{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T05:52:09Z","timestamp":1791525129957,"version":"4.3.4"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>As the number of smart agricultural automation systems increases, accurate disease diagnosis is essential to maximize production efficiency. However, early-stage symptoms of strawberry diseases (e.g., Tipburn, Phytophthora blight, and Fusarium wilt) often manifest as low-contrast micro-symptoms that are visually similar to the inherent complex texture of strawberry leaves, leading to high technical difficulties in achieving an accurate diagnosis. Furthermore, providing an explanation for the diagnosis remains challenging, which hinders trust in field applications. We present EN-FDEA, a deep learning framework that integrates an EfficientNetV2 backbone with a Convolutional Block Attention Module (CBAM) and a Fine-grained Discriminative Enhancement (FDEA) module combining depthwise separable convolution, parallel feature amplification, and channel recalibration, and we evaluate it together with a provenance audit of the corpus on which it is trained. Parsing the acquisition metadata embedded in every file name showed that the 1,000 abnormal images of each disease originate from only 33\u201373 individual plants, and that normal and abnormal images share no greenhouse; under the image-level cross-validation used in the original design, 91.9\u201399.8% of abnormal plants appear in both the training and the test partition of a fold. All results reported here are therefore obtained under plant-disjoint cross-validation with five random seeds, with a site-disjoint arm as the strictest comparison. Removing plant leakage lowers balanced accuracy by up to 0.082 and removing site overlap by up to 0.173. Under the leakage-free protocol, EN-FDEA performs comparably to, and not reliably better than, its EfficientNetV2 backbone (mean paired balanced-accuracy differences of \u20130.013 to +0.012 across datasets and conditions); the only Holm-corrected significant advantage is Phytophthora blight under overexposure (+0.012, p = 0.047). Forensic analysis further shows that the elevated performance previously observed under synthetic overexposure is a property of the transform: a logistic-regression classifier using only global exposure statistics reaches balanced accuracies of 0.81\u20130.92, and models trained on original images transfer poorly to synthetic overexposure while transferring well to genuinely over-illuminated frames selected from the corpus itself. We report explanation faithfulness, calibration, and measured deployment cost, and we state where the corpus structure, rather than the model, bounds what can be concluded. Code, split definitions, and per-image predictions are released so that every number can be regenerated.<\/jats:p>","DOI":"10.3389\/fpls.2026.1941698","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T05:35:05Z","timestamp":1791524105000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable fine-grained feature enhancement framework for strawberry diagnostic decision making"],"prefix":"10.3389","volume":"17","author":[{"given":"Hye-Young","family":"Wang","sequence":"first","affiliation":[{"name":"Department of AI Application, Hansung University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seoung-Ho","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Korea University College of Medicine","place":["Seoul, Republic of Korea"]},{"name":"Faculty of Basic Liberal Art, Hansung University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"key":"B43","first-page":"9505","article-title":"Sanity checks for saliency maps","author":"Adebayo","year":"2018"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200267","article-title":"Assessing the trustworthiness of saliency maps for localizing abnormalities in medical imaging","volume":"3","author":"Arun","year":"2021","journal-title":"Radiology: Artif. Intell."},{"key":"B3","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.biosystemseng.2016.01.017","article-title":"A review on the main challenges in automatic plant disease identification based on visible range images","volume":"144","author":"Barbedo","year":"2016","journal-title":"Biosyst. Eng"},{"key":"B4","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.compag.2018.08.013","article-title":"Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification","volume":"153","author":"Barbedo","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B7","doi-asserted-by":"publisher","first-page":"11554","DOI":"10.1038\/s41598-022-15163-0","article-title":"A deep learning based approach for automated plant disease classification using vision transformer","volume":"12","author":"Borhani","year":"2022","journal-title":"Sci. Rep."},{"key":"B41","first-page":"839","article-title":"Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"B42","first-page":"782","article-title":"Transformer interpretability beyond attention visualization","author":"Chefer","year":"2021"},{"key":"B16","first-page":"833","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"B38","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1037\/0033-2909.114.3.494","article-title":"Dominance statistics: Ordinal analyses to answer ordinal questions","volume":"114","author":"Cliff","year":"1993","journal-title":"Psychol. Bull."},{"key":"B37","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B39","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"Dem\u0161ar","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate statistical tests for comparing supervised classification learning algorithms","volume":"10","author":"Dietterich","year":"1998","journal-title":"Neural Comput."},{"key":"B12","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.compag.2018.01.009","article-title":"Deep learning models for plant disease detection and diagnosis","volume":"145","author":"Ferentinos","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B30","first-page":"25261","article-title":"MambaVision: A hybrid mamba-transformer vision backbone","author":"Hatamizadeh","year":"2025"},{"key":"B33","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/plants13182556","article-title":"Automatic disease detection from strawberry leaf based on improved YOLOv8","volume":"13","author":"He","year":"2024","journal-title":"Plants"},{"key":"B40","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J. Stat."},{"key":"B13","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"B34","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"B2","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: A survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B25","doi-asserted-by":"publisher","first-page":"15:1","DOI":"10.1145\/2382577.2382579","article-title":"Leakage in data mining: Formulation, detection, and avoidance","volume":"6","author":"Kaufman","year":"2012","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture11090827","article-title":"Impacts of background removal on convolutional neural networks for plant disease classification in-situ","volume":"11","author":"KC","year":"2021","journal-title":"Agriculture"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.chemolab.2023.104869","article-title":"Early detection of drought stress in tomato from spectroscopic data: A novel convolutional neural network with feature selection","volume":"239","author":"Kuo","year":"2023","journal-title":"Chemometrics Intelligent Lab. Syst."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.05501","article-title":"Next-ViT: Next generation vision transformer for efficient deployment in realistic industrial scenarios","author":"Li","year":"2022"},{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/s18082674","article-title":"Machine learning in agriculture: A review","volume":"18","author":"Liakos","year":"2018","journal-title":"Sensors"},{"key":"B10","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"B35","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"McNemar","year":"1947","journal-title":"Psychometrika"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2016.01419","article-title":"Using deep learning for image-based plant disease detection","volume":"7","author":"Mohanty","year":"2016","journal-title":"Front. Plant Sci."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1203546","article-title":"Explainable deep learning in plant phenotyping","volume":"6","author":"Mostafa","year":"2023","journal-title":"Front. Artif. Intell."},{"key":"B17","doi-asserted-by":"publisher","first-page":"29955","DOI":"10.1038\/s41598-025-14847-7","article-title":"Robust multiclass classification of crop leaf diseases using hybrid deep learning and grad-CAM interpretability","volume":"15","author":"Murugesan","year":"2025","journal-title":"Sci. Rep."},{"key":"B21","doi-asserted-by":"publisher","first-page":"37919","DOI":"10.1038\/s41598-025-21611-4","article-title":"Interpretable deep multimodal-based tomato disease diagnosis and severity estimation","volume":"15","author":"Nasir","year":"2025","journal-title":"Sci. Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"30720","DOI":"10.1038\/s41598-025-94083-1","article-title":"A lightweight and explainable CNN model for empowering plant disease diagnosis","volume":"15","author":"Pal","year":"2025","journal-title":"Sci. Rep."},{"key":"B29","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B19","first-page":"1135","article-title":"Why Should I Trust You?: Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"B26","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1038\/s42256-021-00307-0","article-title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","volume":"3","author":"Roberts","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"B9","first-page":"618","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1491","DOI":"10.1186\/s12870-025-07377-x","article-title":"Deep learning technique for plant disease classification and pest detection and model explainability elevating agricultural sustainability","volume":"25","author":"Shafik","year":"2025","journal-title":"BMC Plant Biol."},{"key":"B15","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"B31","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","author":"Tan","year":"2021"},{"key":"B27","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1038\/s41746-022-00592-y","article-title":"Machine learning for medical imaging: Methodological failures and recommendations for the future","volume":"5","author":"Varoquaux","year":"2022","journal-title":"NPJ Digital Med."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy12051035","article-title":"Explainable deep learning study for leaf disease classification","volume":"12","author":"Wei","year":"2022","journal-title":"Agronomy"},{"key":"B14","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"Woo","year":"2018"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1452551","article-title":"Plant disease recognition datasets in the age of deep learning: Challenges and opportunities","volume":"15","author":"Xu","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002683","article-title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study","volume":"15","author":"Zech","year":"2018","journal-title":"PloS Med."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1941698\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T05:35:06Z","timestamp":1791524106000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1941698\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":44,"alternative-id":["10.3389\/fpls.2026.1941698"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1941698","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]},"article-number":"1941698"}}