{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T11:24:56Z","timestamp":1786879496647,"version":"build-2736575974"},"reference-count":28,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T00:00:00Z","timestamp":1786838400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T00:00:00Z","timestamp":1786838400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["analyticalsciencejournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Microscopy Res &amp; Technique"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Histological image classification plays a critical role in biomedical research and diagnostic processes. Advances in the field of deep learning present significant opportunities for enhancing diagnostic accuracy and developing automated decision support systems. This study aims to comparatively evaluate the out\u2010of\u2010distribution generalization and cross\u2010domain classification performance of different deep neural network encoders. In this study, models were trained on an internal dataset of 4307 hematoxylin and eosin (H&amp;E) stained images of male rat lung, cerebellum, and adipose tissues, obtained under ethical committee approval (Ege University, HADYEK 2026\u201006). To evaluate genuine generalization, testing was conducted on a separate, diverse external cohort of 600 mixed human\u2010and\u2010animal images. Nine different deep learning architectures\u2014MobileNetV3\u2010S, MobileNetV3\u2010L, DenseNet121, DenseNet201, ConvNeXt\u2010S, ConvNeXt\u2010B, DINOv3 ViT\u2010S, DINOv3 ViT\u2010H+, and the pathology foundation model UNI2\u2010h\u2014were evaluated using frozen feature extraction combined with a linear probe. For performance evaluation, accuracy, sensitivity, specificity,\n                    <jats:italic>F<\/jats:italic>\n                    1 score, Cohen's\n                    <jats:italic>\u03ba<\/jats:italic>\n                    , and ROC\u2010AUC metrics were analyzed along with per\u2010image inference times. While all models achieved near\u2010perfect results during internal cross\u2010validation, their performance diverged significantly on the external dataset, confirming that the observed differences reflect genuine cross\u2010domain generalization capabilities rather than under\u2010fitting. All competitive models demonstrated high performance in classifying adipose and cerebellum tissues, achieving an\n                    <jats:italic>F<\/jats:italic>\n                    1 score of 95% or higher for these tissues. In distinguishing the lung tissue, which has the most diverse structure and is the most difficult to classify, the UNI2\u2010h model emerged as the most successful, achieving an\n                    <jats:italic>F<\/jats:italic>\n                    1 score of 97.4% and a recall of 95.0%. When evaluated in terms of computational efficiency, the MobileNetV3\u2010Small model stood out as having the lowest processing time among all scenarios, demonstrating an inference time of 9.4\u2009ms on the CPU and 12.5\u2009ms on the GPU. In conclusion, while the pathology foundation model UNI2\u2010h achieved the highest accuracy values across all metrics, the ConvNeXt\u2010Small model was identified as the system providing the optimal balance between speed and accuracy. These findings indicate that although UNI2\u2010h stands out for the most precise results in cross\u2010domain classifications, the ConvNeXt\u2010Small architecture emerges as an ideal alternative, particularly in practical applications where computational efficiency is critical and resources are constrained.\n                  <\/jats:p>","DOI":"10.1002\/jemt.70173","type":"journal-article","created":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T10:30:12Z","timestamp":1786876212000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross\u2010Species Generalization and Comparative Performance Analysis of Deep Neural Network Architectures in Histological Image Classification"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9655-0286","authenticated-orcid":false,"given":"Kaan","family":"Celen","sequence":"first","affiliation":[{"name":"Department of Histology and Embryology, Faculty of Medicine Ege University  Izmir Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6475-642X","authenticated-orcid":false,"given":"Fatih","family":"Oltulu","sequence":"additional","affiliation":[{"name":"Department of Histology and Embryology, Faculty of Medicine Ege University  Izmir Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8372-1183","authenticated-orcid":false,"given":"Buse","family":"Caglar","sequence":"additional","affiliation":[{"name":"Software Testing Department Boyner Retailing  Istanbul Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3759-6616","authenticated-orcid":false,"given":"Aylin","family":"Buhur","sequence":"additional","affiliation":[{"name":"Department of Basic Sciences, Faculty of Dentistry Galata University  Istanbul Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7995-7650","authenticated-orcid":false,"given":"Burak","family":"Kilicarslan","sequence":"additional","affiliation":[{"name":"Software Development Department Pasifik Health Tech Software  Istanbul Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2464-6783","authenticated-orcid":false,"given":"Burhan Berk","family":"\u00c7olak","sequence":"additional","affiliation":[{"name":"Department of Statistics, Graduate School of Natural and Applied Sciences Ege University  Izmir Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4227-1637","authenticated-orcid":false,"given":"Altug","family":"Yavasoglu","sequence":"additional","affiliation":[{"name":"Department of Histology and Embryology, Faculty of Medicine Ege University  Izmir Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,16]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00414\u2010025\u201003659\u2010z"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885\u2010025\u201013563\u20109"},{"key":"e_1_2_12_4_1","unstructured":"Arora E.2026.\u201cLost in Translation: How Language Re\u2010Aligns Vision for Cross\u2010Species Pathology.\u201dPreprint arXiv.http:\/\/arxiv.org\/abs\/2603.04405."},{"key":"e_1_2_12_5_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.104491","article-title":"Comparison of Texture\u2010Based Classification and Deep Learning for Plantar Soft Tissue Histology Segmentation","volume":"134","author":"Brady L.","year":"2021","journal-title":"Computers in Biology and Medicine"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12040369"},{"key":"e_1_2_12_7_1","volume-title":"Genotype\u2010Tissue Expression (GTEx) Portal","author":"GTEx Consortium","year":"2026"},{"issue":"12","key":"e_1_2_12_8_1","doi-asserted-by":"crossref","first-page":"1374","DOI":"10.5858\/arpa.2022-0462-RA","article-title":"An Update on the Role of Immunohistochemistry in the Evaluation of Pancreatic\/Liver\/Gastrointestinal Luminal Tract Disorders","volume":"147","author":"Huang J.","year":"2023","journal-title":"Archives of Pathology and Laboratory Medicine"},{"key":"e_1_2_12_9_1","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.canlet.2019.12.007","article-title":"Artificial Intelligence in Cancer Diagnosis and Prognosis: Opportunities and Challenges","volume":"471","author":"Huang S.","year":"2020","journal-title":"Cancer Letters"},{"key":"e_1_2_12_10_1","doi-asserted-by":"crossref","first-page":"2832","DOI":"10.1002\/glia.24454","article-title":"Pathological Bergmann Glia Alterations and Disrupted Calcium Dynamics in Ataxic Canavan Disease Mice","volume":"71","author":"Hull V. L.","year":"2023","journal-title":"Glia"},{"key":"e_1_2_12_11_1","first-page":"289","article-title":"Predictive Pathology in Routine Diagnostics of Solid Tumors","volume":"27","author":"Lassmann S.","year":"2012","journal-title":"Histology and Histopathology"},{"key":"e_1_2_12_12_1","doi-asserted-by":"crossref","first-page":"754","DOI":"10.3350\/cmh.2021.0394","article-title":"Deep Learning\u2010Based Prediction of Molecular Cancer Biomarkers From Tissue Slides: A New Tool for Precision Oncology","volume":"28","author":"Lee S. H.","year":"2022","journal-title":"Clinical and Molecular Hepatology"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201007883\u2010w"},{"key":"e_1_2_12_14_1","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/RBME.2024.3357877","article-title":"Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions","volume":"18","author":"Luo L.","year":"2025","journal-title":"IEEE Reviews in Biomedical Engineering"},{"key":"e_1_2_12_15_1","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.soc.2021.12.001","article-title":"Colorectal Cancer: Preoperative Evaluation and Staging","volume":"31","author":"Mahmoud N. N.","year":"2022","journal-title":"Surgical Oncology Clinics of North America"},{"key":"e_1_2_12_16_1","article-title":"Paraseptal Emphysema","volume":"49","author":"Marchiori E.","year":"2024","journal-title":"Jornal Brasileiro de Pneumologia"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201057970\u20107"},{"key":"e_1_2_12_18_1","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/s41586-019-1799-6","article-title":"International Evaluation of an AI System for Breast Cancer Screening","volume":"577","author":"McKinney S. M.","year":"2020","journal-title":"Nature"},{"key":"e_1_2_12_19_1","volume-title":"Nonneoplastic Lesion Atlas","author":"National Toxicology Program","year":"2026"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae004"},{"key":"e_1_2_12_21_1","volume-title":"Circuits Within the Cerebellum","author":"Purves D.","year":"2001"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjonc\u20102026\u2010001102"},{"key":"e_1_2_12_23_1","unstructured":"Scienta Team E.Bandasack V.Bouget et\u00a0al.2026.\u201cEVA: Towards a Universal Model of the Immune System.\u201dPreprint arXiv.http:\/\/arxiv.org\/abs\/2602.10168."},{"key":"e_1_2_12_24_1","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1097\/PAS.0000000000002495","article-title":"Pseudoneoplastic Fat Atrophy of Intra\u2010Abdominal Sites: A Clinicopathologic Study of 16 Cases Representing a Potential Diagnostic Pitfall","volume":"50","author":"Suster D. I.","year":"2026","journal-title":"American Journal of Surgical Pathology"},{"key":"e_1_2_12_25_1","unstructured":"Tizhoosh H. R.2026.\u201cBeyond the Failures: Rethinking Foundation Models in Pathology.\u201dPreprint arXiv.http:\/\/arxiv.org\/abs\/2510.23807."},{"key":"e_1_2_12_26_1","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1038\/s41591-021-01343-4","article-title":"Deep Learning in Histopathology: The Path to the Clinic","volume":"27","author":"Laak J.","year":"2021","journal-title":"Nature Medicine"},{"key":"e_1_2_12_27_1","doi-asserted-by":"crossref","first-page":"eabo4802","DOI":"10.1126\/scitranslmed.abo4802","article-title":"Improving Breast Cancer Diagnostics With Deep Learning for MRI","volume":"14","author":"Witowski J.","year":"2022","journal-title":"Science Translational Medicine"},{"key":"e_1_2_12_28_1","unstructured":"Wu J.\u2010C. Q.Ye D.\u2010L.Deng et\u00a0al.2024.\u201cNo\u2010Free\u2010Lunch Theories for Tensor\u2010Network Machine Learning Models.\u201dPreprint arXiv.http:\/\/arxiv.org\/abs\/2412.05674."},{"key":"e_1_2_12_29_1","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1148\/radiol.2019190372","article-title":"Lymph Node Metastasis Prediction From Primary Breast Cancer US Images Using Deep Learning","volume":"294","author":"Zhou L.\u2010Q.","year":"2020","journal-title":"Radiology"}],"container-title":["Microscopy Research and Technique"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jemt.70173","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jemt.70173","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jemt.70173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T10:30:20Z","timestamp":1786876220000},"score":1,"resource":{"primary":{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/10.1002\/jemt.70173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,16]]},"references-count":28,"alternative-id":["10.1002\/jemt.70173"],"URL":"https:\/\/doi.org\/10.1002\/jemt.70173","archive":["Portico"],"relation":{},"ISSN":["1059-910X","1097-0029"],"issn-type":[{"value":"1059-910X","type":"print"},{"value":"1097-0029","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,16]]},"assertion":[{"value":"2026-04-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"jemt.70173"}}