{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T12:13:38Z","timestamp":1780402418984,"version":"3.54.1"},"reference-count":26,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"KAU Endowment (WAQF) at King Abdulaziz University, Jeddah, Saudi Arabia"},{"name":"Deanship of Scientific Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Transmission electron microscopy (TEM) is an essential tool for diagnosing renal diseases. It produces high-resolution visualization of glomerular and mesangial ultrastructural features. However, manual interpretation of TEM images is labor-intensive and prone to interobserver variability. In this study, we introduced and evaluated deep learning architectures based on YOLOv8-OBB for automated detection of six ultrastructural features in kidney biopsy TEM images: glomerular basement membrane, mesangial folds, mesangial deposits, normal podocytes, podocytopathy, and subepithelial deposits. Methods: Building on our previous work, we propose a modified YOLOv8-OBB architecture that incorporates three major refinements: a grayscale input channel, a high-resolution P2 feature pyramid with refinement blocks (FPRbl), and a four-branch oriented detection head designed to detect small-to-large structures at multiple image scales (feature-map strides of 4, 8, 16, and 32 pixels). We compared two pretrained variants: our previous YOLOv8-OBB model developed with a grayscale input channel (GSch) and four additional feature-extraction layers (4FExL) (Pretrained + GSch + 4FExL) and the newly developed (Pretrained + FPRbl). Results: Quantitative assessment showed that our previously developed model (Pretrained + GSch + 4FExL) achieved an F1-score of 0.93 and mAP@0.5 of 0.953, while the (Pretrained + FPRbl) model developed in this study achieved an F1-score of 0.92 and mAP@0.5 of 0.941, demonstrating strong and clinically meaningful performance for both approaches. Qualitative assessment based on expert visual inspection of predicted bounding boxes revealed complementary strengths: (Pretrained + GSch + 4FExL) exhibited higher recall for subtle or infrequent findings, whereas (Pretrained + FPRbl) produced cleaner bounding boxes with higher-confidence predictions. Conclusions: This study presents how targeted architectural refinements in YOLOv8-OBB can enhance the detection of small, low-contrast, and variably oriented ultrastructural features in renal TEM images. Evaluating these refinements and translating them into a web-based platform (Renal-AI) showed the clinical applicability of deep learning-based tools for improving diagnostic efficiency and reducing interpretive variability in kidney pathology.<\/jats:p>","DOI":"10.3390\/diagnostics16020264","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T11:01:14Z","timestamp":1768388474000},"page":"264","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Renal-AI: A Deep Learning Platform for Multi-Scale Detection of Renal Ultrastructural Features in Electron Microscopy Images"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4693-1594","authenticated-orcid":false,"given":"Leena","family":"Nezamuldeen","sequence":"first","affiliation":[{"name":"The Vaccines and Immunotherapy Unit, King Fahd Medical Research Center, King Abdulaziz University, Jeddah 22254, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Walaa","family":"Mal","sequence":"additional","affiliation":[{"name":"Faculty of Applied Medical Sciences, Department of Medical Laboratory Sciences, King Abdulaziz University, Jeddah 22254, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8664-7571","authenticated-orcid":false,"given":"Reem A.","family":"Al Zahrani","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Department of Pathology, King Abdulaziz University, Jeddah 22254, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahar","family":"Jambi","sequence":"additional","affiliation":[{"name":"Faculty of Computing and Information Technology, Department of Information Systems, King Abdulaziz University, Jeddah 22254, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3174-1007","authenticated-orcid":false,"given":"M. Saleet","family":"Jafri","sequence":"additional","affiliation":[{"name":"School of Systems Biology, George Mason University, Fairfax, VA 22030, USA"},{"name":"Center for Biomedical Engineering and Technology, School of Medicine, University of Maryland, Baltimore, MD 21201, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"ref_1","first-page":"7","article-title":"Epidemiology of chronic kidney disease: An update 2022","volume":"Volume 12","author":"Kovesdy","year":"2022","journal-title":"Kidney International Supplements 2011"},{"key":"ref_2","unstructured":"Transplantation, S.C.f.O. (2024, January 11). The Saudi Center for Organ Transplantation, Available online: https:\/\/www.scot.gov.sa\/en\/home-page."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1555","DOI":"10.1038\/modpathol.3800239","article-title":"Practice guidelines for the renal biopsy","volume":"17","author":"Walker","year":"2004","journal-title":"Mod. Pathol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Basso, M.N., Barua, M., Meyer, J., John, R., and Khademi, A. (2022). Machine learning in renal pathology. Front. Nephrol., 2.","DOI":"10.3389\/fneph.2022.1007002"},{"key":"ref_5","first-page":"400","article-title":"Interobserver Variability in Assessment of Renal Mass Biopsies","volume":"18","author":"Nyk","year":"2020","journal-title":"Urol. J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1007\/s10278-009-9233-5","article-title":"Analysis of the glomerular basement membrane in images of renal biopsies using the split-and-merge method: A pilot study","volume":"23","author":"Kamenetsky","year":"2010","journal-title":"J. Digit. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"225","DOI":"10.17305\/bjbms.2022.8318","article-title":"Artificial intelligence in renal pathology: Current status and future","volume":"23","author":"Feng","year":"2023","journal-title":"Biomol. Biomed."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wen, Q., Jin, L., and Chen, W. (2022). Artificial Intelligence-Assisted Renal Pathology: Advances and Prospects. J. Clin. Med., 11.","DOI":"10.3390\/jcm11164918"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/s40620-021-01221-9","article-title":"Assessment of glomerular morphological patterns by deep learning algorithms","volume":"35","author":"Weis","year":"2022","journal-title":"J. Nephrol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"106619","DOI":"10.1016\/j.bspc.2024.106619","article-title":"Swin Transformer based detection and segmentation networks for measurement and quantification analysis of arteriolar vessels from renal whole slide images","volume":"96","author":"Zhou","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_11","first-page":"124710K","article-title":"Spatially Aware Transformer Networks for Contextual Prediction of Diabetic Nephropathy Progression from Whole Slide Images","volume":"12471","author":"Shickel","year":"2023","journal-title":"medRxiv"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"38957","DOI":"10.1038\/s41598-025-22814-5","article-title":"Transformer-based multiclass segmentation pipeline for basic kidney histology","volume":"15","author":"He","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2081","DOI":"10.1681\/ASN.2017111210","article-title":"Region-Based Convolutional Neural Nets for Localization of Glomeruli in Trichrome-Stained Whole Kidney Sections","volume":"29","author":"Bukowy","year":"2018","journal-title":"J. Am. Soc. Nephrol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"101808","DOI":"10.1016\/j.artmed.2020.101808","article-title":"Classification of glomerular hypercellularity using convolutional features and support vector machine","volume":"103","author":"Chagas","year":"2020","journal-title":"Artif. Intell. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1016\/j.ajpath.2021.05.004","article-title":"A Deep Learning-Based Approach for Glomeruli Instance Segmentation from Multistained Renal Biopsy Pathologic Images","volume":"191","author":"Jiang","year":"2021","journal-title":"Am. J. Pathol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ma, P., Li, J., Zhang, Z., Qiu, W., Li, D., Wang, J., Li, B., Guo, S., Zhang, J., and Cen, Z. (2025). AI-based system for analysis of electron microscope images in glomerular disease. JAMA Netw. Open, 8.","DOI":"10.1001\/jamanetworkopen.2025.34985"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1080\/01913123.2021.1882628","article-title":"Deep learning for the classification of medical kidney disease: A pilot study for electron microscopy","volume":"45","author":"Hacking","year":"2021","journal-title":"Ultrastruct. Pathol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, J., and Zhang, A. (2023). Deep learning-based multi-model approach on electron microscopy image of renal biopsy classification. BMC Nephrol., 24.","DOI":"10.1186\/s12882-023-03182-6"},{"key":"ref_19","unstructured":"Alsadi, A., Majeed, N.K., Saeed, D.M., Dharmamer, Y., Singh, M.B., and Patel, T.N. (2022). A deep-learning approach at automated detection of electrondense immune deposits in medical renal biopsies. J. Nephropathol., 11."},{"key":"ref_20","unstructured":"Nezamuldeen, L., Mal, W., Al Zahrani, R.A., Jambi, S., and Jafri, M.S. (2025, January 6\u201310). The Detection of Ultrastructural Features on Electron Microscope Images of Renal Samples Using Deep Learning. Proceedings of the 37th European Congress of Pathology, Vienna, Austria."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jones, T.C., Hard, G.C., and Mohr, U. (1998). Urinary System, Springer. [2nd ed.].","DOI":"10.1007\/978-3-642-80335-2"},{"key":"ref_22","unstructured":"Bradski, G., and Kaehler, A. (2000). OpenCV. Dr. Dobb\u2019s Journal of Software Tools, Prentice Hall."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Redmon, J. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_24","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2023, June 10). Ultralytics YOLOv8. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"067501","DOI":"10.1117\/1.JMI.8.6.067501","article-title":"Deep learning segmentation of glomeruli on kidney donor frozen sections","volume":"8","author":"Li","year":"2021","journal-title":"J. Med. Imaging"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1684218","DOI":"10.1155\/2019\/1684218","article-title":"Automatic Segmentation of Pathological Glomerular Basement Membrane in Transmission Electron Microscopy Images with Random Forest Stacks","volume":"2019","author":"Cao","year":"2019","journal-title":"Comput. Math. Methods Med."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/2\/264\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T05:53:39Z","timestamp":1768542819000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/2\/264"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":26,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["diagnostics16020264"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16020264","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]}}}