.1016/j.compeleceng.2021.107023 (2021).
Zhao, Y., Chen, J., Xu, X., Lei, J. & Zhou, W. SEV-Net: Residual network embedded with attention mechanism for plant disease severity detection. Concurrency Computation: Pract. Experience. 33 (10), e6161. https://doi.org/10.1002/cpe.6161 (2021).
Xiang, S., Liang, Q., Sun, W., Zhang, D. & Wang, Y. L-CSMS: novel lightweight network for plant disease severity recognition. J. Plant Dis. Prot. 128, 557–569. https://doi.org/10.1007/s41348-020-00423-w (2021).
Wang, C. et al. A cucumber leaf disease severity classification method based on the fusion of DeepLabV3 + and U-Net. Comput. Electron. Agric. 189, 106373. https://doi.org/10.1016/j.compag.2021.106373 (2021).
Guan, Q., Song, K., Feng, S., Yu, F. & Xu, T. Detection of peanut leaf spot disease based on leaf-, plant-, and field-scale hyperspectral reflectance. Remote Sens. 14 (19), 4988. https://doi.org/10.3390/rs14194988 (2022).
Fenu, G. & Malloci, F. M. Using multioutput learning to diagnose plant disease and stress severity. Complexity 2021 (1), 6663442. https://doi.org/10.1155/2021/6663442 (2021).
Yin, C. et al. Maize small leaf spot classification based on improved deep convolutional neural networks with a multi-scale attention mechanism. Agronomy 12 (4), 906. https://doi.org/10.3390/agronomy12040906 (2022).
Liu, B. Y., Fan, K. J., Su, W. H. & Peng, Y. Two-stage convolutional neural networks for diagnosing the severity of alternaria leaf blotch disease of the apple tree. Remote Sens. 14 (11), 2519. https://doi.org/10.3390/rs14112519 (2022).
Alves, K. S. et al. Del Ponte, RGB-based phenotyping of foliar disease severity under controlled conditions. Trop. Plant. Pathol. 1–13. https://doi.org/10.1007/s40858-021-00448-y (2022).
Kurmi, Y. & Gangwar, S. A leaf image localization based algorithm for different crops disease classification. Inform. Process. Agric. 9 (3), 456–474. https://doi.org/10.1016/j.inpa.2021.03.001 (2022).
Muntaqim, M. Z., Kafi, H. M. & Smrity, T. A. Privacy-aware plant disease detection: federated learning with homomorphic encryption on image data. Visual Comput. 42 (1), 18. https://doi.org/10.1007/s00371-025-04261-5 (2026).
Muntaqim, M. Z. et al. Federated learning meets few-shot learning: A voting ensemble based combined approach to cauliflower leaf disease classification across non-iid data distributions. Array 100516. https://doi.org/10.1016/j.array.2025.100516 (2025).
Russel, N. S. & Selvaraj, A. Leaf species and disease classification using multiscale parallel deep CNN architecture. Neural Comput. Appl. 34 (21), 19217–19237. https://doi.org/10.1007/s00521-022-07521-w (2022).
Chelloug, S. A., Alkanhel, R., Muthanna, M. S. A., Aziz, A. & Muthanna, A. MULTINET: A Multi-Agent DRL and EfficientNet Assisted Framework for 3D Plant Leaf Disease Identification and Severity Quantification. IEEE Access. https://doi.org/10.1109/ACCESS.2023.3303868 (2023).
Lv, Z. et al. Combining multiple spectral enhancement features for improving spectroscopic asymptomatic detection and symptomatic severity classification of southern corn leaf blight. Precision Agric. 24 (4), 1593–1618. https://doi.org/10.1007/s11119-023-10010-2 (2023).
Shewale, M. V. & Daruwala, R. D. High performance deep learning architecture for early detection and classification of plant leaf disease. J. Agric. Food Res. 14, 100675. https://doi.org/10.1016/j.jafr.2023.100675 (2023).
Yao, H. et al. A Cucumber Leaf Disease Severity Grading Method in Natural Environment Based on the Fusion of TRNet and U-Net. Agronomy 14 (1), 72. https://doi.org/10.3390/agronomy14010072 (2023).
Pal, A. & Kumar, V. AgriDet: Plant Leaf Disease severity classification using agriculture detection framework. Eng. Appl. Artif. Intell. 119, 105754. https://doi.org/10.1016/j.engappai.2022.105754 (2023).
Abdalla, A. et al. Assessing fusarium oxysporum disease severity in cotton using unmanned aerial system images and a hybrid domain adaptation deep learning time series model. Biosyst. Eng. 237, 220–231. https://doi.org/10.1016/j.biosystemseng.2023.12.014 (2024).
Gautam, V., Ranjan, R. K., Dahiya, P. & Kumar, A. ESDNN: A novel ensembled stack deep neural network for mango leaf disease classification and detection. Multimedia Tools Appl. 83 (4), 10989–11015. https://doi.org/10.1007/s11042-023-16012- (2024).
Thangaraj, R., Pandiyan, P., Anandamurugan, S. & Rajendar, S. A deep convolution neural network model based on feature concatenation approach for classification of tomato leaf disease. Multimedia Tools Appl. 83 (7), 18803–18827. https://doi.org/10.1007/s11042-023-16347-0 (2024).
Ritharson, P. I., Raimond, K., Mary, X. A., Robert, J. E. & Andrew, J. DeepRice: A deep learning and deep feature based classification of Rice leaf disease subtypes. Artif. Intell. Agric. 11, 34–49. https://doi.org/10.1016/j.aiia.2023.11.001 (2024).
Andrushia, A. D., Neebha, T. M., Patricia, A. T., Sagayam, K. M. & Pramanik, S. Capsule network-based disease classification for Vitis Vinifera leaves. Neural Comput. Appl. 36 (2), 757–772. https://doi.org/10.1007/s00521-023-09058-y (2024).
Elfatimi, E., Eryiğit, R. & Elfatimi, L. Deep multi-scale convolutional neural networks for automated classification of multi-class leaf diseases in tomatoes. Neural Comput. Appl. 36 (2), 803–822. https://doi.org/10.1007/s00521-023-09062-2 (2024).
Sreedevi, A. & Manike, C. A smart solution for tomato leaf disease classification by modified recurrent neural network with severity computation. Cybernetics Syst. 55 (2), 409–449. https://doi.org/10.1080/01969722.2022.2122004 (2024).
Dai, G., Tian, Z., Fan, J., Sunil, C. & Dewi, C. DFN-PSAN: Multi-level deep information feature fusion extraction network for interpretable plant disease classification. Comput. Electron. Agric. 216, 108481. https://doi.org/10.1016/j.compag.2023.108481 (2024).
Yao, J., Tran, S. N., Garg, S. & Sawyer, S. Deep learning for plant identification and disease classification from leaf images: multi-prediction approaches. ACM Comput. Surveys. 56 (6), 1–37. https://doi.org/10.48550/arXiv.2310.16273 (2024).
Zhao, C. et al. Plant Disease Segmentation Networks for Fast Automatic Severity Estimation Under Natural Field Scenarios. Agriculture 15 (6), 583. https://doi.org/10.3390/agriculture15060583 (2025).
Kumari, K. et al. Spectral sensor-based device for real‐time detection and severity estimation of groundnut bud necrosis virus in tomato. J. Field Robot. 42 (1), 5–19. https://doi.org/10.1002/rob.22391 (2025).
Faye, D., Diop, I., Mbaye, N., Dione, D. & Diedhiou, M. M. Mango fruit diseases severity estimation based on image segmentation and deep learning. Discover Appl. Sci. 7 (2), 1–12. https://doi.org/10.1007/s42452-025-06550-z (2025).
Alfred, R., Leo, J. & Kaijage, S. F. Optimizing dataset diversity for a robust deep-learning model in rice blast disease identification to enhance crop health assessment across diverse conditions. Smart Agricultural Technol. 10, 100726. https://doi.org/10.1016/j.atech.2024.100726 (2025).
Günder, M. et al. SugarViT—Multi-objective regression of UAV images with Vision Transformers and Deep Label Distribution Learning demonstrated on disease severity prediction in sugar beet. PloS one. 20 (2), e0318097. https://doi.org/10.1371/journal.pone.0318097 (2025).
Ng, C. P., Tang, T. Y. & Pariatamby, A. How urgent environmental challenges and tech advancements reshape commercial food systems: A bibliometric analysis leveraging natural-language processing. Int. J. Eng. Bus. Manage. 18, 18479790251394768. https://doi.org/10.1177/184797902513947 (2026).
Zhang, Y. et al. ESM-YOLOv11: a lightweight deep learning framework for real-time peanut leaf spot disease detection and precision severity quantification in field conditions. Comput. Electron. Agric. 238, 110801. https://doi.org/10.1016/j.compag.2025.110801 (2025).
Tang, X. et al. YOLOv11-AIU: a lightweight detection model for the grading detection of early blight disease in tomatoes. Plant. Methods. 21 (1), 118. https://doi.org/10.1186/s13007-025-01435-z (2025).
Xu, Y. X., Yu, X. H., Yi, Q., Zhang, Q. Y. & Su, W. H. Dual-Phase Severity Grading of Strawberry Angular Leaf Spot Based on Improved YOLOv11 and OpenCV. Plants 14 (11), 1656. https://doi.org/10.3390/plants14111656 (2025).
Zhong, W. et al. A Classification method for the severity of aloe anthracnose based on the improved YOLOv11-seg. Agronomy 15 (8), 1896. https://doi.org/10.3390/agronomy15081896 (2025).
Dinesh, P. & Lakshmanan, R. Multiclass semantic segmentation for prime disease detection with severity level identification in Citrus plant leaves. Sci. Rep. 15 (1), 21208. https://doi.org/10.1038/s41598-025-04758-y (2025).
Subbarayudu, C. & Kubendiran, M. Segmentation-based lightweight multi-class classification model for crop disease detection, classification, and severity assessment using DCNN. PLoS One. 20 (5), e0322705. https://doi.org/10.1371/journal.pone.0322705 (2025).
Picon, A. et al. Crop-conditional semantic segmentation for efficient agricultural disease assessment. Artif. Intell. Agric. 15 (1), 79–87. https://doi.org/10.1016/j.aiia.2025.01.002 (2025).
Shi, T. et al. Recent advances in plant disease severity assessment using convolutional neural networks. Sci. Rep. 13 (1), 2336. https://doi.org/10.1038/s41598-023-29230-7 (2023).
Yang, B. et al. Identifying plant disease and severity from leaves: A deep multitask learning framework using triple-branch Swin Transformer and deep supervision. Comput. Electron. Agric. 209, 107809. https://doi.org/10.1016/j.compag.2023.107809 (2023).
Sharma, V., Tripathi, A. K. & Mittal, H. DLMC-Net: Deeper lightweight multi-class classification model for plant leaf disease detection. Ecol. Inf. 75, 102025. https://doi.org/10.1016/j.ecoinf.2023.102025 (2023).
Mafukidze, H. D. et al. Adaptive thresholding of cnn features for maize leaf disease classification and severity estimation. Appl. Sci. 12 (17), 8412. https://doi.org/10.3390/app12178412 (2022).
Wei, T. et al. Plantseg: A large-scale in-the-wild dataset for plant disease segmentation. https://arXiv.org/abs/2409.04038. https://doi.org/10.48550/arXiv.2409.04038 (2024).
Polly, R. & Devi, E. A. Semantic segmentation for plant leaf disease classification and damage detection: A deep learning approach. Smart Agricultural Technol. 9, 100526. https://doi.org/10.1016/j.atech.2024.100526 (2024).
Huang, M., Xu, G., Li, J. & Huang, J. A method for segmenting disease lesions of maize leaves in real time using attention YOLACT++. Agriculture 11 (12), 1216. https://doi.org/10.3390/agriculture11121216 (2021).
Garcia-D’Urso, N. E., Galan-Cuenca, A., Climent-Pérez, P., Saval-Calvo, M. & Azorin-Lopez, J. and A. Fuster-Guillo. Efficient instance segmentation using deep learning for species identification in fish markets. In International Joint Conference on Neural Networks (IJCNN). https://doi.org/10.1109/IJCNN55064.2022.9892945 (IEEE, 2022).
Fenu, G. & Malloci, F. M. DiaMOS plant: A dataset for diagnosis and monitoring plant disease. Agronomy 11 (11), 2107. https://doi.org/10.3390/agronomy11112107 (2021).
Hughes, D. & Salathé, M. An open access repository of images on plant health to enable the development of mobile disease diagnostics. https://arXiv.org/abs/1511.08060. https://doi.org/10.48550/arXiv.1511.08060 (2015).
Author information
Authors and Affiliations
Contributions
Conceptualization, Methodology A, B; software A; validation A, C formal analysis A, B; investigation A, B; resources B, C; data curation A, B; writing; original draft preparation A; writing; review and editing A, B; visualization A, C; supervision B, C; project administration B, C; All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Qasim, M., Adnan, S.M. & Safi, Q.G.K. Optimized Lightweight U-Net and YOLACT framework for multi-disease severity detection in pome fruit leaves. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45947-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45947-7
