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

Abstract

Background: The modified Rodnan skin score (mRSS), a measure of systemic sclerosis (SSc) skin thickness, is agnostic to inflammation and vasculopathy. Previously, we demonstrated the potential of neural network-based digital pathology applied to SSc skin biopsies as a quantitative outcome. Here, we leverage 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 ≤ 6 years were enrolled in an open-label trial of belumosudil [a Rho-associated coiled-coil containing protein kinase 2 (ROCK2) inhibitor]. Participants underwent serial mRSS and arm biopsies at week (W) 0, 24 and 52. Two blinded dermatopathologists scored stained sections (e.g., Masson's trichrome, hematoxylin and eosin, CD3, α-smooth muscle actin) for 16 published SSc dermal pathological parameters. We applied our deep learning model to generate QIF signatures/biopsy and obtain 'Fibrosis Scores'. Associations between Fibrosis Score and mRSS (Spearman correlation), and between Fibrosis Score and mRSS versus histologic parameters [odds ratios (OR)], were determined.

Results: Only ten patients were enrolled due to early study termination, and of those, five had available biopsies due to fixation issues. Median, interquartile range (IQR) for mRSS change (0-52 W) for the ten participants was -2 (-9-7.5) and for the five with biopsies was -2.5 (-11-7.5). The correlation between Fibrosis Score and mRSS was R = 0.3; p = 0.674. Per 1-unit mRSS change (0-52 W), histologic parameters with the greatest associated changes were (OR, 95% CI, p-value): telangiectasia (2.01, [(1.31-3.07], 0.001), perivascular CD3 + (0.99, [0.97-1.02], 0.015), and % of CD8 + among CD3 + (0.95, [0.89-1.01], 0.031). Likewise, per 1-unit Fibrosis Score change, parameters with greatest changes were (OR, p-value): hyalinized collagen (1.1, [1.04 - 1.16], < 0.001), subcutaneous (SC) fat loss (1.47, [1.19-1.81], < 0.001), thickened intima (1.21, [1.06-1.38], 0.005), and eccrine entrapment (1.14, [1-1.31], 0.046).

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

Keywords: AlexNet; Artificial intelligence; Belumosudil; Deep Neural Network; Dermal fibrosis; Modified Rodnan skin score; Outcome measure; Outcomes; Scleroderma; Skin fibrosis; Systemic sclerosis.

Fig. 1

Systemic sclerosis dermatopathology parameters and scoring, inter-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)

Fig. 2

Deep Neural Network applied to trichrome-stained skin biopsy sections. 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

Fig. 3

Modified Rodnan skin score trajectories. A Ten participants’ mRSS change from W0-52, median (interquartile range/IQR): −2.5 (−11—7.5). B Five participants’, with paired biopsies, mRSS change from W0-52, median (IQR): W0 to last follow-up: −2 (−9—7.5)

Fig. 4

Stained sections for three participants. H&E and trichrome-stained biopsies for three participants with 0-, 24- and 52-W biopsies showing associated mRSS and local arm scores

Fig. 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 W0-52