2f:I[703058,["/_next/static/immutable/chunks/3bhq_5eh1d760.js","/_next/static/immutable/chunks/1855-ogyi8eh4.js","/_next/static/immutable/chunks/2pfsjpn6k6zlg.js","/_next/static/immutable/chunks/26c7v3_3uwnwu.js","/_next/static/immutable/chunks/25a3ozcrvi1ff.js","/_next/static/immutable/chunks/2r4wx50nvjh_4.js","/_next/static/immutable/chunks/23fsw06hsi5b1.js","/_next/static/immutable/chunks/06_yt270h41rg.js","/_next/static/immutable/chunks/3ezsiz-7shkna.js","/_next/static/immutable/chunks/20x2y96ldu5wx.js","/_next/static/immutable/chunks/2lxntcm3pd1_h.js","/_next/static/immutable/chunks/00dgco8irq3jw.js","/_next/static/immutable/chunks/00nwe-kq0rboc.js","/_next/static/immutable/chunks/2051ffx3xzio9.js"],"PaperListPageClient"] 30:T670,Accurate evaluation of skin lesions is an essential component of dermatological examination, yet it can be time-consuming and subject to interobserver variability. While artificial intelligence (AI) models have shown reliability in diagnosing specific skin diseases, lesion-level identification remains underexplored in veterinary dermatology. To develop and evaluate a convolutional neural network (CNN)-based AI model for the automated identification of four skin lesion types in dogs: erythema, lichenification, alopecia and erosion/ulcer. Clinical skin images were collected from dogs presented to a veterinary medical teaching hospital. Four EfficientNet models were independently trained, one for each lesion type. Model performance was evaluated by comparing the prediction results with veterinary surgeon-labelled data, using six metrics: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score. All four CNN models achieved an accuracy of > 90%, indicating a reliable performance across all lesion types. The alopecia model yielded the highest accuracy (98.12%) and F1 score (98.18%). The erythema and erosion/ulcer models exhibited balanced performance across all metrics. For the lichenification model, the sensitivity (87.02%) and F1 score (89.88%) were the lowest among the four lesion types. The CNN-based AI models developed in this study demonstrated validity in identifying common canine skin lesions from clinical images. These models may facilitate rapid and objective dermatological evaluation, supporting clinical diagnosis and lesion monitoring throughout treatment.31:Ta4c,ABSTRACT Background Accurate evaluation of skin lesions is an essential component of dermatological examination, yet it can be time‐consuming and subject to interobserver variability. While artificial intelligence (AI) models have shown reliability in diagnosing specific skin diseases, lesion‐level identification remains underexplored in veterinary dermatology. Objectives To develop and evaluate a convolutional neural network (CNN)‐based AI model for the automated identification of four skin lesion types in dogs: erythema, lichenification, alopecia and erosion/ulcer. Animals Clinical skin images were collected from dogs presented to a veterinary medical teaching hospital. Materials and Methods Four EfficientNet models were independently trained, one for each lesion type. Model performance was evaluated by comparing the prediction results with veterinary surgeon‐labelled data, using six metrics: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score. Results All four CNN models achieved an accuracy of > 90%, indicating a reliable performance across all lesion types. The alopecia model yielded the highest accuracy (98.12%) and F1 score (98.18%). The erythema and erosion/ulcer models exhibited balanced performance across all metrics. For the lichenification model, the sensitivity (87.02%) and F1 score (89.88%) were the lowest among the four lesion types. Conclusions and Clinical Relevance The CNN‐based AI models developed in this study demonstrated validity in identifying common canine skin lesions from clinical images. These models may facilitate rapid and objective dermatological evaluation, supporting clinical diagnosis and lesion monitoring throughout treatment. 25:[[["$","script","0",{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"{\"@context\":\"https://schema.org\",\"@type\":\"CollectionPage\",\"name\":\"Canine Skin Lesions: condition Research & Clinical Takeaways\",\"description\":\"Explore peer-reviewed papers on Canine Skin Lesions (condition). Clinician-written summaries and actionable practice insights. Updated daily.\",\"url\":\"https://www.reachrx.ai/hub/tag/condition/Canine%20Skin%20Lesions\",\"breadcrumb\":{\"@type\":\"BreadcrumbList\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https://www.reachrx.ai\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Research Hub\",\"item\":\"https://www.reachrx.ai/hub\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Conditions\",\"item\":\"https://www.reachrx.ai/hub/tag/condition\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Canine Skin Lesions\",\"item\":\"https://www.reachrx.ai/hub/tag/condition/Canine%20Skin%20Lesions\"}]}}"}}]],["$","$L2f",null,{"title":"Canine Skin Lesions: Research & Clinical Takeaways","description":"Discover peer-reviewed research on Canine Skin Lesions with concise clinician summaries and next-step guidance.","papers":[{"doi":"10.1111/vde.70083","pmid":"42067986","title":"Artificial Intelligence‐Based Identification of Common Canine Skin Lesions From Clinical Images","journal_title":"Veterinary Dermatology","journal_issn":"0959-4493","published_at":"2026-05-02T00:00:00.000Z","url":"https://doi.org/10.1111/vde.70083","source_score":1,"is_retracted":false,"is_open_access":false,"raw_metadata":{"ooir":{"day":"2026-05-09","doi":"10.1111/vde.70083","days":"7","issn":"0959-4493","rank":"10","field":"Clinical Medicine","score":"1","category":"Dermatology","categories":["Dermatology"],"_categories":["Dermatology"]},"pubmed":{"doi":"10.1111/vde.70083","title":"Artificial Intelligence-Based Identification of Common Canine Skin Lesions From Clinical Images.","journal":"Veterinary dermatology","methods":"","results":"All four CNN models achieved an accuracy of > 90%, indicating a reliable performance across all lesion types. The alopecia model yielded the highest accuracy (98.12%) and F1 score (98.18%). The erythema and erosion/ulcer models exhibited balanced performance across all metrics. For the lichenification model, the sensitivity (87.02%) and F1 score (89.88%) were the lowest among the four lesion types.","abstract":"$30","keywords":["EfficientNet","convolutional neural networks","deep learning","dog","teledermatology"],"pubmed_id":"42067986","conclusions":"","publication_date":"2026-05-02T00:00:00"},"crossref":{"DOI":"10.1111/vde.70083","URL":"https://doi.org/10.1111/vde.70083","ISSN":["0959-4493","1365-3164"],"link":[{"URL":"https://onlinelibrary.wiley.com/doi/pdf/10.1111/vde.70083","content-type":"application/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https://onlinelibrary.wiley.com/doi/full-xml/10.1111/vde.70083","content-type":"application/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https://onlinelibrary.wiley.com/doi/pdf/10.1111/vde.70083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"page":null,"type":"journal-article","issue":null,"score":1,"title":["Artificial Intelligence‐Based Identification of Common Canine Skin Lesions From Clinical Images"],"author":[{"given":"Soh‐Yoon","family":"Kang","sequence":"first","affiliation":[{"name":"Laboratory of Veterinary Dermatology and the Research Institute for Veterinary Science, College of Veterinary Medicine, Seoul National University Seoul Korea"}]},{"given":"Yeong‐Hun","family":"Kang","sequence":"additional","affiliation":[{"name":"Laboratory of Veterinary Dermatology and the Research Institute for Veterinary Science, College of Veterinary Medicine, Seoul National University Seoul Korea"},{"name":"Western Animal Medical Center Seoul Korea"}]},{"given":"Hyun‐Jung","family":"Kim","sequence":"additional","affiliation":[{"name":"AIFORPET Corporation Seoul Korea"}]},{"given":"Eun‐A.","family":"Huh","sequence":"additional","affiliation":[{"name":"AIFORPET Corporation Seoul Korea"}]},{"given":"Jong‐Soo","family":"Jeon","sequence":"additional","affiliation":[{"name":"AIFORPET Corporation Seoul Korea"}]},{"given":"Hyun‐Su","family":"Kim","sequence":"additional","affiliation":[{"name":"AIFORPET Corporation Seoul Korea"}]},{"given":"Min‐Sun","family":"Kim","sequence":"additional","affiliation":[{"name":"Laboratory of Veterinary Dermatology and the Research Institute for Veterinary Science, College of Veterinary Medicine, Seoul National University Seoul Korea"}]},{"given":"Anisha","family":"Tiwari","sequence":"additional","affiliation":[{"name":"Suvidha Pet Care and Derma Centre Jammu Jammu and Kashmir India"}]},{"given":"Cheol‐Yong","family":"Hwang","sequence":"additional","affiliation":[{"name":"Laboratory of Veterinary Dermatology and the Research Institute for Veterinary Science, College of Veterinary Medicine, Seoul National University Seoul Korea"}]}],"issued":{"date-parts":[[2026,5,1]]},"member":"311","prefix":"10.1111","source":"Crossref","volume":null,"archive":["Portico"],"created":{"date-time":"2026-05-02T04:19:39Z","timestamp":1777695579000,"date-parts":[[2026,5,2]]},"indexed":{"date-time":"2026-05-04T23:39:48Z","timestamp":1777937988165,"date-parts":[[2026,5,4]]},"license":[{"URL":"http://creativecommons.org/licenses/by-nc-nd/4.0/","start":{"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000,"date-parts":[[2026,5,1]]},"delay-in-days":0,"content-version":"vor"},{"URL":"http://doi.wiley.com/10.1002/tdm_license_1.1","start":{"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000,"date-parts":[[2026,5,1]]},"delay-in-days":0,"content-version":"tdm"}],"subject":[],"abstract":"$31","language":"en","relation":{},"resource":{"primary":{"URL":"https://onlinelibrary.wiley.com/doi/10.1111/vde.70083"}},"subtitle":[],"assertion":[{"name":"received","group":{"name":"publication_history","label":"Publication History"},"label":"Received","order":0,"value":"2025-09-01"},{"name":"accepted","group":{"name":"publication_history","label":"Publication History"},"label":"Accepted","order":2,"value":"2026-04-07"},{"name":"published","group":{"name":"publication_history","label":"Publication History"},"label":"Published","order":3,"value":"2026-05-01"}],"deposited":{"date-time":"2026-05-02T04:19:45Z","timestamp":1777695585000,"date-parts":[[2026,5,2]]},"issn-type":[{"type":"print","value":"0959-4493"},{"type":"electronic","value":"1365-3164"}],"published":{"date-parts":[[2026,5,1]]},"publisher":"Wiley","reference":[{"DOI":"10.1038/s41415-023-5845-2","key":"e_1_2_11_2_1","year":"2023","issue":null,"author":"Dave M.","volume":"234","first-page":"761","unstructured":null,"article-title":"Artificial Intelligence in Healthcare and Education","journal-title":"British Dental Journal","doi-asserted-by":"crossref"},{"DOI":"10.25259/IJDVL_518_19","key":"e_1_2_11_3_1","year":"2021","issue":null,"author":"Pai V. V.","volume":"87","first-page":"457","unstructured":null,"article-title":"Artificial Intelligence in Dermatology and Healthcare: An Overview","journal-title":"Indian Journal of Dermatology, Venereology and Leprology","doi-asserted-by":"crossref"},{"DOI":"10.1038/s41598-019-50437-0","key":"e_1_2_11_4_1","year":"2019","issue":null,"author":"Kim J. Y.","volume":"9","first-page":null,"unstructured":null,"article-title":"CNN‐Based Diagnosis Models for Canine Ulcerative Keratitis","journal-title":"Scientific Reports","doi-asserted-by":"crossref"},{"DOI":"10.2460/ajvr.22.03.0038","key":"e_1_2_11_5_1","year":"2022","issue":null,"author":"Basran P. S.","volume":"83","first-page":"385","unstructured":null,"article-title":"The Unmet Potential of Artificial Intelligence in Veterinary Medicine","journal-title":"American Journal of Veterinary Research","doi-asserted-by":"crossref"},{"DOI":null,"key":"e_1_2_11_6_1","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"M.TanandQ.Le “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks ”Proceedings of the 36th International Conference on Machine Learning Long Beach CA USA: 2019; 6105–6114.","article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":"10.1016/j.neuri.2021.100034","key":"e_1_2_11_7_1","year":"2022","issue":null,"author":"Ali K.","volume":"2","first-page":null,"unstructured":null,"article-title":"Multiclass Skin Cancer Classification Using EfficientNets–A First Step Towards Preventing Skin Cancer","journal-title":"Neuroscience Informatics","doi-asserted-by":"crossref"},{"DOI":"10.1109/ACCESS.2022.3184113","key":"e_1_2_11_8_1","year":"2022","issue":null,"author":"Shah H. A.","volume":"10","first-page":"65426","unstructured":null,"article-title":"A Robust Approach for Brain Tumor Detection in Magnetic Resonance Images Using Finetuned Efficientnet","journal-title":"IEEE Access","doi-asserted-by":"crossref"},{"DOI":"10.7717/peerj.5161","key":"e_1_2_11_9_1","year":"2018","issue":null,"author":"Kim E.","volume":"6","first-page":null,"unstructured":null,"article-title":"Major Medical Causes by Breed and Life Stage for Dogs Presented at Veterinary Clinics in the Republic of Korea: A Survey of Electronic Medical Records","journal-title":"PeerJ","doi-asserted-by":"crossref"},{"DOI":"10.1186/s12917-021-02775-3","key":"e_1_2_11_10_1","year":"2021","issue":null,"author":"O'Neill D. G.","volume":"17","first-page":null,"unstructured":null,"article-title":"Prevalence of Commonly Diagnosed Disorders in UK Dogs Under Primary Veterinary Care: Results and Applications","journal-title":"BMC Veterinary Research","doi-asserted-by":"crossref"},{"DOI":null,"key":"e_1_2_11_11_1","year":"2013","issue":null,"author":"Miller W. H.","volume":null,"first-page":"66","unstructured":null,"article-title":null,"journal-title":null,"doi-asserted-by":null},{"DOI":"10.1136/vr.158.16.533","key":"e_1_2_11_12_1","year":"2006","issue":null,"author":"Hill P. B.","volume":"158","first-page":"533","unstructured":null,"article-title":"Survey of the Prevalence, Diagnosis and Treatment of Dermatological Conditions in Small Animals in General Practice","journal-title":"Veterinary Record","doi-asserted-by":"crossref"},{"DOI":null,"key":"e_1_2_11_13_1","year":"2012","issue":null,"author":"Ural K.","volume":"1","first-page":"86","unstructured":null,"article-title":"Understanding Primary and Secondary Skin Lesions Among Infectious Dermatoses in Dogs: Lessons We Learned From Cases","journal-title":"Animal Health and Production Hygiene","doi-asserted-by":null},{"DOI":"10.1177/03009858231170295","key":"e_1_2_11_14_1","year":"2023","issue":null,"author":"Welle M. M.","volume":"60","first-page":"748","unstructured":null,"article-title":"Canine Noninflammatory Alopecia: An Approach to Its Classification and a Diagnostic Aid","journal-title":"Veterinary Pathology","doi-asserted-by":"crossref"},{"DOI":"10.1111/vde.12107","key":"e_1_2_11_15_1","year":"2014","issue":null,"author":"Olivry T.","volume":"25","first-page":"77","unstructured":null,"article-title":"Validation of the Canine Atopic Dermatitis Extent and Severity Index (CADESI)‐4, a Simplified Severity Scale for Assessing Skin Lesions of Atopic Dermatitis in Dogs","journal-title":"Veterinary Dermatology","doi-asserted-by":"crossref"},{"DOI":"10.1111/j.1365-3164.2012.01113.x","key":"e_1_2_11_16_1","year":"2012","issue":null,"author":"Plant J. D.","volume":"23","first-page":null,"unstructured":null,"article-title":"Development and Validation of the Canine Atopic Dermatitis Lesion Index, a Scale for the Rapid Scoring of Lesion Severity in Canine Atopic Dermatitis","journal-title":"Veterinary Dermatology","doi-asserted-by":"crossref"},{"DOI":"10.1038/s41598-021-96707-8","key":"e_1_2_11_17_1","year":"2021","issue":null,"author":"Pham T.‐C.","volume":"11","first-page":"17485","unstructured":null,"article-title":"AI Outperformed Every Dermatologist in Dermoscopic Melanoma Diagnosis, Using an Optimized Deep‐CNN Architecture With Custom Mini‐Batch Logic and Loss Function","journal-title":"Scientific Reports","doi-asserted-by":"crossref"},{"DOI":"10.1016/j.dajour.2023.100278","key":"e_1_2_11_18_1","year":"2023","issue":null,"author":"Venugopal V.","volume":"8","first-page":null,"unstructured":null,"article-title":"A Deep Neural Network Using Modified EfficientNet for Skin Cancer Detection in Dermoscopic Images","journal-title":"Decision Analytics Journal","doi-asserted-by":"crossref"},{"DOI":"10.1111/jdv.15965","key":"e_1_2_11_19_1","year":"2020","issue":null,"author":"Zhao S.","volume":"34","first-page":"518","unstructured":null,"article-title":"Smart Identification of Psoriasis by Images Using Convolutional Neural Networks: A Case Study in China","journal-title":"Journal of the European Academy of Dermatology and Venereology","doi-asserted-by":"crossref"},{"DOI":"10.3390/diagnostics12081879","key":"e_1_2_11_20_1","year":"2022","issue":null,"author":"Huynh Q. T.","volume":"12","first-page":null,"unstructured":null,"article-title":"Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence","journal-title":"Diagnostics","doi-asserted-by":"crossref"},{"DOI":"10.1007/s42979-022-01645-5","key":"e_1_2_11_21_1","year":"2023","issue":null,"author":"Upadhyay A.","volume":"4","first-page":null,"unstructured":null,"article-title":"Dog Skin Diseases Detection and Identification Using Convolutional Neural Networks","journal-title":"SN Computer Science","doi-asserted-by":"crossref"},{"DOI":"10.1111/vde.13221","key":"e_1_2_11_22_1","year":"2024","issue":null,"author":"Smith A.","volume":"35","first-page":"138","unstructured":null,"article-title":"Computer Vision Model for the Detection of Canine Pododermatitis and Neoplasia of the Paw","journal-title":"Veterinary Dermatology","doi-asserted-by":"crossref"},{"DOI":"10.1111/vde.13332","key":"e_1_2_11_23_1","year":"2025","issue":null,"author":"Apostolopoulos N.","volume":"36","first-page":"424","unstructured":null,"article-title":"Detection of Canine External Ear Canal Lesions Using Artificial Intelligence","journal-title":"Veterinary Dermatology","doi-asserted-by":"crossref"},{"DOI":"10.1007/s13273-022-00249-7","key":"e_1_2_11_24_1","year":"2022","issue":null,"author":"Hwang S.","volume":"18","first-page":"299","unstructured":null,"article-title":"Classification of Dog Skin Diseases Using Deep Learning With Images Captured From Multispectral Imaging Device","journal-title":"Molecular & Cellular Toxicology","doi-asserted-by":"crossref"},{"DOI":"10.1145/3065386","key":"e_1_2_11_25_1","year":"2017","issue":null,"author":"Krizhevsky A.","volume":"60","first-page":"84","unstructured":null,"article-title":"ImageNet Classification With Deep Convolutional Neural Networks","journal-title":"Communications of the ACM","doi-asserted-by":"crossref"},{"DOI":"10.1080/21681163.2020.1824685","key":"e_1_2_11_26_1","year":"2021","issue":null,"author":"Zuluaga‐Gomez J.","volume":"9","first-page":"131","unstructured":null,"article-title":"A CNN‐Based Methodology for Breast Cancer Diagnosis Using Thermal Images","journal-title":"Computational Methods in Biomechanics and Biomedical Engineering. Imaging & Visualization","doi-asserted-by":"crossref"},{"DOI":"10.1007/s42979-020-0074-0","key":"e_1_2_11_27_1","year":"2020","issue":null,"author":"Zheng W.","volume":"1","first-page":null,"unstructured":null,"article-title":"The Effects of Class Imbalance and Training Data Size on Classifier Learning: An Empirical Study","journal-title":"SN Computer Science","doi-asserted-by":"crossref"},{"DOI":"10.1186/s12917-018-1569-y","key":"e_1_2_11_28_1","year":"2018","issue":null,"author":"Olivry T.","volume":"14","first-page":"238","unstructured":null,"article-title":"Development of a Core Outcome Set for Therapeutic Clinical Trials Enrolling Dogs With Atopic Dermatitis (COSCAD'18)","journal-title":"BMC Veterinary Research","doi-asserted-by":"crossref"},{"DOI":"10.1126/sciadv.abq6147","key":"e_1_2_11_29_1","year":"2022","issue":null,"author":"Daneshjou R.","volume":"8","first-page":null,"unstructured":null,"article-title":"Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set","journal-title":"Science Advances","doi-asserted-by":"crossref"},{"DOI":"10.1038/s41591-023-02728-3","key":"e_1_2_11_30_1","year":"2024","issue":null,"author":"Groh M.","volume":"30","first-page":"573","unstructured":null,"article-title":"Deep Learning‐Aided Decision Support for Diagnosis of Skin Disease Across Skin Tones","journal-title":"Nature Medicine","doi-asserted-by":"crossref"},{"DOI":"10.1016/j.xjidi.2022.100150","key":"e_1_2_11_31_1","year":"2023","issue":null,"author":"Jeong H. K.","volume":"3","first-page":null,"unstructured":null,"article-title":"Deep Learning in Dermatology: A Systematic Review of Current Approaches, Outcomes, and Limitations","journal-title":"JID Innovations","doi-asserted-by":"crossref"},{"DOI":"10.1038/s41746-024-01033-8","key":"e_1_2_11_32_1","year":"2024","issue":null,"author":"Venkatesh K. P.","volume":"7","first-page":"32","unstructured":null,"article-title":"Deep Learning Models Across the Range of Skin Disease","journal-title":"NPJ Digital Medicine","doi-asserted-by":"crossref"},{"DOI":"10.1109/APCIT62007.2024.10673511","key":"e_1_2_11_33_1","year":null,"issue":null,"author":null,"volume":null,"first-page":null,"unstructured":"Y.Yashu V.Kukreja P.Srivastava A.Garg andS.Hariharan “Paws and Pixels: Enhancing Canine Dermatology Through Image Analysis ”In2024 Asia Pacific Conference on Innovation in Technology (APCIT) Mysore India: 2024; 1–6.","article-title":null,"journal-title":null,"doi-asserted-by":"crossref"},{"DOI":"10.1111/vop.70052","key":"e_1_2_11_34_1","year":"2026","issue":null,"author":"Okur S.","volume":"29","first-page":null,"unstructured":null,"article-title":"Comparison of Diagnostic Performance Between Large Language Models and Veterinary Evaluators in Feline Ocular Diseases Based on Clinical Summaries and Anterior Segment Photographs","journal-title":"Veterinary Ophthalmology","doi-asserted-by":"crossref"}],"short-title":[],"update-policy":"https://doi.org/10.1002/crossmark_policy","alternative-id":["10.1111/vde.70083"],"article-number":"vde.70083","content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"original-title":[],"container-title":["Veterinary Dermatology"],"reference-count":33,"published-online":{"date-time":null,"timestamp":null,"date-parts":[[2026,5,1]]},"references-count":33,"short-container-title":["Veterinary Dermatology"],"is-referenced-by-count":0},"unpaywall":{"doi":"10.1111/vde.70083","is_oa":false,"title":"Artificial Intelligence‐Based Identification of Common Canine Skin Lesions From Clinical Images","updated":"2026-05-05T11:59:32+00:00","published_date":"2026-05-01","best_oa_location":null}},"created_at":"2026-05-14T15:13:26.918Z","updated_at":"2026-05-14T15:13:26.918Z","tags":[{"paper_doi":"10.1111/vde.70083","tag_type":"category","value":"Dermatology","value_numeric":null},{"paper_doi":"10.1111/vde.70083","tag_type":"condition","value":"Canine Skin Lesions","value_numeric":null},{"paper_doi":"10.1111/vde.70083","tag_type":"study_design","value":"Diagnostic Accuracy Study","value_numeric":null},{"paper_doi":"10.1111/vde.70083","tag_type":"warning","value":"External validation and gold-standard adjudication are not described in the excerpt.","value_numeric":null},{"paper_doi":"10.1111/vde.70083","tag_type":"warning","value":"Sample size and dataset splits are not stated in the provided text.","value_numeric":null},{"paper_doi":"10.1111/vde.70083","tag_type":"warning","value":"Study design is inferred as diagnostic accuracy/model development; full design details are not provided here.","value_numeric":null}],"summaries":{"what_studied":"A convolutional neural network approach (four EfficientNet models) was trained to identify four canine skin lesion types—erythema, lichenification, alopecia, and erosion/ulcer—from clinical images, using veterinary surgeon–labeled data as the reference and reporting accuracy, sensitivity, specificity, PPV, NPV, and F1.","key_result":"All four models had accuracy >90%. The alopecia model had 98.12% accuracy and a 98.18% F1 score; the lichenification model had an 87.02% sensitivity and an 89.88% F1 score; erythema and erosion/ulcer showed balanced performance across metrics (no further numbers provided).","limitations":"Single-center image set from a veterinary teaching hospital may limit generalizability. The reference standard was surgeon labels rather than an independent gold standard.","practice_takeaway":"CNNs can accurately flag common canine skin lesions from routine photos, with strongest performance for alopecia. These tools may support faster, more objective lesion assessment and monitoring in practice."}}],"initialOffset":1,"fetchConfig":{"kind":"tags","tags":[{"tag_type":"condition","value":"Canine Skin Lesions"}]},"breadcrumbItems":[{"name":"Home","href":"/"},{"name":"Research Hub","href":"/hub"},{"name":"Conditions","href":"/hub/tag/condition"},{"name":"Canine Skin Lesions"}],"hrefConfig":{"basePath":"/hub/papers","webViewQueryParams":{"hub_ctx":"tag","hub_tag_type":"condition","hub_tag_value":"Canine Skin Lesions"}}}]]

Papers