{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:38:20Z","timestamp":1792787900675,"version":"4.5.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":61,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Manipal Academy of Higher Education, Manipal","id":[{"id":"https:\/\/ror.org\/02xzytt36","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Plant Biol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Detecting plant leaf diseases at an early stage is one of the most important requirements for sustainable agriculture, increasing crop productivity, and achieving the global Sustainable Development Goals (SDGs). However, accurately recognizing them in real-world farm fields can still be difficult due to factors such as background complexity, changes in light conditions, and very similar looking classes from a visual standpoint. In order to solve these problems, the authors here present a new Multi-Scale Feature Fusion (MSFF) model that can offer robust and highly accurate performance in identifying plant leaf diseases. Firstly, the brand new hybrid method starts with a U-Net segmentation designed exclusively to separate the diseased parts and thus allow the classification to be more robust. Next, Rank Order Fuzzy (ROF) is implemented to get rid of the background while still maintaining the edges, and the additional data is used for the network to generalize better. The color distribution is then analyzed to determine the variations in color brought about by the infection. In terms of features, EfficientNet is paired with an Attention-based Autoencoder to produce both spatially detailed global features and compact latent representations. The two sets of features are then combined through Canonical Correlation Analysis (CCA) which not only identifies the dependencies between the features but also enhances the discriminative strength. The final fused feature set is fed to module based on YOLO for detection and classification in order to obtain the final result of the plant disease identification system which is both accurate and fast. Among other datasets, the model has been tested on different apple leaf datasets such as FGVC7, AppleLeafSet, PlantVillage Apple, Kaggle Apple Leaves, and ATLDSD, which contain five disease classes. The results of the experiments indicate a classification accuracy of 99.95%, thus the model is superior to several state-of-the-art deep learning and classical machine learning methods. Statistical methods like five-fold cross-validation, paired t-tests (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.05), and effect size analysis support the strength and importance of the model. Besides, the Grad-CAM heat maps also reveal that the model is pinpointing the disease areas that are biologically relevant. These findings make it very clear that the MSFF is a reliable, explainable, and scalable tool for precise plant disease recognition even in complex farming environments.\n                  <\/jats:p>","DOI":"10.1186\/s12870-026-09444-3","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T02:04:57Z","timestamp":1784340297000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comprehensive plant disease classification and severity estimation for sustainable farming via automatic segmentation and multi-scale feature fusion"],"prefix":"10.1186","volume":"26","author":[{"given":"Vinay","family":"Gautam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaganpreet","family":"Kaur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyoti","family":"Rani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sathiyaraj","family":"Rajendran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G. S. Pradeep","family":"Ghantasala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"9444_CR1","first-page":"220236","volume":"155","author":"MA Khan","year":"2018","unstructured":"Khan MA, et al. CCDF: Automatic system for segmentation and recognition of fruit crops diseases based on correlation coefcient and deep CNN features. Comput Electron Agricult. 2018;155:220236.","journal-title":"Comput Electron Agricult"},{"issue":"4","key":"9444_CR2","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/s12571-012-0200-5","volume":"4","author":"S Savary","year":"2012","unstructured":"Savary S, Ficke A, Aubertot J-N, Hollier C. Crop losses due to diseases and their implications for global food production losses and food security. Food Secur. 2012;4(4):519\u201337.","journal-title":"Food Secur"},{"issue":"1","key":"9444_CR3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.9790\/0661-16151016","volume":"16","author":"KR Gavhale","year":"2014","unstructured":"Gavhale KR, Gawande U. An overview of the research on plant leaves disease detection using image processing techniques. IOSR J Comput Eng. 2014;16(1):10\u20136.","journal-title":"IOSR J Comput Eng"},{"key":"9444_CR4","doi-asserted-by":"crossref","unstructured":"Samajpati BJ, Degadwala SD. ``Fusion approach for apple fruit diseases detection and classication using random forest classifier,'' in Proc. Int. Conf. Commun. Signal Process. (ICCSP), 2016:10151019.","DOI":"10.1109\/ICCSP.2016.7754302"},{"issue":"2","key":"9444_CR5","first-page":"7483","volume":"10","author":"Z Chuanlei","year":"2017","unstructured":"Chuanlei Z, Shanwen Z, Jucheng Y, Yancui S, Jia C. Apple leaf disease identication using genetic algorithm and correlation based feature selection method. Int J Agricult Biol Eng. 2017;10(2):7483.","journal-title":"Int J Agricult Biol Eng"},{"key":"9444_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.sasc.2025.200199","author":"AL Rukuna","year":"2025","unstructured":"Rukuna AL, Zambuk FU, Gital AY, Bello UM. Citrus diseases detection and classification based on Efficientnet-B5. Syst Soft Comput. 2025. https:\/\/doi.org\/10.1016\/j.sasc.2025.200199.","journal-title":"Syst Soft Comput"},{"key":"9444_CR7","doi-asserted-by":"publisher","first-page":"e2655","DOI":"10.7717\/peerj-cs.2655","volume":"11","author":"AS Doutoum","year":"2025","unstructured":"Doutoum AS, Tugrul B. A systematic review of deep learning techniques for apple leaf diseases classification and detection. PeerJ Comput Sci. 2025;11:e2655.","journal-title":"PeerJ Comput Sci"},{"key":"9444_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2025.111311","author":"SH Durjoy","year":"2025","unstructured":"Durjoy SH, Shikder ME, Mojumdar MU. A comprehensive hog plum leaf disease dataset for enhanced detection and classification. Data Brief. 2025. https:\/\/doi.org\/10.1016\/j.dib.2025.111311.","journal-title":"Data Brief"},{"issue":"1","key":"9444_CR9","doi-asserted-by":"publisher","first-page":"100092","DOI":"10.1016\/j.cropd.2024.100092","volume":"4","author":"KN Rahman","year":"2025","unstructured":"Rahman KN, Banik SC, Islam R, Al Fahim A. A real time monitoring system for accurate plant leaves disease detection using deep learning. Crop Design. 2025;4(1):100092.","journal-title":"Crop Design"},{"key":"9444_CR10","doi-asserted-by":"publisher","first-page":"107005","DOI":"10.1016\/j.cropro.2024.107005","volume":"188","author":"I Attri","year":"2025","unstructured":"Attri I, Awasthi LK, Sharma TP. EQID: entangled quantum image descriptor an approach for early plant disease detection. Crop Prot. 2025;188:107005.","journal-title":"Crop Prot"},{"issue":"190","key":"9444_CR11","doi-asserted-by":"publisher","first-page":"107117","DOI":"10.1016\/j.cropro.2025.107117","volume":"1","author":"P Chavan","year":"2025","unstructured":"Chavan P, Chavan PP, Chavan A. Fusion architecture for crop detection and leaf disease detection with improved U-Net segmentation model and image processing. Crop Prot. 2025;1(190):107117.","journal-title":"Crop Prot"},{"issue":"9","key":"9444_CR12","doi-asserted-by":"publisher","first-page":"7212","DOI":"10.1016\/j.jksuci.2022.07.004","volume":"34","author":"S Hasan","year":"2022","unstructured":"Hasan S, Jahan S, Islam MI. Disease detection of apple leaf with combination of color segmentation and modified DWT. J King Saud Univ-Comput Inf Sci. 2022;34(9):7212\u201324.","journal-title":"J King Saud Univ-Comput Inf Sci"},{"issue":"1","key":"9444_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10341-024-01239-w","volume":"67","author":"A Banjar","year":"2025","unstructured":"Banjar A, Javed A, Nawaz M, Dawood H. E-AppleNet: an enhanced deep learning approach for apple fruit leaf disease classification. Appl Fruit Sci. 2025;67(1):1.","journal-title":"Appl Fruit Sci"},{"issue":"78","key":"9444_CR14","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/j.aej.2023.07.076","volume":"1","author":"F Arshad","year":"2023","unstructured":"Arshad F, Mateen M, Hayat S, Wardah M, Al-Huda Z, Gu YH, et al. PLDPNet: End-to-end fusion deep learning framework for potato leaf disease prediction. Alex Eng J. 2023;1(78):406\u201318.","journal-title":"Alex Eng J"},{"issue":"1","key":"9444_CR15","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1016\/j.biosystemseng.2008.09.030","volume":"102","author":"A Camargo","year":"2009","unstructured":"Camargo A, Smith JS. An image-processing based algorithm to automatically identify plant disease visual symptoms. Biosyst Eng. 2009;102(1):921.","journal-title":"Biosyst Eng"},{"issue":"1","key":"9444_CR16","doi-asserted-by":"publisher","first-page":"e0316081","DOI":"10.1371\/journal.pone.0316081","volume":"20","author":"N Butt","year":"2025","unstructured":"Butt N, Iqbal MM, Ramzan S, Raza A, Abualigah L, Fitriyani NL, et al. Citrus diseases detection using innovative deep learning approach and Fusion Meta-Heuristic. PLoS ONE. 2025;20(1):e0316081.","journal-title":"PLoS ONE"},{"issue":"1","key":"9444_CR17","doi-asserted-by":"publisher","first-page":"19343","DOI":"10.48084\/etasr.9216","volume":"15","author":"K Sundaramoorthi","year":"2025","unstructured":"Sundaramoorthi K, Kamarasan M. Integration of deep learning with fox optimization algorithm for early detection and classification of tomato leaf and fruit diseases. Eng Technol Appl Sci Res. 2025;15(1):19343\u20138.","journal-title":"Eng Technol Appl Sci Res"},{"issue":"19","key":"9444_CR18","first-page":"101623","volume":"1","author":"K Oliullah","year":"2025","unstructured":"Oliullah K, Islam MR, Babar JI, Quraishi MN, Rahman MM, Mahbub-Or-Rashid M, et al. FruVeg_MultiNet: A fusion deep learning-enabled IoT system for fresh fruit and vegetable identification with web interface and customized blind glasses for visually impaired individuals. J Agric Food Res. 2025;1(19):101623.","journal-title":"J Agric Food Res"},{"issue":"1","key":"9444_CR19","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s12065-024-01000-y","volume":"18","author":"N Shinde","year":"2025","unstructured":"Shinde N, Ambhaikar A. An efficient plant disease prediction model based on machine learning and deep learning classifiers. Evol Intell. 2025;18(1):14.","journal-title":"Evol Intell"},{"key":"9444_CR20","doi-asserted-by":"publisher","first-page":"113281","DOI":"10.1016\/j.postharvbio.2024.113281","volume":"219","author":"D Chen","year":"2025","unstructured":"Chen D, Lin F, Lu C, Zhuang J, Su H, Zhang D, et al. YOLOv8-MDN-Tiny: a lightweight model for multi-scale disease detection of postharvest golden passion fruit. Postharvest Biol Technol. 2025;219:113281.","journal-title":"Postharvest Biol Technol"},{"issue":"6","key":"9444_CR21","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1007\/s42979-024-02959-2","volume":"5","author":"I Ahmed","year":"2024","unstructured":"Ahmed I, Yadav PK. Predicting apple plant diseases in orchards using machine learning and deep learning algorithms. SN Comput Sci. 2024;5(6):700.","journal-title":"SN Comput Sci"},{"key":"9444_CR22","unstructured":"Jingze Feng, Xiaofei Chao. Apple Tree Leaf Disease Segmentation Dataset[DS\/OL]. V1. Science Data Bank, 2022[2025\u201308\u201313]. https:\/\/cstr.cn\/31253.11.sciencedb.01627. CSTR:31253.11.sciencedb.01627."},{"key":"9444_CR23","doi-asserted-by":"crossref","unstructured":"Boukabouya RA, Moussaoui A, Berrimi M. Vision Transformer Based Models for Plant Disease Detection and Diagnosis. In2022 5th International Symposium on Informatics and its Applications (ISIA) 2022 (pp. 1-6). IEEE.","DOI":"10.1109\/ISIA55826.2022.9993508"},{"key":"9444_CR24","unstructured":"https:\/\/www.kaggle.com\/c\/plant-pathology-2020-ATLDSD) and Baidu AI Studio (https:\/\/aistudio.baidu.com\/aistudio-\/datasetdetail\/11591"},{"key":"9444_CR25","doi-asserted-by":"publisher","first-page":"59069","DOI":"10.1109\/ACCESS.2019.2914929","volume":"7","author":"P Jiang","year":"2019","unstructured":"Jiang P, Chen Y, Liu B, He D, Liang C. Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks. IEEE Access. 2019;7:59069\u201380.","journal-title":"IEEE Access"},{"issue":"6","key":"9444_CR26","doi-asserted-by":"publisher","first-page":"061815","DOI":"10.1117\/1.JEI.31.6.061815","volume":"31","author":"M Bukumira","year":"2022","unstructured":"Bukumira M, Antonijevic M, Jovanovic D, Zivkovic M, Mladenovic D, Kunjadic G. Carrot grading system using computer vision feature parameters and a cascaded graph convolutional neural network. J Electron Imaging. 2022;31(6):061815\u2013061815.","journal-title":"J Electron Imaging"},{"key":"9444_CR27","doi-asserted-by":"publisher","first-page":"831219","DOI":"10.3389\/fpls.2022.831219","volume":"13","author":"L Fu","year":"2022","unstructured":"Fu L, Li S, Sun Y, Mu Y, Hu T, Gong H. Lightweight-convolutional neural network for apple leaf disease identification. Front Plant Sci. 2022;13:831219.","journal-title":"Front Plant Sci"},{"issue":"7","key":"9444_CR28","doi-asserted-by":"publisher","first-page":"617","DOI":"10.3390\/agriculture11070617","volume":"11","author":"P Bansal","year":"2021","unstructured":"Bansal P, Kumar R, Kumar S. Disease detection in apple leaves using deep convolutional neural network. Agriculture (Basel). 2021;11(7):617.","journal-title":"Agriculture (Basel)"},{"key":"9444_CR29","doi-asserted-by":"publisher","first-page":"107093","DOI":"10.1016\/j.compag.2022.107093","volume":"198","author":"AI Khan","year":"2022","unstructured":"Khan AI, Quadri SMK, Banday S, Shah JL. Deep diagnosis: a real-time apple leaf disease detection system based on deep learning. Comput Electron Agric. 2022;198:107093.","journal-title":"Comput Electron Agric"},{"key":"9444_CR30","doi-asserted-by":"publisher","first-page":"61886","DOI":"10.1109\/ACCESS.2024.3389648","volume":"12","author":"K Taji","year":"2024","unstructured":"Taji K, Sohail A, Shahzad T, Khan BS, Khan MA, Ouahada K. An ensemble fusion framework: a comparative analysis of metaheuristic algorithms for ensemble fusion CNN features for plants disease classification. IEEE Access. 2024;12:61886\u2013906.","journal-title":"IEEE Access"},{"key":"9444_CR31","first-page":"108612","volume":"218","author":"R Kannan","year":"2024","unstructured":"Kannan R, Kumar S, Prakash M. Hybrid EfficientNet\u2013DenseNet framework for automated apple leaf disease detection using deep convolutional neural networks. Comput Electron Agric. 2024;218:108612.","journal-title":"Comput Electron Agric."},{"key":"9444_CR32","first-page":"121034","volume":"235","author":"M Ali","year":"2024","unstructured":"Ali M, Rahman T, Hossain MS. AppleLeafNet: A 37-layer deep convolutional neural network for robust apple leaf disease classification. Expert Syst Appl. 2024;235:121034.","journal-title":"Expert Syst Appl."},{"key":"9444_CR33","first-page":"45678","volume":"13","author":"A Bonkra","year":"2025","unstructured":"Bonkra A, Singh D, Verma P. Modified EfficientNetB3 and ResNet50 architectures for high-accuracy apple leaf disease identification. IEEE Access. 2025;13:45678\u201392.","journal-title":"IEEE Access."},{"key":"9444_CR34","first-page":"45987","volume":"13","author":"A Bonkra","year":"2025","unstructured":"Bonkra A, Singh D, Verma P. Comparative analysis of CNN and traditional techniques for apple leaf disease classification. IEEE Access. 2025;13:45987\u201399.","journal-title":"IEEE Access."},{"issue":"21","key":"9444_CR35","first-page":"32987","volume":"80","author":"A Bansal","year":"2021","unstructured":"Bansal A, Gupta R, Sharma N. Ensemble deep learning models for apple leaf disease classification. Multimedia Tools and Applications. 2021;80(21):32987\u20133012.","journal-title":"Multimedia Tools and Applications."},{"issue":"8","key":"9444_CR36","first-page":"5678","volume":"34","author":"J Jose","year":"2022","unstructured":"Jose J, Santhi B. IFPA-GA optimized SVM-SVI for plant leaf disease identification. J King Saud Univ Comput Inform Sci. 2022;34(8):5678\u201389.","journal-title":"J King Saud Univ Comput Inform Sci"},{"key":"9444_CR37","first-page":"2140","volume":"192","author":"R Sangeetha","year":"2022","unstructured":"Sangeetha R, Devi L, Kumar A. Apple leaf disease detection using VGG16 deep learning model. Procedia Comput Sci. 2022;192:2140\u20137.","journal-title":"Procedia Comput Sci"},{"key":"9444_CR38","doi-asserted-by":"crossref","first-page":"106011","DOI":"10.1016\/j.compag.2021.106011","volume":"182","author":"S Gawade","year":"2021","unstructured":"Gawade S, Patil V, Kulkarni A. Mask R-CNN based segmentation and classification for apple leaf disease detection. Comput Electron Agric. 2021;182:106011.","journal-title":"Comput Electron Agric"},{"key":"9444_CR39","first-page":"108845","volume":"221","author":"X Li","year":"2024","unstructured":"Li X, Zhang Y, Chen H. Optimized YOLOv5s with Wise-IoU and RepVGG for apple leaf disease detection in orchard environments. Comput Electron Agric. 2024;221:108845.","journal-title":"Comput Electron Agric"},{"key":"9444_CR40","doi-asserted-by":"crossref","first-page":"107036","DOI":"10.1016\/j.compag.2022.107036","volume":"198","author":"H Di","year":"2022","unstructured":"Di H, Li Y. DF-Tiny-YOLO: An improved YOLO-based model for real-time apple leaf disease detection. Comput Electron Agric. 2022;198:107036.","journal-title":"Comput Electron Agric"},{"key":"9444_CR41","doi-asserted-by":"publisher","unstructured":"Hashan AM. Apple leaf disease symptoms dataset [Dataset]. Kaggle. 2021. https:\/\/doi.org\/10.34740\/KAGGLE\/DSV\/2068940.","DOI":"10.34740\/KAGGLE\/DSV\/2068940"},{"issue":"20","key":"9444_CR42","doi-asserted-by":"publisher","first-page":"8531","DOI":"10.3390\/s23208531","volume":"23","author":"M De Silva","year":"2023","unstructured":"De Silva M, Brown D. Multispectral plant Disease Detection with Vision transformer\u2013convolutional neural network fusion approaches. Sensors. 2023;23(20):8531.","journal-title":"Sensors"},{"key":"9444_CR43","unstructured":"Hughes DP, Salath\u00e9 M. An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv preprint arXiv:1511.08060. 2015."},{"key":"9444_CR44","doi-asserted-by":"crossref","unstructured":"Akinyemi JD, Adebayo KJ. The PV-ALE dataset: enhancing apple leaf disease classification through transfer learning with convolutional neural networks. arXi (2024). https:\/\/arxiv.org\/abs\/2410.22490.","DOI":"10.1007\/978-3-031-88039-1_13"}],"container-title":["BMC Plant Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12870-026-09444-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12870-026-09444-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12870-026-09444-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T06:33:42Z","timestamp":1789626822000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12870-026-09444-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,18]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["9444"],"URL":"https:\/\/doi.org\/10.1186\/s12870-026-09444-3","relation":{},"ISSN":["1471-2229"],"issn-type":[{"value":"1471-2229","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,18]]},"assertion":[{"value":"18 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethics and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"1607"}}