{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:58:24Z","timestamp":1790211504057,"version":"4.1.0"},"reference-count":36,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Science and Higher Education of the Russian Federation","award":["075-15-2022-1110"],"award-info":[{"award-number":["075-15-2022-1110"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Segmenting nerve fibres in histological images is a tricky job because of how much the tissue looks can change. Modern neural network architectures, including U-Net and transformers, demonstrate varying degrees of effectiveness in this area. The aim of this study is to conduct a comparative analysis of the SegFormer, VGG-UNet, and FabE-Net models in terms of segmentation quality and speed. Methods: The training sample consisted of more than 75,000 pairs of images of different tissues (original slice and corresponding mask), scaled from 1024 \u00d7 1024 to 224 \u00d7 224 pixels to optimise computations. Three neural network architectures were used: the classic VGG-UNet, FabE-Net with attention and global context perception blocks, and the SegFormer transformer model. For an objective assessment of the quality of the models, expert validation was carried out with the participation of four independent pathologists, who evaluated the quality of segmentation according to specified criteria. Quality metrics (precision, recall, F1-score, accuracy) were calculated as averages based on the assessments of all experts, which made it possible to take into account variability in interpretation and increase the reliability of the results. Results: SegFormer achieved stable stabilisation of the loss function faster than the other models\u2014by the 20\u201330th epoch, compared to 45\u201360 epochs for VGG-UNet and FabE-Net. Despite taking longer to train per epoch, SegFormer produced the best segmentation quality, with the following metrics: precision 0.84, recall 0.99, F1-score 0.91 and accuracy 0.89. It also annotated a complete histological section in the fastest time. Visual analysis revealed that, compared to other models, which tended to produce incomplete or excessive segmentation, SegFormer more accurately and completely highlights nerve structures. Conclusions: Using attention mechanisms in SegFormer compensates for morphological variability in tissues, resulting in faster and higher-quality segmentation. Image scaling does not impair training quality while significantly accelerating computational processes. These results confirm the potential of SegFormer for practical use in digital pathology, while also highlighting the need for high-precision, immunohistochemistry-informed labelling to improve segmentation accuracy.<\/jats:p>","DOI":"10.3390\/diagnostics15182408","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T11:18:16Z","timestamp":1758539896000},"page":"2408","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Comparative Analysis of SegFormer, FabE-Net and VGG-UNet Models for the Segmentation of Neural Structures on Histological Sections"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6175-8403","authenticated-orcid":false,"given":"Igor","family":"Makarov","sequence":"first","affiliation":[{"name":"Almazov National Medical Research Centre, St. Petersburg 197341, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Koshevaya","sequence":"additional","affiliation":[{"name":"Almazov National Medical Research Centre, St. Petersburg 197341, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alina","family":"Pechenina","sequence":"additional","affiliation":[{"name":"Almazov National Medical Research Centre, St. Petersburg 197341, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Galina","family":"Boyko","sequence":"additional","affiliation":[{"name":"Almazov National Medical Research Centre, St. Petersburg 197341, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9023-6986","authenticated-orcid":false,"given":"Anna","family":"Starshinova","sequence":"additional","affiliation":[{"name":"Almazov National Medical Research Centre, St. Petersburg 197341, Russia"},{"name":"Department of Mathematics and Computer Science, St-Petersburg State University, St. Petersburg 199034, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1878-4467","authenticated-orcid":false,"given":"Dmitry","family":"Kudlay","sequence":"additional","affiliation":[{"name":"Department of Pharmacology, Institute of Pharmacy, I.M. Sechenov First Moscow State Medical University, Moscow 119991, Russia"},{"name":"Institute of Immunology FMBA of Russia, Moscow 115522, Russia"},{"name":"Faculty of Bioengineering and Bioinformatics, Lomonosov Moscow State University, Moscow 119991, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taiana","family":"Makarova","sequence":"additional","affiliation":[{"name":"Almazov National Medical Research Centre, St. Petersburg 197341, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lubov","family":"Mitrofanova","sequence":"additional","affiliation":[{"name":"Almazov National Medical Research Centre, St. Petersburg 197341, Russia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1002\/(SICI)1097-0320(19990501)36:1<18::AID-CYTO3>3.0.CO;2-J","article-title":"Artificial neural network-aided image analysis system for cell counting","volume":"36","author":"Frydel","year":"1999","journal-title":"Cytometry"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Malon, C., Miller, M., Christopher, H.B., Cosatto, E., and Graf, H.P. (2008, January 28\u201331). Identifying histological elements with convolutional neural networks. Proceedings of the 5th International Conference on Soft Computing as Transdisciplinary Science and Technology (CSTST \u201808), Cergy-Pontoise, France.","DOI":"10.1145\/1456223.1456316"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Qin, L., Heng, Y., Deng, S., Gu, J., Mao, F., Xue, Y., Jiang, Z., Wang, J., Cheng, D., and Wu, K. (2023). Perineural invasion affects prognosis of patients undergoing colorectal cancer surgery: A propensity score matching analysis. BMC Cancer, 23.","DOI":"10.1186\/s12885-023-10936-w"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Haider, S.A., Sharif, R., and Sharif, F. (2025). Multi-Organ Denervation: The Past, Present and Future. J. Clin. Med., 14.","DOI":"10.3390\/jcm14082746"},{"key":"ref_6","first-page":"631","article-title":"Acute changes in histopathology and intravascular imaging after catheter-based renal denervation in a porcine model","volume":"90","author":"Sakaoka","year":"2017","journal-title":"Catheter. Cardiovasc. Interv. Off. J. Soc. Card. Angiogr. Interv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/s41536-020-0096-1","article-title":"Innervation: The missing link for biofabricated tissues and organs","volume":"5","author":"Das","year":"2020","journal-title":"NPJ Regen. Med."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Wang, L., Dong, J., Zhang, Y., Luo, P., Qi, J., Liu, X., and Xian, C.J. (2015). Three-dimensional Reconstruction of Peripheral Nerve Internal Fascicular Groups. Sci. Rep., 5.","DOI":"10.1038\/srep17168"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1055\/s-0033-1356496","article-title":"Pathology and pathobiology of pulmonary hypertension","volume":"34","author":"Guignabert","year":"2013","journal-title":"Semin. Respir. Crit. Care Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"S1789","DOI":"10.21037\/jtd.2019.08.54","article-title":"Evaluation and classification of pulmonary arterial hypertension","volume":"11","author":"Sahay","year":"2019","journal-title":"J. Thorac. Dis."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s00408-020-00375-w","article-title":"Guidelines for the Treatment of Pulmonary Arterial Hypertension","volume":"198","author":"Vazquez","year":"2020","journal-title":"Lung"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1801887","DOI":"10.1183\/13993003.01887-2018","article-title":"Pathology and pathobiology of pulmonary hypertension: State of the art and research perspectives","volume":"53","author":"Humbert","year":"2019","journal-title":"Eur. Respir. J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s11886-019-1235-4","article-title":"Pulmonary Arterial Hypertension: A Pharmacotherapeutic Update","volume":"21","author":"Coons","year":"2019","journal-title":"Curr. Cardiol. Rep."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1007\/s10741-016-9566-3","article-title":"Neurohormonal activation and pharmacological inhibition in pulmonary arterial hypertension and related right ventricular failure","volume":"21","author":"Ameri","year":"2016","journal-title":"Heart Fail. Rev."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1186\/s12931-017-0679-6","article-title":"Autonomic nervous system involvement in pulmonary arterial hypertension","volume":"18","author":"Vaillancourt","year":"2017","journal-title":"Respir. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"381","DOI":"10.5603\/CJ.a2020.0186","article-title":"The progress of pulmonary artery denervation","volume":"29","author":"Xie","year":"2022","journal-title":"Cardiol. J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s00395-018-0714-x","article-title":"Effect of pulmonary artery denervation in postcapillary pulmonary hypertension: Results of a randomized controlled translational study","volume":"114","author":"Pereda","year":"2019","journal-title":"Basic Res. Cardiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e002837","DOI":"10.1161\/CIRCINTERVENTIONS.115.002837","article-title":"Hemodynamic, functional, and clinical responses to pulmonary artery denervation in patients with pulmonary arterial hypertension of different causes: Phase II results from the Pulmonary Artery Denervation-1 study","volume":"8","author":"Chen","year":"2015","journal-title":"Circ. Cardiovasc. Interv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Goncharova, N.S., Moiseeva, O.M., Condori Leandro, H.I., Zlobina, I.S., Berezina, A.V., Malikov, K.N., Tashkhanov, D.M., Lebedev, D.S., and Mikhaylov, E.N. (2020). Electrical Stimulation-Guided Approach to Pulmonary Artery Catheter Ablation in Patients with Idiopathic Pulmonary Arterial Hypertension: A Pilot Feasibility Study with a 12-Month Follow-Up. BioMed Res. Int., 2020.","DOI":"10.1155\/2020\/8919515"},{"key":"ref_20","first-page":"362","article-title":"Discrimination of ventricular tachycardia and localization of its exit site using surface electrocardiography","volume":"16","author":"Lebedev","year":"2019","journal-title":"J. Geriatr. Cardiol. JGC"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2378","DOI":"10.1002\/ar.25068","article-title":"Laser renal denervation: A comprehensive evaluation of microstructural renal artery lesions","volume":"306","author":"Vakhrushev","year":"2023","journal-title":"Anat. Rec."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1007\/s11760-025-04125-4","article-title":"A multi-pretraining U-Net architecture for semantic segmentation","volume":"19","author":"Copurkaya","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Li, J., and Li, X. (2023). MIU-Net: MIX-Attention and Inception U-Net for Histopathology Image Nuclei Segmentation. Appl. Sci., 13.","DOI":"10.3390\/app13084842"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"833","DOI":"10.17816\/DD629866","article-title":"Comparative analysis of modifications of U-Net neural network architectures in the problem of medical image segmentation","volume":"5","author":"Dostovalova","year":"2024","journal-title":"Digit. Diagn."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Imran, M., Islam Tiwana, M., Mohsan, M.M., Alghamdi, N.S., and Akram, M.U. (2024). Transformer-based framework for multi-class segmentation of skin cancer from histopathology images. Front. Med., 11.","DOI":"10.3389\/fmed.2024.1380405"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"103143","DOI":"10.1016\/j.media.2024.103143","article-title":"CellViT: Vision Transformers for precise cell segmentation and classification","volume":"94","author":"Rempe","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, X., Pang, S., Zhang, R., Zhu, J., Fu, X., Tian, Y., and Gao, J. (2023). ATTransUNet: An enhanced hybrid transformer architecture for ultrasound and histopathology image segmentation. Comput. Biol. Med., 152.","DOI":"10.1016\/j.compbiomed.2022.106365"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Wang, S., Zhang, Y., Ren, Y., Zhai, X., Wu, W., and Pang, S. (2023, January 5\u20138). ConTNet: Cross attention convolution and transformer for aneurysm image segmentation. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Istanbul, Turkiye.","DOI":"10.1109\/BIBM58861.2023.10386012"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Y\u0131ld\u0131z, S., Memi\u015f, A., and Varl\u0131, S. (2024, January 15\u201318). Segmentation of Cell Nuclei in Histology Images with Vision Transformer Based U-Net Models. Proceedings of the 32nd Signal Processing and Communications Applications Conference (SIU), Mersin, Turkiye.","DOI":"10.1109\/SIU61531.2024.10601151"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Del Bue, A., Canton, C., Pont-Tuset, J., and Tommasi, T. (2025). Going Beyond U-Net: Assessing Vision Transformers for Semantic Segmentation in Microscopy Image Analysis. Computer Vision\u2014ECCV 2024 Workshops, ECCV 2024, Proceedings of the European Conference on Computer Vision, Milan, Italy, 29 September\u20134 October 2024, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-031-91581-9"},{"key":"ref_31","first-page":"A2697","article-title":"Categorization of occult tumour cells in lymph nodes in patients with colon cancer not reliable enough","volume":"155","author":"Welling","year":"2011","journal-title":"Ned. Tijdschr. Voor Geneeskd."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1155\/2012\/385271","article-title":"Mitotic figure recognition: Agreement among pathologists and computerized detector","volume":"35","author":"Malon","year":"2012","journal-title":"Anal. Cell. Pathol."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Rasool, A., Fraz, M.M., and Javed, S. (2021, January 20\u201321). Multiscale Unified Network for Simultaneous Segmentation of Nerves and Micro-vessels in Histology Images. Proceedings of the International Conference on Digital Futures and Transformative Technologies (ICoDT2), Islamabad, Pakistan.","DOI":"10.1109\/ICoDT252288.2021.9441509"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tovbis, D., Agur, A., Mogk, J.P.M., and Zariffa, J. (2020). Automatic three-dimensional reconstruction of fascicles in peripheral nerves from histological images. PLoS ONE, 15.","DOI":"10.1101\/2020.01.22.913251"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ono, D., Kawai, H., Kuwahara, H., and Yokota, T. (2024). Automated whole slide morphometry of sural nerve biopsy using machine learning. Neuropathol. Appl. Neurobiol., 50.","DOI":"10.1111\/nan.12967"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"9915","DOI":"10.1007\/s00521-019-04516-y","article-title":"FABnet: Feature attention-based network for simultaneous segmentation of microvessels and nerves in routine histology images of oral cancer","volume":"32","author":"Fraz","year":"2020","journal-title":"Neural Comput. Appl."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2408\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:47:00Z","timestamp":1760035620000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/18\/2408"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":36,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["diagnostics15182408"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15182408","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}