{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T17:00:07Z","timestamp":1793379607226,"version":"4.5.0"},"posted":{"date-parts":[[2026,1,27]]},"group-title":"Immunology","reference-count":42,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:00:00Z","timestamp":1769472000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,1,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Tuberculosis (TB), caused by\n                  <jats:italic>Mycobacterium tuberculosis<\/jats:italic>\n                  (\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  ), remains a major global health challenge, with approximately 10.8 million new cases and 1.25 million deaths reported in 2023. Human responses to\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  are heterogeneous with clinical outcomes including bacterial clearance, asymptomatic latent\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  infection, and severe fatal pulmonary TB. Here, we aim to address knowledge gaps in the organization of\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  granulomas by identifying cell-based spatial features indicating asymptomatic lung infection. To address this gap, which cannot be directly studied in humans, we used lung sections from\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  infected Diversity Outbred mice with acute pulmonary TB, asymptomatic\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  infection, or chronic pulmonary TB that were stained for T cells, B cells, macrophages, and bronchiolar epithelial cells by multiplexed immunofluorescence. We first developed a new, accurate model to automatically segment lung granulomas, detect\/quantify the cell types within granulomas, and extract the location of immune cells in granulomas for each disease state. Analysis of model-derived results show that lung granulomas from asymptomatic mice have a characteristic spatial profile consisting of higher CD4+ and CD8a+ T cell densities, closer B cell proximity to bronchiolar epithelium, and increased T cell-macrophage proximity in asymptomatic\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  infection. Next, we propose a second novel approach to utilize a large language model (LLM) to independently decode complex cellular patterns within granulomas, and distinguished key immunological signatures: balanced immune expression in asymptomatic\n                  <jats:italic>M<\/jats:italic>\n                  .\n                  <jats:italic>tb<\/jats:italic>\n                  mice, dysfunctional responses with low cellularity in acute TB, and highest immune cells in chronic TB. Overall, the results from this study show that lung granulomas in asymptomatic infection are characterized by increased T cell density, increased numbers of peribronchiolar B cells, and T cells closer to macrophages as compared to acute and chronic TB. These methods and results help establish an automated pipeline to extract and analyze data from multiplexed fluorescence images and provide a foundation to better understand how granuloma architecture varies by disease state.\n                <\/jats:p>","DOI":"10.64898\/2026.01.26.701667","type":"posted-content","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T03:40:12Z","timestamp":1769571612000},"source":"Crossref","is-referenced-by-count":3,"title":["Deep Learning-Based Spatial Immunoprofiling of Multiplex Immunofluorescence Images Distinguishes Tuberculosis Disease States in Diversity Outbred Mice"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7262-3034","authenticated-orcid":false,"given":"Usama","family":"Sajjad","sequence":"first","affiliation":[{"name":"Department of Pathology, The Ohio State University Wexner Medical Center, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3873-9188","authenticated-orcid":false,"given":"Nicholas A.","family":"Crossland","sequence":"additional","affiliation":[{"name":"National Emerging Infectious Diseases Laboratories (NEIDL), Boston University, Boston, MA, USA"},{"name":"Department of Pathology and Laboratory Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"},{"name":"Department of Virology, Immunology, & Microbiology, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Metin N.","family":"Gurcan","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence Research, Wake Forest University School of Medicine, Winston-Salem, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6782-4424","authenticated-orcid":false,"given":"Gillian","family":"Beamer","sequence":"additional","affiliation":[{"name":"Texas Biomedical Research Institute, San Antonio, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Khalid","family":"Khan Niazi","sequence":"additional","affiliation":[{"name":"Department of Pathology, The Ohio State University Wexner Medical Center, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026020504294336000_2026.01.26.701667v1.1","unstructured":"Organization WH. Global report on infection prevention and control 2024: World Health Organization; 2024."},{"key":"2026020504294336000_2026.01.26.701667v1.2","doi-asserted-by":"crossref","unstructured":"Tavolara TE , Niazi MKK , Ginese M , Piedra-Mora C , Gatti DM , Beamer G , et al. Automatic discovery of clinically interpretable imaging biomarkers for Mycobacterium tuberculosis supersusceptibility using deep learning. EBioMedicine. 2020;62.","DOI":"10.1016\/j.ebiom.2020.103094"},{"key":"2026020504294336000_2026.01.26.701667v1.3","doi-asserted-by":"publisher","DOI":"10.1128\/iai.00263-23"},{"key":"2026020504294336000_2026.01.26.701667v1.4","doi-asserted-by":"publisher","DOI":"10.1093\/infdis\/jir451"},{"key":"2026020504294336000_2026.01.26.701667v1.5","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01245-2015"},{"issue":"1","key":"2026020504294336000_2026.01.26.701667v1.6","first-page":"139127","article-title":"The tuberculous granuloma: an unsuccessful host defence mechanism providing a safety shelter for the bacteria?","volume":"2012","year":"2012","journal-title":"Journal of Immunology Research"},{"key":"2026020504294336000_2026.01.26.701667v1.7","doi-asserted-by":"crossref","first-page":"804838","DOI":"10.3389\/fneur.2022.804838","article-title":"Tuberculous granuloma: emerging insights from proteomics and metabolomics","volume":"13","year":"2022","journal-title":"Frontiers in Neurology"},{"key":"2026020504294336000_2026.01.26.701667v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/ng2087"},{"key":"2026020504294336000_2026.01.26.701667v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/ng.847"},{"key":"2026020504294336000_2026.01.26.701667v1.10","doi-asserted-by":"publisher","DOI":"10.1128\/msphere.00097-20"},{"key":"2026020504294336000_2026.01.26.701667v1.11","doi-asserted-by":"publisher","DOI":"10.1007\/s00335-012-9414-2"},{"key":"2026020504294336000_2026.01.26.701667v1.12","unstructured":"Akbar AR , Sajjad U , Su Z , Li W , Xing F , Ruiz J , et al. CellEcoNet: Decoding the Cellular Language of Pathology with Deep Learning for Invasive Lung Adenocarcinoma Recurrence Prediction. arXiv preprint arXiv:250816742. 2025."},{"key":"2026020504294336000_2026.01.26.701667v1.13","unstructured":"Sajjad U , Akbar AR , Su Z , Knight D , Frankel WL , Gurcan MN , et al. Morphology-Aware Prognostic model for Five-Year Survival Prediction in Colorectal Cancer from H&E Whole Slide Images. arXiv preprint arXiv:251014800. 2025."},{"key":"2026020504294336000_2026.01.26.701667v1.14","doi-asserted-by":"crossref","unstructured":"Tavolara TE , Niazi M , Gower AC , Ginese M , Beamer G , Gurcan MN . Deep learning predicts gene expression as an intermediate data modality to identify susceptibility patterns in Mycobacterium tuberculosis infected Diversity Outbred mice. EBioMedicine. 2021;67.","DOI":"10.1016\/j.ebiom.2021.103388"},{"key":"2026020504294336000_2026.01.26.701667v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103143"},{"key":"2026020504294336000_2026.01.26.701667v1.16","doi-asserted-by":"crossref","unstructured":"Sajjad U , Niazi KK , Beamer G , Gurcan MN , editors. Clinically interpretable imaging biomarker discovery in BCG-vaccinated mycobacterium tuberculosis-infected diversity outbred mice using deep learning. Medical Imaging 2025: Digital and Computational Pathology; 2025: SPIE.","DOI":"10.1117\/12.3047288"},{"key":"2026020504294336000_2026.01.26.701667v1.17","unstructured":"Su Z , Akbar AR , Sajjad U , Parwani AV , Niazi MKK . Streamline pathology foundation model by cross-magnification distillation. arXiv preprint arXiv:250923097. 2025."},{"key":"2026020504294336000_2026.01.26.701667v1.18","doi-asserted-by":"crossref","unstructured":"Tavolara TE , Niazi MKK , Beamer G , Gurcan MN , editors. Identifying lung imaging biomarkers of BCG vaccination after infection with Mycobacterium tuberculosis. Medical Imaging 2021: Digital Pathology; 2021: SPIE.","DOI":"10.1117\/12.2581945"},{"key":"2026020504294336000_2026.01.26.701667v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2020.103094"},{"key":"2026020504294336000_2026.01.26.701667v1.20","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aay0233"},{"issue":"9","key":"2026020504294336000_2026.01.26.701667v1.21","first-page":"1141","article-title":"Lung necrosis and neutrophils reflect common pathways of susceptibility to Mycobacterium tuberculosis in genetically diverse, immune-competent mice","volume":"8","year":"2015","journal-title":"Disease models & mechanisms"},{"issue":"12","key":"2026020504294336000_2026.01.26.701667v1.22","doi-asserted-by":"crossref","first-page":"661","DOI":"10.3390\/microorganisms7120661","article-title":"Automatic detection of granuloma necrosis in pulmonary tuberculosis using a two-phase algorithm: 2D-TB","volume":"7","year":"2019","journal-title":"Microorganisms"},{"issue":"6","key":"2026020504294336000_2026.01.26.701667v1.23","doi-asserted-by":"crossref","first-page":"e1011915","DOI":"10.1371\/journal.ppat.1011915","article-title":"Systems genetics uncover new loci containing functional gene candidates in Mycobacterium tuberculosis-infected Diversity Outbred mice","volume":"20","year":"2024","journal-title":"PLoS Pathogens"},{"key":"2026020504294336000_2026.01.26.701667v1.24","doi-asserted-by":"publisher","DOI":"10.1177\/0300985811429313"},{"key":"2026020504294336000_2026.01.26.701667v1.25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.ppat.1009773"},{"key":"2026020504294336000_2026.01.26.701667v1.26","unstructured":"Zhou Z , Rahman Siddiquee MM , Tajbakhsh N , Liang J , editors. Unet++: A nested u-net architecture for medical image segmentation. Deep learning in medical image analysis and multimodal learning for clinical decision support: 4th international workshop, DLMIA 2018, and 8th international workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, proceedings 4; 2018: Springer."},{"key":"2026020504294336000_2026.01.26.701667v1.27","doi-asserted-by":"crossref","unstructured":"Dundar MM , Badve S , Raykar VC , Jain RK , Sertel O , Gurcan MN , editors. A multiple instance learning approach toward optimal classification of pathology slides. 2010 20th International Conference on Pattern Recognition; 2010: IEEE.","DOI":"10.1109\/ICPR.2010.669"},{"key":"2026020504294336000_2026.01.26.701667v1.28","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2011.2110648"},{"issue":"13","key":"2026020504294336000_2026.01.26.701667v1.29","doi-asserted-by":"crossref","first-page":"3428","DOI":"10.3390\/cancers15133428","article-title":"NRK-ABMIL: Subtle Metastatic Deposits Detection for Predicting Lymph Node Metastasis in Breast Cancer Whole-Slide Images","volume":"15","year":"2023","journal-title":"Cancers"},{"key":"2026020504294336000_2026.01.26.701667v1.30","unstructured":"Ilse M , Tomczak J , Welling M , editors. Attention-based deep multiple instance learning. International conference on machine learning; 2018: PMLR."},{"key":"2026020504294336000_2026.01.26.701667v1.31","unstructured":"Shen M , Li Y , Chen L , Yang Q. From mind to machine: The rise of manus ai as a fully autonomous digital agent. arXiv preprint arXiv:250502024. 2025."},{"issue":"1","key":"2026020504294336000_2026.01.26.701667v1.32","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1038\/s41698-022-00285-5","article-title":"Cell graph neural networks enable the precise prediction of patient survival in gastric cancer","volume":"6","year":"2022","journal-title":"NPJ precision oncology"},{"key":"2026020504294336000_2026.01.26.701667v1.33","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07618-3"},{"key":"2026020504294336000_2026.01.26.701667v1.34","doi-asserted-by":"crossref","unstructured":"Afzaal U , Su Z , Sajjad U , Stack T , Lu H , Niu S , et al. HistoChat: Instruction-tuning multimodal vision language assistant for colorectal histopathology on limited data. Patterns. 2025.","DOI":"10.1016\/j.patter.2025.101284"},{"key":"2026020504294336000_2026.01.26.701667v1.35","doi-asserted-by":"crossref","unstructured":"Afzaal U , Su Z , Sajjad U , Stack T , Rezapour M , Lu H , et al. , editors. Instruction tuning for colorectal histopathology: a multimodal vision-language assistant on human-evaluated data. Medical Imaging 2025: Digital and Computational Pathology; 2025: SPIE.","DOI":"10.1117\/12.3047352"},{"key":"2026020504294336000_2026.01.26.701667v1.36","doi-asserted-by":"crossref","unstructured":"Amirizaniani M , Martin E , Sivachenko M , Mashhadi A , Shah C , editors. Can llms reason like humans? assessing theory of mind reasoning in llms for open-ended questions. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management; 2024.","DOI":"10.1145\/3627673.3679832"},{"key":"2026020504294336000_2026.01.26.701667v1.37","doi-asserted-by":"crossref","unstructured":"Li D , Cao S , Griggs T , Liu S , Mo X , Tang E , et al. LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! arXiv preprint arXiv:250207374. 2025.","DOI":"10.18653\/v1\/2025.findings-emnlp.866"},{"issue":"2","key":"2026020504294336000_2026.01.26.701667v1.38","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1002\/path.1906","article-title":"New insights into the function of granulomas in human tuberculosis","volume":"208","year":"2006","journal-title":"The Journal of Pathology: A Journal of the Pathological Society of Great Britain and Ireland"},{"key":"2026020504294336000_2026.01.26.701667v1.39","doi-asserted-by":"publisher","DOI":"10.1038\/nm.4073"},{"issue":"6","key":"2026020504294336000_2026.01.26.701667v1.40","doi-asserted-by":"crossref","first-page":"e20221392","DOI":"10.1084\/jem.20221392","article-title":"Spatial mapping reveals granuloma diversity and histopathological superstructure in human tuberculosis","volume":"220","year":"2023","journal-title":"Journal of Experimental Medicine"},{"issue":"3","key":"2026020504294336000_2026.01.26.701667v1.41","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.jrid.2018.08.001","article-title":"Spatial and temporal evolution of lung granulomas in a cynomolgus macaque model of Mycobacterium tuberculosis infection","volume":"5","year":"2018","journal-title":"Radiology of Infectious Diseases"},{"key":"2026020504294336000_2026.01.26.701667v1.42","doi-asserted-by":"publisher","DOI":"10.1128\/IAI.00592-09"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.01.26.701667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T12:29:54Z","timestamp":1770294594000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.01.26.701667"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,27]]},"references-count":42,"URL":"https:\/\/doi.org\/10.64898\/2026.01.26.701667","relation":{},"subject":[],"published":{"date-parts":[[2026,1,27]]},"subtype":"preprint"}}