{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T05:50:06Z","timestamp":1769579406719,"version":"3.49.0"},"reference-count":55,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:00:00Z","timestamp":1769472000000},"content-version":"vor","delay-in-days":26,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Recent trends in computational pathology favour increasingly complex deep learning architectures, raising the question of whether such complexity is necessary for routine diagnostic tasks. This study challenges this assumption through a comprehensive analysis of the relationship between model complexity, data pre\u2010processing, and performance across four fundamental digital pathology tasks: nuclei counting, steatosis quantification, glomeruli detection, and Ki67 proliferation index (PI) assessment. We evaluated five deep learning models of varying complexity (lightweight: MobileNetV2, U\u2010Net, and more complex: ConvNeXt, K\u2010Net, and Swin Transformer) combined with different image pre\u2010processing techniques. To evaluate model performance without extensive ground truth (GT) annotations, we introduced a validation strategy utilizing the relative absolute deviation (RAD) between network predictions and correlation of performance metrics. Our findings demonstrate that pre\u2010processing strategies, particularly stain normalization (NORM), can be more impactful than model complexity, reducing error rates by up to 50% compared to processing original (ORIG) images. With appropriate pre\u2010processing, lightweight models achieved comparable or superior results to complex models while reducing processing times by up to 40%. Only specific tasks involving complex morphological features, such as glomeruli detection, significantly benefited from more sophisticated architectures. This study provides an evidence\u2010based framework for selecting optimal model\u2010pre\u2010processing combinations in clinical settings, suggesting that investing in pre\u2010processing pipelines rather than model complexity may be more beneficial for routine computational pathology applications.<\/jats:p>","DOI":"10.1049\/ipr2.70290","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T17:23:45Z","timestamp":1769534625000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Shifting the Focus of Digital Pathology: The Raising Relevance of Pre\u2010Processing Phase Over Model Complexity"],"prefix":"10.1049","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-7401","authenticated-orcid":false,"given":"Massimo","family":"Salvi","sequence":"first","affiliation":[{"name":"Biolab, PoliTo<sup>BIO<\/sup>Med Lab Department of Electronics and Telecommunications Politecnico Di Torino  Turin Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicola","family":"Michielli","sequence":"additional","affiliation":[{"name":"Biolab, PoliTo<sup>BIO<\/sup>Med Lab Department of Electronics and Telecommunications Politecnico Di Torino  Turin Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Mogetta","sequence":"additional","affiliation":[{"name":"Biolab, PoliTo<sup>BIO<\/sup>Med Lab Department of Electronics and Telecommunications Politecnico Di Torino  Turin Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Gambella","sequence":"additional","affiliation":[{"name":"Pathology Unit Department of Surgical Sciences and Integrated Diagnostics (DISC) University of Genoa  Genoa Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulkadir","family":"Sengur","sequence":"additional","affiliation":[{"name":"Electrical\u2010Electronics Engineering Department Technology Faculty Firat University  Elazig Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filippo","family":"Molinari","sequence":"additional","affiliation":[{"name":"Biolab, PoliTo<sup>BIO<\/sup>Med Lab Department of Electronics and Telecommunications Politecnico Di Torino  Turin Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arkadiusz","family":"Gertych","sequence":"additional","affiliation":[{"name":"Faculty of Biomedical Engineering Silesian University of Technology  Gliwice Poland"},{"name":"Department of Surgery Cedars\u2010Sinai Medical Center  Los Angeles California USA"},{"name":"Department of Pathology and Laboratory Medicine Cedars\u2010Sinai Medical Center  Los Angeles California USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2026,1,27]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41379\u2010021\u201000919\u20102"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.13045"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2023.3297604"},{"issue":"2","key":"e_1_2_10_5_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.jhepr.2024.101270","article-title":"AI\u2010Based Tumor\u2010infiltrating Lymphocytes Scoring System for Assessing HCC Prognosis in Patients Undergoing Liver Resection","volume":"7","author":"Chen Z.","year":"2024","journal-title":"JHEP Reports"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12941"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41698\u2010024\u201000575\u20100"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12652"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mpdhp.2024.08.001"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.labinv.2024.102111"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/his.15178"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44222\u2010023\u201000096\u20108"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.4103\/jpi.jpi_53_18"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12112794"},{"key":"e_1_2_10_15_1","unstructured":"L.Deininger B.Stimpel A.Yuce et\u00a0al.A Comparative Study Between Vision Transformers and CNNs in Digital Pathology ArXiv Preprint ArXiv:2206.00389 (2022)."},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104129"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2021.101930"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhep.2023.11.013"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2021.101865"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112081"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41374\u2010020\u201000514\u20100"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2947628"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103836"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101544"},{"issue":"3","key":"e_1_2_10_25_1","first-page":"503","article-title":"Semantic Segmentation Framework for Glomeruli Detection and Classification in Kidney Histological Sections","volume":"9","author":"Altini N.","year":"2020","journal-title":"Electronics (Basel)"},{"key":"e_1_2_10_26_1","doi-asserted-by":"crossref","unstructured":"M.Sandler A.Howard M.Zhu A.Zhmoginov andL.\u2010C.Chen \u201cMobilenetv2: Inverted Residuals and Linear Bottlenecks \u201d inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition(2018):4510\u20134520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"O.Ronneberger P.Fischer andT.Brox \u201cU\u2010Net: Convolutional Networks for Biomedical Image Segmentation \u201d inMedical Image Computing and Computer\u2010Assisted Intervention\u2013MICCAI 2015(2015):234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_10_28_1","doi-asserted-by":"crossref","unstructured":"Z.Liu H.Mao C.\u2010Y.Wu C.Feichtenhofer T.Darrell andS.Xie \u201cA Convnet for the 2020s \u201d in:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition9(2022):11976\u201311986.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_2_10_29_1","first-page":"10326","article-title":"K\u2010Net: Towards Unified Image Segmentation","volume":"34","author":"Zhang W.","year":"2021","journal-title":"NIPS'21: Proceedings of the 35th International Conference on Neural Information Processing Systems"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"Z.Liu Y.Lin Y.Cao et\u00a0al. \u201cSwin Transformer: Hierarchical Vision Transformer Using Shifted Windows \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision(2021):10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105506"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpi.2022.100145"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajpath.2025.01.009"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12530\u2010023\u201009491\u20103"},{"issue":"1","key":"e_1_2_10_35_1","first-page":"49","article-title":"An Innovative Methodology for the Automated Morphometric and Quantitative Estimation of Liver Steatosis","volume":"24","author":"Liquori G. E.","year":"2009","journal-title":"Histology and Histopathology"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1097\/MNH.0b013e3283410a7d"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1159\/000346475"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2677499"},{"key":"e_1_2_10_39_1","unstructured":"Mms. Contributors MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark (2020)."},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdu450"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/modpathol.2017.46"},{"issue":"5","key":"e_1_2_10_42_1","doi-asserted-by":"crossref","first-page":"1058","DOI":"10.1111\/liv.15217","article-title":"Consensus Recommendations for Histological Criteria of Autoimmune Hepatitis From the International AIH Pathology Group: Results of a Workshop on AIH Histology Hosted by the European Reference Network on Hepatological Diseases and the European Society of Pathology","volume":"42","author":"Lohse A. W.","year":"2022","journal-title":"Liver International"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00428\u2010022\u201003454\u2010w"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/modpathol.2012.72"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41379\u2010022\u201001055\u20101"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12022\u2010023\u201009755\u20103"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13000\u2010022\u201001225\u20104"},{"issue":"5","key":"e_1_2_10_48_1","first-page":"301","article-title":"Minimal Requirements for the Molecular Testing of Lung Cancer","volume":"3","author":"Popper H. H.","year":"2014","journal-title":"Translational Lung Cancer Research"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2007.12.9858"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lungcan.2011.10.017"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010018\u201037638\u20109"},{"key":"e_1_2_10_52_1","first-page":"1","article-title":"The Role of the Pathologist in the Design and Conducting of Biomarker\u2010driven Clinical Trials in Cancer: Position Paper of the European Society of Pathology","author":"Matias\u2010Guiu X.","year":"2024","journal-title":"Virchows Archiv"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00428-015-1857-x"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9101644"},{"key":"e_1_2_10_55_1","unstructured":"R.Deng C.Cui Q.Liu et\u00a0al. Segment Anything Model (Sam) for Digital Pathology: Assess Zero\u2010Shot Segmentation on Whole Slide Imaging ArXiv Preprint ArXiv:2304.04155 (2023)."},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110621"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70290","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70290","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T17:23:48Z","timestamp":1769534628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/ipr2.70290"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70290","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-09-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70290"}}