Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 38 min ago
Peer-reviewedCC BY 4.0PLOS One

Deep learning-based spatial immunoprofiling of multiplex immunofluorescence images distinguishes tuberculosis disease states in diversity outbred mice

  • Usama Sajjad1
  • Nicholas A. Crossland2
  • Metin N. Gurcan3
  • Gillian Beamer4
  • Muhammad Khalid Khan Niazi5
5 affiliations
  1. 1Department of Pathology, The Ohio State University Wexner Medical Center, Columbus, Ohio, United States of America
  2. 2National Emerging Infectious Diseases Laboratories (NEIDL), Boston University, Boston, Massachusetts, United States of America
  3. 3Department of Pathology and Laboratory Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, United States of America
  4. 4Department of Virology, Immunology, & Microbiology, Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, United States of America
  5. 5Center for Artificial Intelligence Research, Wake Forest University School of Medicine, Winston-Salem, North Carolina, United States of America
Open at sourcePDFDOICite

Abstract

Tuberculosis (TB), caused by Mycobacterium tuberculosis (M.tb), remains a major global health challenge, with approximately 10.8 million new cases and 1.25 million deaths reported in 2023. Human responses to M.tb are heterogeneous with clinical outcomes including bacterial clearance, asymptomatic latent M.tb infection, and severe fatal pulmonary TB. Here, we aim to address knowledge gaps in the organization of M.tb 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 M.tb-infected Diversity Outbred mice with acute pulmonary TB, asymptomatic M.tb 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 shows 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 M.tb infection. Next, we propose a second novel approach to utilize a large language model (LLM) to independently decode complex cellular patterns within granulomas, and distinguish key immunological signatures: balanced immune expression in asymptomatic M.tb mice, dysfunctional responses with low cellularity in acute TB, and highest immune-cell abundance 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.

Related

  1. High prevalence and diversity of mesophilic bacteria detected in pre-enrichment raw milk from Ecuador using two multiplex TaqMan qPCR assays
    Anthony Loor-Giler, Claire Muslin, Byron Puga-Torres +2
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textPlant biologyCrossref
  2. Development and evaluation of a multiplex PCR for simultaneous detection of Mycobacterium tuberculosis complex, Mycobacterium avium complex, and Burkholderia pseudomallei in clinical specimens
    Hasyanee Binmaeil, Thanakon Bunsong, Janjira Thaipadungpanit +7
    PLOS Neglected Tropical DiseasesPeer-reviewedCC BY 4.0Full textEnzymology & metabolismMicrobiologyPLOS
  3. Gene conversion is a key driver of diversity hotspots in Mycobacterium tuberculosis antigens and virulence-associated loci
    Maximillian G. Marin, Natalia Quinones-Olvera, Hu Jin +7
    Proceedings of the National Academy of Sciences of the United States of AmericaPeer-reviewedCC BY-NC-ND 4.0Full textMicrobiologyPMC
  4. A multi-electrode array and immunofluorescence workflow to characterize impacts of HHV-6 infection in induced pluripotent stems cells differentiated to mixed neuronal endpoints
    E. Bahramian, X. Yang, A. Bajpai +2
    bioRxivPreprintAll rights reservedFull textMicrobiologybioRxiv
  5. High-Dimensional Multi-omic Mapping of Post-Mortem Human Brain Using Iterative Indirect Immunofluorescence Imaging on Xenium-Processed Tissues
    B. Karaahmet, T. Lama, A. Wang +7
    bioRxivPreprintCC BYFull textNeurosciencebioRxiv

Cite

BibTeXRIS
BibTeX
@article{sajjad2026deep,
  title = {{Deep learning-based spatial immunoprofiling of multiplex immunofluorescence images distinguishes tuberculosis disease states in diversity outbred mice}},
  author = {Usama Sajjad and Nicholas A. Crossland and Metin N. Gurcan and Gillian Beamer and Muhammad Khalid Khan Niazi},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0358334},
  url = {https://doi.org/10.1371/journal.pone.0358334},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Deep learning-based spatial immunoprofiling of multiplex immunofluorescence images distinguishes tuberculosis disease states in diversity outbred mice
AU  - Usama Sajjad
AU  - Nicholas A. Crossland
AU  - Metin N. Gurcan
AU  - Gillian Beamer
AU  - Muhammad Khalid Khan Niazi
PY  - 2026
DA  - 2026/09/25
JO  - PLOS One
DO  - 10.1371/journal.pone.0358334
UR  - https://doi.org/10.1371/journal.pone.0358334
AB  - Tuberculosis (TB), caused by Mycobacterium tuberculosis (M.tb), remains a major global health challenge, with approximately 10.8 million new cases and 1.25 million deaths reported in 2023. Human responses to M.tb are heterogeneous with clinical outcomes including bacterial clearance, asymptomatic latent M.tb infection, and severe fatal pulmonary TB. Here, we aim to address knowledge gaps in the organization of M.tb 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 M.tb-infected Diversity Outbred mice with acute pulmonary TB, asymptomatic M.tb 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 shows 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 M.tb infection. Next, we propose a second novel approach to utilize a large language model (LLM) to independently decode complex cellular patterns within granulomas, and distinguish key immunological signatures: balanced immune expression in asymptomatic M.tb mice, dysfunctional responses with low cellularity in acute TB, and highest immune-cell abundance 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.
SN  - 1932-6203
ER  -