Search

Context.— Pathology studies using convolutional neural networks (CNNs) have focused on neoplasms, while studies in inflammatory pathology are rare. We previously demonstrated a CNN that differentiates reactive gastropathy, Helicobacter pylori gastritis (HPG), and normal gastric mucosa. Objective.— To determine whether a CNN can differentiate the following 2 gastric inflammatory patterns: autoimmune gastritis (AG) and HPG. Design.— Gold standard diagnoses were blindly established by 2 gastrointestinal (GI) pathologists. One hundred eighty-seven cases were scanned for analysis by HALO-AI. All levels and tissue fragments per slide were included for analysis. The cases were randomized, 112 (60%; 60 HPG, 52 AG) in the training set and 75 (40%; 40 HPG, 35 AG) in the test set. A HALO-AI correct area distribution (AD) cutoff of 50% or more was required to credit the CNN with the correct diagnosis. The test set was blindly reviewed by pathologists with different levels of GI pathology expertise as follows: 2 GI pathologists, 2 general surgical pathologists, and 2 residents. Each pathologist rendered their preferred diagnosis, HPG or AG. Results.— At the HALO-AI AD percentage cutoff of 50% or more, the CNN results were 100% concordant with the gold standard diagnoses. On average, autoimmune gastritis cases had 84.7% HALO-AI autoimmune gastritis AD and HP cases had 87.3% HALO-AI HP AD. The GI pathologists, general anatomic pathologists, and residents were on average, 100%, 86%, and 57% concordant with the gold standard diagnoses, respectively. Conclusions.— A CNN can distinguish between cases of HPG and autoimmune gastritis with accuracy equal to GI pathologists.

Increased T helper (Th)1/Th17 immune responses are a hallmark of Crohn’s disease (CD) immunopathogenesis. CD90+ (myo-)fibroblasts (MFs) are abundant cells in the normal (N) intestinal mucosa contributing to mucosal tolerance via suppression of Th1 cell activity through cell surface membrane-bound PD-L1 (mPD-L1). CD-MFs have a decreased level of mPD-L1. Consequently, mPD-L1-mediated suppression of Th1 cells by CD-MFs is decreased, yet the mechanism responsible for the reduction in mPDL-1 is unknown. Increased expression of matrix metalloproteinases (MMPs) has been reported in CD. Herein we observed that when compared to N- and ulcerative colitis (UC)-MFs, CD-MFs increase in LPS-inducible levels of MMP-7 and -9 with a significant increase in both basal and inducible MMP-10. A similar pattern of MMP expression was observed in the CD-inflamed mucosa. Treatment of N-MFs with a combination of recombinant human MMP-7, -9 and -10 significantly decreased mPD-L1. In contrast, inhibition of MMP activity with MMP inhibitors or anti-MMP-10 neutralizing antibodies restores mPD-L1 on CD-MFs. CD-MFs demonstrated reduced capacity to suppress Th1 and Th17 responses from activated CD4+ T cells. By contrast, supplementation of the CD-MF:T-cell co-cultures with MMP inhibitors or anti-MMP neutralizing antibodies restored the CD-MF-mediated suppression. Our data suggest that (i) increased MMP-10 expression by CD-MFs and concomitant cleavage of PD-L1 from the surface of CD-MFs are likely to be one of the factors contributing to the decrease of mPD-L1-mediated suppression of Th1/Th17 cells in CD; and (ii) MMPs are likely to have a significant role in the intestinal mucosal immune responses.