Automated multi-scale computational pathotyping (AMSCP) of inflamed synovial tissue

Richard D. Bell; Matthew Brendel; Maxwell A. Konnaris; Justin Xiang; Miguel Otero; Mark A. Fontana; Zilong Bai; Daria M. Krenitsky; Nida Meednu; Javier Rangel-Moreno; Dagmar Scheel-Toellner; Hayley Carr; Saba Nayar; Jack McMurray; Edward DiCarlo; Jennifer H. Anolik; Laura T. Donlin; Dana E. Orange; H. Mark Kenney; Edward M. Schwarz; Andrew Filer; Lionel B. Ivashkiv; Fei Wang

doi:10.1038/s41467-024-51012-6

Automated multi-scale computational pathotyping (AMSCP) of inflamed synovial tissue

Richard D. Bell^*, Matthew Brendel, Maxwell A. Konnaris, Justin Xiang, Miguel Otero, Mark A. Fontana, Zilong Bai, Daria M. Krenitsky, Nida Meednu, Javier Rangel-Moreno, Dagmar Scheel-Toellner, Hayley Carr, Saba Nayar, Jack McMurray, Edward DiCarlo, Jennifer H. Anolik, Laura T. Donlin, Dana E. Orange, H. Mark Kenney, Edward M. SchwarzAndrew Filer, Lionel B. Ivashkiv, Fei Wang

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

3 Downloads (Pure)

Abstract

Rheumatoid arthritis (RA) is a complex immune-mediated inflammatory disorder in which patients suffer from inflammatory-erosive arthritis. Recent advances on histopathology heterogeneity of RA synovial tissue revealed three distinct phenotypes based on cellular composition (pauci-immune, diffuse and lymphoid), suggesting that distinct etiologies warrant specific targeted therapy which motivates a need for cost effective phenotyping tools in preclinical and clinical settings. To this end, we developed an automated multi-scale computational pathotyping (AMSCP) pipeline for both human and mouse synovial tissue with two distinct components that can be leveraged together or independently: (1) segmentation of different tissue types to characterize tissue-level changes, and (2) cell type classification within each tissue compartment that assesses change across disease states. Here, we demonstrate the efficacy, efficiency, and robustness of the AMSCP pipeline as well as the ability to discover novel phenotypes. Taken together, we find AMSCP to be a valuable cost-effective method for both pre-clinical and clinical research.

Original language	English
Article number	7503
Journal	Nature Communications
Volume	15
DOIs	https://doi.org/10.1038/s41467-024-51012-6
Publication status	Published - 29 Aug 2024

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41467-024-51012-6Licence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

BellRD2024AutomatedFinal published version, 4.82 MBLicence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

Cite this

Bell, R. D., Brendel, M., Konnaris, M. A., Xiang, J., Otero, M., Fontana, M. A., Bai, Z., Krenitsky, D. M., Meednu, N., Rangel-Moreno, J., Scheel-Toellner, D., Carr, H., Nayar, S., McMurray, J., DiCarlo, E., Anolik, J. H., Donlin, L. T., Orange, D. E., Kenney, H. M., ... Wang, F. (2024). Automated multi-scale computational pathotyping (AMSCP) of inflamed synovial tissue. Nature Communications, 15, Article 7503. https://doi.org/10.1038/s41467-024-51012-6

@article{426922dbf8c14e4da5e3e9ec8bb8a4e9,

title = "Automated multi-scale computational pathotyping (AMSCP) of inflamed synovial tissue",

abstract = "Rheumatoid arthritis (RA) is a complex immune-mediated inflammatory disorder in which patients suffer from inflammatory-erosive arthritis. Recent advances on histopathology heterogeneity of RA synovial tissue revealed three distinct phenotypes based on cellular composition (pauci-immune, diffuse and lymphoid), suggesting that distinct etiologies warrant specific targeted therapy which motivates a need for cost effective phenotyping tools in preclinical and clinical settings. To this end, we developed an automated multi-scale computational pathotyping (AMSCP) pipeline for both human and mouse synovial tissue with two distinct components that can be leveraged together or independently: (1) segmentation of different tissue types to characterize tissue-level changes, and (2) cell type classification within each tissue compartment that assesses change across disease states. Here, we demonstrate the efficacy, efficiency, and robustness of the AMSCP pipeline as well as the ability to discover novel phenotypes. Taken together, we find AMSCP to be a valuable cost-effective method for both pre-clinical and clinical research.",

author = "Bell, {Richard D.} and Matthew Brendel and Konnaris, {Maxwell A.} and Justin Xiang and Miguel Otero and Fontana, {Mark A.} and Zilong Bai and Krenitsky, {Daria M.} and Nida Meednu and Javier Rangel-Moreno and Dagmar Scheel-Toellner and Hayley Carr and Saba Nayar and Jack McMurray and Edward DiCarlo and Anolik, {Jennifer H.} and Donlin, {Laura T.} and Orange, {Dana E.} and Kenney, {H. Mark} and Schwarz, {Edward M.} and Andrew Filer and Ivashkiv, {Lionel B.} and Fei Wang",

year = "2024",

month = aug,

day = "29",

doi = "10.1038/s41467-024-51012-6",

language = "English",

volume = "15",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Springer",

}

Bell, RD, Brendel, M, Konnaris, MA, Xiang, J, Otero, M, Fontana, MA, Bai, Z, Krenitsky, DM, Meednu, N, Rangel-Moreno, J, Scheel-Toellner, D, Carr, H, Nayar, S, McMurray, J, DiCarlo, E, Anolik, JH, Donlin, LT, Orange, DE, Kenney, HM, Schwarz, EM, Filer, A, Ivashkiv, LB & Wang, F 2024, 'Automated multi-scale computational pathotyping (AMSCP) of inflamed synovial tissue', Nature Communications, vol. 15, 7503. https://doi.org/10.1038/s41467-024-51012-6

TY - JOUR

T1 - Automated multi-scale computational pathotyping (AMSCP) of inflamed synovial tissue

AU - Bell, Richard D.

AU - Brendel, Matthew

AU - Konnaris, Maxwell A.

AU - Xiang, Justin

AU - Otero, Miguel

AU - Fontana, Mark A.

AU - Bai, Zilong

AU - Krenitsky, Daria M.

AU - Meednu, Nida

AU - Rangel-Moreno, Javier

AU - Scheel-Toellner, Dagmar

AU - Carr, Hayley

AU - Nayar, Saba

AU - McMurray, Jack

AU - DiCarlo, Edward

AU - Anolik, Jennifer H.

AU - Donlin, Laura T.

AU - Orange, Dana E.

AU - Kenney, H. Mark

AU - Schwarz, Edward M.

AU - Filer, Andrew

AU - Ivashkiv, Lionel B.

AU - Wang, Fei

PY - 2024/8/29

Y1 - 2024/8/29

N2 - Rheumatoid arthritis (RA) is a complex immune-mediated inflammatory disorder in which patients suffer from inflammatory-erosive arthritis. Recent advances on histopathology heterogeneity of RA synovial tissue revealed three distinct phenotypes based on cellular composition (pauci-immune, diffuse and lymphoid), suggesting that distinct etiologies warrant specific targeted therapy which motivates a need for cost effective phenotyping tools in preclinical and clinical settings. To this end, we developed an automated multi-scale computational pathotyping (AMSCP) pipeline for both human and mouse synovial tissue with two distinct components that can be leveraged together or independently: (1) segmentation of different tissue types to characterize tissue-level changes, and (2) cell type classification within each tissue compartment that assesses change across disease states. Here, we demonstrate the efficacy, efficiency, and robustness of the AMSCP pipeline as well as the ability to discover novel phenotypes. Taken together, we find AMSCP to be a valuable cost-effective method for both pre-clinical and clinical research.

AB - Rheumatoid arthritis (RA) is a complex immune-mediated inflammatory disorder in which patients suffer from inflammatory-erosive arthritis. Recent advances on histopathology heterogeneity of RA synovial tissue revealed three distinct phenotypes based on cellular composition (pauci-immune, diffuse and lymphoid), suggesting that distinct etiologies warrant specific targeted therapy which motivates a need for cost effective phenotyping tools in preclinical and clinical settings. To this end, we developed an automated multi-scale computational pathotyping (AMSCP) pipeline for both human and mouse synovial tissue with two distinct components that can be leveraged together or independently: (1) segmentation of different tissue types to characterize tissue-level changes, and (2) cell type classification within each tissue compartment that assesses change across disease states. Here, we demonstrate the efficacy, efficiency, and robustness of the AMSCP pipeline as well as the ability to discover novel phenotypes. Taken together, we find AMSCP to be a valuable cost-effective method for both pre-clinical and clinical research.

U2 - 10.1038/s41467-024-51012-6

DO - 10.1038/s41467-024-51012-6

M3 - Article

SN - 2041-1723

VL - 15

JO - Nature Communications

JF - Nature Communications

M1 - 7503

ER -