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.

Superparamagnetic nanoparticle-enhanced MRI of Alzheimer's disease plaques and activated microglia in 3X transgenic mouse brains: Contrast optimization.

PURPOSE: To optimize magnetic resonance imaging (MRI) of antibody-conjugated superparamagnetic nanoparticles for detecting amyloid-ß plaques and activated microglia in a 3X transgenic mouse model of Alzheimer's disease. MATERIALS AND METHODS: Ten 3X Tg mice were fed either chow or chow containing 100 ppm resveratrol. Four brains, selected from animals injected with either anti-amyloid targeted superparamagnetic iron oxide nanoparticles, or anti-Iba-1-conjugated FePt-nanoparticles, were excised, fixed with formalin, and placed in Fomblin for ex vivo MRI (11.7T) using multislice-multiecho, multiple gradient echo, rapid acquisition with relaxation enhancement, and susceptibility-weighted imaging (SWI). Aß plaques and areas of neuroinflammation appeared as hypointense regions whose number, location, and Z-score were measured as a function of sequence type and echo time. RESULTS: The MR contrast was due to the shortening of the transverse relaxation time of the plaque-adjacent tissue water. A theoretical analysis of this effect showed that the echo time was the primary determinant of plaque contrast and was used to optimize Z-scores. The Z-scores of the detected lesions varied from 21 to 34 as the echo times varied from 4 to 25 msec, with SWI providing the highest Z-score and number of detected lesions. Computation of the entire plaque and activated microglial distributions in 3D showed that resveratrol treatment led to a reduction of ∼24-fold of Aß plaque density and ∼4-fold in microglial activation. CONCLUSION: Optimized MRI of antibody-conjugated superparamagnetic nanoparticles served to reveal the 3D distributions of both Aß plaques and activated microglia and to measure the effects of drug treatments in this 3X Tg model. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2017;46:574-588.