Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2024 Oct 15:rs.3.rs-4889334.
doi: 10.21203/rs.3.rs-4889334/v1.

Neural network analysis as a novel skin outcome in a trial of belumosudil in patients with systemic sclerosis

Ilayda Gunes  1 , Elana Bernstein  2 , Shawn E Cowper  3 , Gauri Panse  3 , Niki Pradhan  2 , Lucy Duran Camacho  1 , Nicolas Page  1 , Elizabeth Bundschuh  1 , Alyssa Williams  1 , Mary Carns  4 , Kathleen Aren  4 , Sarah Fantus  4 , Elizabeth R Volkmann  5 , Heather Bukiri  5 , Chase Correia  4 , Rui Wang  6 , Vijaya Kolachalama  7 , F Perry Wilson  8 , Seamus Mawe  9 , J Matthew Mahoney  9 , Monique Hinchcliff  1
Affiliations

Neural network analysis as a novel skin outcome in a trial of belumosudil in patients with systemic sclerosis

Ilayda Gunes et al. Res Sq. .

Update in

Abstract

Background: The modified Rodnan skin score (mRSS), used to measure dermal thickness in patients with systemic sclerosis (SSc), is agnostic to inflammation and vasculopathy. Previously, we demonstrated the potential of neural network-based digital pathology applied to stained skin biopsies from SSc patients as a quantitative outcome. We leveraged deep learning and histologic analyses of clinical trial biopsies to decipher SSc skin features 'seen' by artificial intelligence (AI).

Methods: Adults with diffuse cutaneous SSc (disease duration ≤ 6 years) enrolled in an open-label trial evaluating belumosudil underwent serial mRSS assessment and dorsal arm biopsies at week 0, 24 and 52/end of trial. Two blinded dermatopathologists independently scored stained sections [Masson's trichrome, hematoxylin and eosin (H&E), CD3, CD34, CD8, α smooth muscle actin (αSMA)] for 16 published SSc dermal pathological parameters. We applied our previously published deep learning model to generate QIF signatures/biopsy and generated Fibrosis Scores. Associations between Fibrosis Score and mRSS (Spearman correlation); and between Fibrosis Score mRSS versus histologic parameters [odds ratios (OR)] were determined.

Results: Only ten patients were enrolled because the sponsor terminated the trial early. Median, interquartile range (IQR) for mRSS change (0-52 weeks) for the five participants with paired biopsies was - 2.5 (-11-7.5), and for the ten participants was - 2 (-9-7.5). The correlation between Fibrosis Score and mRSS was R = 0.3; p = 0.674. Per 1-unit mRSS change (0-52W), histologic parameters with the greatest associated changes were (OR, p-value): telangiectasia (2.01, 0.001), perivascular CD3+ (1.03, 0.015), and % of CD8 + among CD3+ (1.08, 0.031). Likewise, per 1-unit Fibrosis Score change, parameters with greatest changes were (OR, p-value): hyalinized collagen (1.1, < 0.001), subcutaneous (SC) fat loss (1.47, < 0.001), thickened intima (1.21, 0.005), and eccrine entrapment (1.14, 0.046).

Conclusions: Belumosudil was associated with a non-clinically meaningful improvement in mRSS. Fibrosis Score changes correlated with histologic feature changes (e.g., hyalinized collagen, SC fat loss) that were distinct from those associated with mRSS changes (e.g., telangiectasia, perivascular CD3+, and % of CD8 + among CD3+). These data suggest that AI applied to SSc biopsies may be useful for quantifying pathologic features of SSc beyond skin thickness.

Keywords: AlexNet; Deep Neural Network; artificial intelligence; belumosudil; dermal fibrosis; modified Rodnan skin score; outcome measure; outcomes; scleroderma; skin fibrosis; systemic sclerosis.

PubMed Disclaimer

Conflict of interest statement

Competing Interests MH has received consultancy fees from AbbVie and has received research grant support from Boehringer Ingelheim for an investigator-initiated research project. She is a Scientific Advisory Board Member for the Scleroderma Foundation. She has participated in clinical trials. EJB has received research grants from Kadmon, Boehringer Ingelheim and aTyr. EV has received consulting fees from Boehringer Ingelheim, GSK, Abbvie, BMS, and GLG, has received support from Boehringer Ingelheim, Horizon, Prometheus, Kadmon, and GSK, and serves on the advisory board for Cabaletta and Boehringer Ingelheim. FPW reports research support from AHRQ (R01HS027626), Amgen, and Whoop. FPW reports consulting for Hekaheart, Aura Care, and WndrHlth.

Figures

Figure 1
Figure 1. Systemic sclerosis dermatopathology parameters and scoring, rater agreement and parameter change.
A. Scoring for 16 SSc dermatopathology parameters. B. Histologic parameter Kappa values and parameter score change per week (*indicates p-value<0.05).
Figure 2
Figure 2. Deep Neural Network applied to trichrome-stained skin biopsy section.
A. Image patches of skin biopsy section stained with trichrome. B. Artificial intelligence (AlexNet Deep Neural Network) applied to each image patch (100 per biopsy). C.Quantitative Image Features generated for each image patch.
Figure 3
Figure 3. Modified Rodnan skin score trajectories.
A. Ten participants’ mRSS W0 to last follow-up. The median interquartile range (IQR) mRSS change 0–52W was −2.5 (−11—7.5). B.Five participants’, with matching biopsies, mRSS W0 to last follow-up. The median interquartile range (IQR) mRSS change 0–52W was −2 (−9—7.5).
Figure 4
Figure 4. Stained sections for participants with 0-, 24- and 52-week biopsies.
H&E and trichrome-stained biopsies for three participants during treatment with their mRSS and local arm scores.
Figure 5
Figure 5. Correlation between modified Rodnan skin score (mRSS) and DNN Fibrosis Score.
The Spearman correlation between mRSS and DNN Fibrosis Scores for five participants with baseline and follow-up biopsies.
See this image and copyright information in PMC

References

    1. Hughes M., et al., MRI Digital Artery Volume Index (DAVIX) as a surrogate outcome measure of digital ulcer disease in patients with systemic sclerosis: a prospective cohort study. Lancet Rheumatol, 2023. 5(10): p. e611–e621. - PubMed
    1. Medsger T.A. Jr. and Benedek T.G., History of skin thickness assessment and the Rodnan skin thickness scoring method in systemic sclerosis. J Scleroderma Relat Disord, 2019. 4(2): p. 83–88. - PMC - PubMed
    1. Khanna D., et al., Standardization of the modified Rodnan skin score for use in clinical trials of systemic sclerosis. J Scleroderma Relat Disord, 2017. 2(1): p. 11–18. - PMC - PubMed
    1. Mihai C., et al., Enrichment Strategy for Systemic Sclerosis Clinical Trials Targeting Skin Fibrosis: A Prospective, Multiethnic Cohort Study. ACR Open Rheumatol, 2020. 2(8): p. 496–502. - PMC - PubMed
    1. LeRoy E.C., et al., Scleroderma (systemic sclerosis): classification, subsets and pathogenesis. J Rheumatol, 1988. 15(2): p. 202–5. - PubMed

Publication types

LinkOut - more resources