A Deep Learning Convolutional Neural Network Can Differentiate Between Helicobacter Pylori Gastritis and Autoimmune Gastritis With Results Comparable to Gastrointestinal Pathologists.

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.

Peripheral versus central mechanisms of the cannabinoid type 2 receptor agonist AM1710 in a mouse model of neuropathic pain.

The CB2 R agonist AM1710, examined in animal models of peripheral neuropathy, is effective in controlling aberrant light touch sensitivity, referred to as mechanical allodynia. However, nonspecific binding of AM1710 to CB1 R, either peripherally or centrally, could be partially responsible for the analgesic effects of AM1710. Thus, we sought to determine in mice whether spinal (intrathecal; i.t.) or peripheral AM1710 administration could lead to anti-allodynia by reducing the protein expression of spinal and dorsal root ganglia (DRG) proinflammatory cytokines and elevating the anti-inflammatory cytokine interleukin-10 (IL-10) in the absence of CB1 R. Macrophage cell cultures were examined to characterize AM1710-mediated suppression of the proinflammatory cytokine tumor necrosis factor-alpha (TNF-α). Either i.p. or i.t. AM1710 reversed CCI-induced mechanical allodynia to sham levels in CB1 R (-/-), (+/-), (+/+) mice. CCI-induced neuropathy decreased IL-10 immunoreactivity (IR) in the dorsal root ganglia (DRG) and the dorsal horn of the spinal cord, with i.t. AM1710 restoring basal IL-10 IR. CCI-induced elevations in proinflammatory cytokine IR were decreased within the spinal cord only after i.t. AM1710 in all mouse genotypes. Meanwhile, within DRG tissue from neuropathic mice, proinflammatory cytokines were decreased following either i.p. or i.t. AM1710. Analysis of cultured supernatants revealed AM1710 decreased TNF-alpha protein. We conclude that CB1 R is dispensable for either peripheral or central anti-allodynic actions of AM1710 in neuropathic mice. Cannabinoid CB2 R agonists produce heightened spinal IL-10 which may be clinically relevant to successfully treat neuropathic pain.

Intrathecal cannabilactone CB(2)R agonist, AM1710, controls pathological pain and restores basal cytokine levels.

Spinal glial and proinflammatory cytokine actions are strongly implicated in pathological pain. Spinal administration of the anti-inflammatory cytokine interleukin (IL)-10 abolishes pathological pain and suppresses proinflammatory IL-1ß and tumor necrosis factor alpha (TNF-α). Drugs that bind the cannabinoid type-2 receptor (CB(2)R) expressed on spinal glia reduce mechanical hypersensitivity. To better understand the CB(2)R-related anti-inflammatory profile of key anatomical nociceptive regions, we assessed mechanical hypersensitivity and protein profiles following intrathecal application of the cannabilactone CB(2)R agonist, AM1710, in 2 animal models; unilateral sciatic nerve chronic constriction injury (CCI), and spinal application of human immunodeficiency virus-1 glycoprotein 120 (gp120), a model of peri-spinal immune activation. In CCI animals, lumbar dorsal spinal cord and corresponding dorsal root ganglia (DRG) were evaluated by immunohistochemistry for expression of IL-10, IL-1ß, phosphorylated p38-mitogen-activated-kinase (p-p38MAPK), a pathway associated with proinflammatory cytokine production, glial cell markers, and degradative endocannabinoid enzymes, including monoacylglycerol lipase (MAGL). AM1710 reversed bilateral mechanical hypersensitivity. CCI revealed decreased IL-10 expression in dorsal spinal cord and DRG, while AM1710 resulted in increased IL-10, comparable to controls. Adjacent DRG and spinal sections revealed increased IL-1ß, p-p38MAPK, glial markers, and/or MAGL expression, while AM1710 suppressed all but spinal p-p38MAPK and microglial activation. In spinal gp120 animals, AM1710 prevented bilateral mechanical hypersensitivity. For comparison to immunohistochemistry, IL-1ß and TNF-α protein quantification from lumbar spinal and DRG homogenates was determined, and revealed increased DRG IL-1ß protein levels from gp120, that was robustly prevented by AM1710 pretreatment. Cannabilactone CB(2)R agonists are emerging as anti-inflammatory agents with pain therapeutic implications.