Computer vision applied to dual-energy computed tomography images for precise calcinosis cutis quantification in patients with systemic sclerosis.

BACKGROUND: Although treatments have been proposed for calcinosis cutis (CC) in patients with systemic sclerosis (SSc), a standardized and validated method for CC burden quantification is necessary to enable valid clinical trials. We tested the hypothesis that computer vision applied to dual-energy computed tomography (DECT) finger images is a useful approach for precise and accurate CC quantification in SSc patients. METHODS: De-identified 2-dimensional (2D) DECT images from SSc patients with clinically evident lesser finger CC lesions were obtained. An expert musculoskeletal radiologist confirmed accurate manual segmentation (subtraction) of the phalanges for each image as a gold standard, and a U-Net Convolutional Neural Network (CNN) computer vision model for segmentation of healthy phalanges was developed and tested. A validation study was performed in an independent dataset whereby two independent radiologists manually measured the longest length and perpendicular short axis of each lesion and then calculated an estimated area by assuming the lesion was elliptical using the formula long axis/2 × short axis/2 × π, and a computer scientist used a region growing technique to calculate the area of CC lesions. Spearman's correlation coefficient, Lin's concordance correlation coefficient with 95% confidence intervals (CI), and a Bland-Altman plot (Stata V 15.1, College Station, TX) were used to test for equivalence between the radiologists' and the CNN algorithm-generated area estimates. RESULTS: Forty de-identified 2D DECT images from SSc patients with clinically evident finger CC lesions were obtained and divided into training (N = 30 with image rotation × 3 to expand the set to N = 120) and test sets (N = 10). In the training set, five hundred epochs (iterations) were required to train the CNN algorithm to segment phalanges from adjacent CC, and accurate segmentation was evaluated using the ten held-out images. To test model performance, CC lesional area estimates calculated by two independent radiologists and a computer scientist were compared (radiologist 1 vs. radiologist 2 and radiologist 1 vs. computer vision approach) using an independent test dataset comprised of 31 images (8 index finger and 23 other fingers). For the two radiologists', and the radiologist vs. computer vision measurements, Spearman's rho was 0.91 and 0.94, respectively, both p < 0.0001; Lin's concordance correlation coefficient was 0.91 (95% CI 0.85-0.98, p < 0.001) and 0.95 (95% CI 0.91-0.99, p < 0.001); and Bland-Altman plots demonstrated a mean difference between radiologist vs. radiologist, and radiologist vs. computer vision area estimates of - 0.5 mm2 (95% limits of agreement - 10.0-9.0 mm2) and 1.7 mm2 (95% limits of agreement - 6.0-9.5 mm2, respectively. CONCLUSIONS: We demonstrate that CNN quantification has a high degree of correlation with expert radiologist measurement of finger CC area measurements. Future work will include segmentation of 3-dimensional (3D) images for volumetric and density quantification, as well as validation in larger, independent cohorts.

An Autoimmune Protocol Diet Improves Patient-Reported Quality of Life in Inflammatory Bowel Disease.

BACKGROUND: Prior studies suggest dietary modification may improve clinical response or remission rates in patients with inflammatory bowel disease (IBD). Our aim was to examine whether an autoimmune protocol diet improves quality of life in patients with active Crohn disease (CD) and ulcerative colitis (UC). METHODS: We conducted an uncontrolled clinical trial of the autoimmune protocol diet in adult patients with active IBD (Harvey-Bradshaw Index ≥ 5 for CD or partial Mayo score ≥ 3 for UC, and erosions/ulcers on endoscopy and/or elevated fecal calprotectin). The dietary intervention consisted of a 6-week elimination phase, followed by a 5-week maintenance phase. Short Inflammatory Bowel Disease Questionnaire (SIBDQ) was completed at baseline, and weeks 3, 6, 9, and 11. RESULTS: The final cohort included 6 UC and 9 CD participants. Mean SIBDQ score improved significantly from baseline (46.5) to weeks 3 (54.0, P = 0.02), 6 (53.3, P = 0.02), 9 (62.0, P = 0.03), and 11 (60.5, P = 0.05). Among participants completing all 5 surveys, mean SIBDQ increased from 46.5 to 61.5 by week 11 (P = 0.03). By week 3, participants experienced significant improvements in bowel movement frequency (36%, P = 0.04), stress (28%, P = 0.01), and ability to perform leisure/sport activities (29%, P = 0.02). Effects were not significantly different between CD and UC participants. CONCLUSIONS: Dietary modification can improve quality of life as early as week 3 in patients with active IBD. Larger randomized controlled trials are needed to examine dietary interventions in IBD.

The Autoimmune Protocol Diet Modifies Intestinal RNA Expression in Inflammatory Bowel Disease.

Researchers from the Scripps Clinic in La Jolla, CA recently looked at gene expression to better understand the role that diet plays in inflammatory bowel disease. Their findings suggest that diet may help modify inflammatory pathways in people with ulcerative colitis.

Efficacy of the Autoimmune Protocol Diet for Inflammatory Bowel Disease.

INTRODUCTION: Data suggest dietary modification can improve clinical responses in inflammatory bowel disease (IBD). The goal of this study was to determine the efficacy of an autoimmune protocol diet in patients with Crohn's disease and ulcerative colitis. METHODS: We enrolled adults with active IBD (Harvey-Bradshaw index ≥ 5 or partial Mayo score ≥3 and erosions on endoscopy and/or elevated fecal calprotectin). For the autoimmune protocol, patients underwent 6-week elimination followed by 5-week maintenance phase. Clinical indices, laboratories, and biomarkers were assessed at baseline and weeks 6 and 11. Endoscopy was performed at study completion. RESULTS: The final cohort included 15 patients with IBD, with mean disease duration 19 years (SD 14.6) and active biological use in 7 (47%) patients. Nutrient repletion was initiated for deficiencies in vitamin D (n = 3) and iron (n = 6). From week 0 to weeks 6 and 11, mean partial Mayo score significantly improved from 5.8 (SD 1.2) to 1.2 (SD 2.0) and 1.0 (SD 2.0) for ulcerative colitis, and mean Harvey-Bradshaw index significantly improved from 7 (SD 1.5) to 3.6 (SD 2.1) and 3.4 (SD 2.6) for Crohn's disease. C-reactive protein did not significantly change during study. Mean fecal calprotectin improved from 471 (SD 562) to 112 (SD 104) at week 11 (P = 0.12). Among those with follow-up endoscopy at week 11 (n = 7), improvements were noted in simple endoscopic score for Crohn's disease (n = 1), Rutgeerts score (n = 1), and Mayo endoscopy subscore (n = 4). DISCUSSION: Dietary elimination can improve symptoms and endoscopic inflammation in patients with IBD. Randomized controlled trials are warranted.