{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T20:12:57Z","timestamp":1792267977519,"version":"4.4.0"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014189","name":"Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014189","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>\n                    Gray mold caused by\n                    <jats:italic>Botrytis cinerea<\/jats:italic>\n                    severely limits the postharvest storage and marketability of kiwifruit, creating a need for accurate and non-destructive infection assessment. In this study, a symptom based, ROI-aware, and interpretable deep-learning framework was developed to classify infection levels in golden-fleshed \u2018Haegeum\u2019 kiwifruit. Infection severity was categorized into four levels based on external visual symptoms: Level 1: no lesions; Level 2: slight discoloration; Level 3: localized mycelial growth; Level 4: extensive mycelial growth and tissue breakdown. The associated physiological responses were subsequently characterized for each level. Disease progression induced fruit softening with firmness decreasing from 4.82 at Level 1 to 2.79\u00a0N at Level 4, while respiration rates increased from 0.05 to 0.24 \u00b5mol kg\n                    <jats:sup>-1<\/jats:sup>\n                    s\n                    <jats:sup>-1<\/jats:sup>\n                    . Ethylene production began at Level 3 and sharply increased at Level 4, reaching 0.015 \u00b5mol kg\n                    <jats:sup>-1<\/jats:sup>\n                    s\n                    <jats:sup>-1<\/jats:sup>\n                    . To quantify lesion severity, a region-of-interest-aware pipeline using RGB blue and LAB\n                    <jats:italic>L<\/jats:italic>\n                    * and\n                    <jats:italic>a<\/jats:italic>\n                    * channels was developed, enabling lesion-focused visualization of infection. Compared with the baseline model, the proposed approach improved classification performance, achieving accuracies of 90.3% with EfficientNet-B0, ResNet-50, and ShuffleNet-V2, and 87.6% with ResNet-18. Gradient-weighted class activation mapping further indicated that the ROI-aware pipeline reduced background-related activation and improved the spatial confinement of model attention within fruit regions. These findings demonstrate that symptom-based RGB classification, supported by\n                    <jats:italic>post hoc<\/jats:italic>\n                    physiological characterization and explainable deep-learning analysis, provides a biologically interpretable framework for monitoring visible fungal infection progression in postharvest kiwifruit.\n                  <\/jats:p>","DOI":"10.3389\/fpls.2026.1894572","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T05:41:30Z","timestamp":1785130890000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Physiological and image-based characterization of Botrytis cinerea infection progression in postharvest \u2018Haegeum\u2019 kiwifruit using interpretable deep learning"],"prefix":"10.3389","volume":"17","author":[{"given":"Joonggon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Agriculture, Forestry and Bioresources, College of Agriculture and Life Sciences, Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang-Yeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biosystems Engineering, Seoul National University","place":["Seoul, Republic of Korea"]},{"name":"Integrated Major in Global Smart Farm, Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyeonglim","family":"Min","sequence":"additional","affiliation":[{"name":"Research Institute of Agriculture and Life Sciences, Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chanyong","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ghiseok","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biosystems Engineering, Seoul National University","place":["Seoul, Republic of Korea"]},{"name":"Integrated Major in Global Smart Farm, Seoul National University","place":["Seoul, Republic of Korea"]},{"name":"Research Institute of Agriculture and Life Sciences, Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eun Jin","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Agriculture, Forestry and Bioresources, College of Agriculture and Life Sciences, Seoul National University","place":["Seoul, Republic of Korea"]},{"name":"Research Institute of Agriculture and Life Sciences, Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"9505","DOI":"10.48550\/arXiv.1810.03292","article-title":"Sanity checks for saliency maps","volume":"31","author":"Adebayo","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110510","article-title":"Enhancing performance of vision transformers on small datasets through local inductive bias incorporation","volume":"153","author":"Akkaya","year":"2024","journal-title":"Pattern Recognit."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.postharvbio.2023.112615","article-title":"Detection of subsurface bruises in plums using spectral imaging and deep learning with wavelength selection","volume":"207","author":"Castillo-Girones","year":"2024","journal-title":"Postharvest Biol. Technol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"114","DOI":"10.22698\/jales.20210011","article-title":"Ethylene treatment and storage temperature affect ripening quality of kiwifruit cultivars","volume":"33","author":"Choi","year":"2021","journal-title":"J. Agric. Life. Environ. Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1111\/j.1364-3703.2011.00783.x","article-title":"The top 10 fungal pathogens in molecular plant pathology","volume":"13","author":"Dean","year":"2012","journal-title":"Mol. Plant Pathol."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.foodres.2024.114836","article-title":"Interpretation and explanation of computer vision classification of carambola (Averrhoa carambola L.) according to maturity stage","volume":"192","author":"de Moraes","year":"2024","journal-title":"Food Res. Int."},{"key":"B7","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/978-1-4020-2626-3_14","article-title":"Epidemiology of Botrytis cinerea in orchard and vine crops","volume-title":"Botrytis: Biology, Pathology and Control","author":"Elmer","year":"2007"},{"key":"B8","doi-asserted-by":"crossref","first-page":"101892","DOI":"10.1016\/j.atech.2026.101892","article-title":"Fusion architectures for soft rot detection in melon plants using hyperspectral and multicolor fluorescence imaging","volume":"13","author":"Guti\u00e9rrez","year":"2026","journal-title":"Smart Agric. Technol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s13007-023-01032-y","article-title":"Non-destructive pre-symptomatic detection of gray mold infection in kiwifruit using hyperspectral data and chemometrics","volume":"19","author":"Haghbin","year":"2023","journal-title":"Plant Methods"},{"key":"B10","first-page":"9737","article-title":"A benchmark for interpretability methods in deep neural networks","volume":"32","author":"Hooker","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.postharvbio.2022.111854","article-title":"Postharvest fumigation of (E)-2-hexenal on kiwifruit (Actinidia chinensis cv. \u2018Haegeum\u2019) enhances resistance to Botrytis cinerea","volume":"187","author":"Hyun","year":"2022","journal-title":"Postharvest Biol. Technol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"215","DOI":"10.7745\/KJSSF.2017.50.4.215","article-title":"Fungal infection occurrence on new cultivars of kiwifruit correlated with fruit soluble solids content and firmness","volume":"50","author":"Kim","year":"2017","journal-title":"Korean J. Soil Sci. Fertil."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.postharvbio.2022.112166","article-title":"A comparison of physicochemical and ripening characteristics of golden-fleshed \u2018Haegeum\u2019 and green-fleshed \u2018Hayward\u2019 kiwifruit during storage at 0 \u00b0C and ripening at 25 \u00b0C","volume":"196","author":"Kim","year":"2023","journal-title":"Postharvest Biol. Technol."},{"key":"B14","article-title":"Rethinking the hyperparameters for fine-tuning","author":"Li","year":"2020"},{"key":"B15","doi-asserted-by":"publisher","first-page":"113434","DOI":"10.1016\/j.postharvbio.2025.113434","article-title":"Detection of bruising in pear with varying bruising degrees and formation times by using SIRI technique combining with texture feature-based LS-SVM and ResNet-18-based CNN model","volume":"223","author":"Li","year":"2025","journal-title":"Postharvest Biol. Technol."},{"key":"B16","first-page":"122","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"Ma","year":"2018"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.postharvbio.2023.112348","article-title":"Application of deep learning diagnosis for multiple traits sorting in peach fruit","volume":"201","author":"Masuda","year":"2023","journal-title":"Postharvest Biol. Technol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1111\/j.1478-4408.1976.tb03301.x","article-title":"XIII\u2014The development of the CIE 1976 (L* a* b*) uniform colour-space and colour-difference formula","volume":"92","author":"McLaren","year":"1976","journal-title":"J. Soc Dyers Colour."},{"key":"B19","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1007\/978-3-031-84543-7_19","article-title":"MobileNet-based fruit classification using U-Net generated segmented images: Grad-CAM visualization","volume-title":"Applied Algorithms","author":"Mondal","year":"2025"},{"key":"B20","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1038\/s41438-020-0323-3","article-title":"Deep learning image segmentation and extraction of blueberry fruit traits associated with harvestability and yield","volume":"7","author":"Ni","year":"2020","journal-title":"Hortic. Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"733","DOI":"10.17660\/ActaHortic.1997.444.112","article-title":"Ethylene production by Botrytis cinerea, kiwifruit and Botrytis-rotted kiwifruit under several storage temperatures","volume":"444","author":"Niklis","year":"1997","journal-title":"Acta Hortic."},{"key":"B22","first-page":"151","article-title":"RISE: Randomized input sampling for explanation of black-box models","author":"Petsiuk","year":"2018"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/s25051524","article-title":"Artificial vision systems for fruit inspection and classification: Systematic literature review","volume":"25","author":"Rojas Santelices","year":"2025","journal-title":"Sensors"},{"key":"B24","first-page":"4510","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"B25","first-page":"618","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0264586","article-title":"Fruit classification using attention-based MobileNetV2 for industrial applications","volume":"17","author":"Shahi","year":"2022","journal-title":"PloS One"},{"key":"B27","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of Machine Learning Research","author":"Tan","year":"2019"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.868745","article-title":"Application of convolutional neural network-based detection methods in fresh fruit production: a comprehensive review","volume":"13","author":"Wang","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B29","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1111\/j.1364-3703.2007.00417.x","article-title":"Botrytis cinerea: the cause of grey mould disease","volume":"8","author":"Williamson","year":"2007","journal-title":"Mol. Plant Pathol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1038\/s41438-021-00560-9","article-title":"Applications of deep-learning approaches in horticultural research: a review","volume":"8","author":"Yang","year":"2021","journal-title":"Hortic. Res."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1894572\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T05:41:33Z","timestamp":1785130893000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1894572\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":30,"alternative-id":["10.3389\/fpls.2026.1894572"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1894572","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]},"article-number":"1894572"}}