{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:02:08Z","timestamp":1785427328538,"version":"3.56.0"},"posted":{"date-parts":[[2026,6,23]]},"group-title":"Neuroscience","reference-count":30,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Neurological Disorders and Stroke (NINDS) \/ National Institutes of Health","award":["R01NS123034"],"award-info":[{"award-number":["R01NS123034"]}]},{"name":"National Cancer Institute (NCI) \/ National Institutes of Health","award":["R01CA278819"],"award-info":[{"award-number":["R01CA278819"]}]},{"DOI":"10.13039\/100000005","name":"United States Department of Defense","doi-asserted-by":"crossref","award":["W81XWH20-1-0838"],"award-info":[{"award-number":["W81XWH20-1-0838"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000005","name":"United States Department of Defense","doi-asserted-by":"crossref","award":["W81XWH-20-1-0901"],"award-info":[{"award-number":["W81XWH-20-1-0901"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000005","name":"United States Department of Defense","doi-asserted-by":"crossref","award":["HT9425-23-1-1039"],"award-info":[{"award-number":["HT9425-23-1-1039"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"crossref"}]},{"award":["RD-000547"],"award-info":[{"award-number":["RD-000547"]}],"id":[{"id":"https:\/\/ror.org\/05rsv9s98","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Traumatic brain injury produces widespread axonal damage can be assessed histologically using amyloid precursor protein (APP) immunohistochemistry, which labels injured axonal profiles at cellular resolution [1, 2]. However, quantification of APP pathology remains a major bottleneck: annotation is manual, time-consuming, spatially localized, and variable across raters, limiting scalability and reproducibility. This limitation is particularly important in studies that use histology as a reference for neuroimaging or other tissue-level measurements, where cellular APP pathology must be quantified in a spatial form that can be aligned with imaging abnormalities.<\/jats:p>\n                <jats:p>Here, we introduce PIGMENT, an annotation-efficient deep-learning framework for automated segmentation and quantification of APP-positive pathology in porcine white matter histology. PIGMENT uses a compact SegFormer-B0 architecture trained on 525 expert-annotated 512 \u00d7 512-pixel tiles from four APP-stained sections across three pigs. Because APP-positive profiles are sparse, fragmented, stain-variable, and morphologically diverse, PIGMENT combines limited expert labels with APP-specific augmentation designed to model variation in APP-positive intensity, size, continuity, fragmentation, and local tissue context.<\/jats:p>\n                <jats:p>We evaluated PIGMENT using an instance-level detection rate that measures whether discrete APP-positive components are localized. Across held-out APP-stained data, PIGMENT achieved a mean instance-level detection rate of 0.86. Across the configurations tested, the highest mean detection rate was achieved by a training set that included sections from different animals, suggesting that annotation diversity may be an important factor under limited-label conditions.<\/jats:p>\n                <jats:p>By extending limited high-confidence expert annotations into whole-section APP burden maps, PIGMENT provides a scalable framework for characterizing the extent and spatial distribution of traumatic axonal injury. These maps may support future studies that align histological injury burden with imaging-derived measures.<\/jats:p>","DOI":"10.64898\/2026.06.18.733245","type":"posted-content","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T03:10:16Z","timestamp":1782270616000},"source":"Crossref","is-referenced-by-count":0,"title":["PIGMENT: A deep learning framework for Porcine Immunohistochemistry seGMENTation"],"prefix":"10.64898","author":[{"given":"Pushkar","family":"Ambastha","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Guwahati, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1905-547X","authenticated-orcid":false,"given":"Javid","family":"Dadashkarimi","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8206-7503","authenticated-orcid":false,"given":"Sai Krishna C.","family":"Annavazala","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Drew","family":"Parker","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramon","family":"Diaz-Arrastia","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4204-6459","authenticated-orcid":false,"given":"Hailong","family":"Song","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rebecca P","family":"Donahue","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Douglas H.","family":"Smith","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Pierre","family":"Doll\u00e9","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victoria E.","family":"Johnson","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John A.","family":"Wolf","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ragini","family":"Verma","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026070300550565000_2026.06.18.733245v2.1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00389495"},{"key":"2026070300550565000_2026.06.18.733245v2.2","doi-asserted-by":"crossref","first-page":"S171","DOI":"10.1016\/j.legalmed.2009.01.076","article-title":"Two patterns of \u03b2-amyloid precursor protein (APP) immunoreactivity in cases of blunt head injury","volume":"11","year":"2009","journal-title":"Legal Medicine"},{"key":"2026070300550565000_2026.06.18.733245v2.3","first-page":"91712","volume":"344","year":"1994","journal-title":"Staining of amyloid precursor protein to study axonal damage in mild head injury"},{"key":"2026070300550565000_2026.06.18.733245v2.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.expneurol.2012.01.013"},{"issue":"1","key":"2026070300550565000_2026.06.18.733245v2.5","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1007\/s00401-024-02735-9","article-title":"Sex differences in the extent of acute axonal pathologies after experimental concussion","volume":"147","year":"2024","journal-title":"Acta neuropathologica"},{"key":"2026070300550565000_2026.06.18.733245v2.6","doi-asserted-by":"publisher","DOI":"10.1111\/bpa.12953"},{"key":"2026070300550565000_2026.06.18.733245v2.7","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-022-02498-1"},{"key":"2026070300550565000_2026.06.18.733245v2.8","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A3395"},{"key":"2026070300550565000_2026.06.18.733245v2.9","doi-asserted-by":"crossref","first-page":"799576","DOI":"10.3389\/fnins.2021.799576","article-title":"Potential pitfalls of using fractional anisotropy, axial diffusivity, and radial diffusivity as biomarkers of cerebral white matter microstructure","volume":"15","year":"2022","journal-title":"Frontiers in neuroscience"},{"key":"2026070300550565000_2026.06.18.733245v2.10","doi-asserted-by":"publisher","DOI":"10.1111\/bpa.12677"},{"key":"2026070300550565000_2026.06.18.733245v2.11","doi-asserted-by":"publisher","DOI":"10.3171\/2017.10.jns17352"},{"key":"2026070300550565000_2026.06.18.733245v2.12","doi-asserted-by":"publisher","DOI":"10.1089\/neu.2025.0039"},{"issue":"11","key":"2026070300550565000_2026.06.18.733245v2.13","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.3390\/brainsci13111607","article-title":"Identifying the phenotypes of diffuse axonal injury following traumatic brain injury","volume":"13","year":"2023","journal-title":"Brain sciences"},{"key":"2026070300550565000_2026.06.18.733245v2.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01343-4"},{"key":"2026070300550565000_2026.06.18.733245v2.15","doi-asserted-by":"crossref","unstructured":"Albuquerque, C. , R. Henriques , and M. Castelli , Deep learning-based object detection algorithms in medical imaging: Systematic review. Heliyon, 2025. 11(1).","DOI":"10.1016\/j.heliyon.2024.e41137"},{"key":"2026070300550565000_2026.06.18.733245v2.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102789"},{"issue":"2","key":"2026070300550565000_2026.06.18.733245v2.17","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1038\/s41592-023-02150-0","article-title":"Understanding metric-related pitfalls in image analysis validation","volume":"21","year":"2024","journal-title":"Nature methods"},{"issue":"1","key":"2026070300550565000_2026.06.18.733245v2.18","doi-asserted-by":"crossref","first-page":"5548","DOI":"10.1038\/s41598-024-82639-6","article-title":"Cellpose as a reliable method for single-cell segmentation of autofluorescence microscopy images","volume":"15","year":"2025","journal-title":"Scientific Reports"},{"key":"2026070300550565000_2026.06.18.733245v2.19","unstructured":"Ye, H. , et al., A novel weakly supervised immunohistochemical cell segmentation method via counting labels. Pattern Recognition, 2025: p. 112684."},{"key":"2026070300550565000_2026.06.18.733245v2.20","doi-asserted-by":"crossref","unstructured":"Cullen, D.K. , et al., A porcine model of traumatic brain injury via head rotational acceleration, in Injury models of the central nervous system: methods and protocols. 2016, Springer. p. 289\u2013324.","DOI":"10.1007\/978-1-4939-3816-2_17"},{"key":"2026070300550565000_2026.06.18.733245v2.21","unstructured":"Biosystems, L. , Aperio ImageScope. 2025, Leica Biosystems: Deer Park, IL, USA."},{"key":"2026070300550565000_2026.06.18.733245v2.22","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"2026070300550565000_2026.06.18.733245v2.23","unstructured":"Tarvainen, A. and H. Valpola , Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 2017. 30."},{"key":"2026070300550565000_2026.06.18.733245v2.24","unstructured":"!!! INVALID CITATION !!!."},{"issue":"3","key":"2026070300550565000_2026.06.18.733245v2.25","doi-asserted-by":"crossref","first-page":"e0229839","DOI":"10.1371\/journal.pone.0229839","article-title":"Introducing Hann windows for reducing edge-effects in patch-based image segmentation","volume":"15","year":"2020","journal-title":"PloS one"},{"key":"2026070300550565000_2026.06.18.733245v2.26","doi-asserted-by":"crossref","unstructured":"Butoi, V.I. , et al. Universeg: Universal medical image segmentation. in Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023.","DOI":"10.1109\/ICCV51070.2023.01960"},{"key":"2026070300550565000_2026.06.18.733245v2.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02580-4"},{"issue":"1","key":"2026070300550565000_2026.06.18.733245v2.28","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/1472-6947-12-8","article-title":"Predicting sample size required for classification performance","volume":"12","year":"2012","journal-title":"BMC medical informatics and decision making"},{"key":"2026070300550565000_2026.06.18.733245v2.29","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24750"},{"issue":"1","key":"2026070300550565000_2026.06.18.733245v2.30","doi-asserted-by":"crossref","first-page":"70","DOI":"10.3390\/brainsci15010070","article-title":"Diffusion Tensor Imaging as Neurologic Predictor in Patients Affected by Traumatic Brain Injury: Scoping Review","volume":"15","year":"2025","journal-title":"Brain Sciences"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.18.733245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:55:39Z","timestamp":1783065339000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.06.18.733245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.64898\/2026.06.18.733245","relation":{},"subject":[],"published":{"date-parts":[[2026,6,23]]},"subtype":"preprint"}}