Artificial Intelligence-based CT Assessment of Bronchiectasis: The COPDGene Study.

Background CT is the standard method used to assess bronchiectasis. A higher airway-to-artery diameter ratio (AAR) is typically used to identify enlarged bronchi and bronchiectasis; however, current imaging methods are limited in assessing the extent of this metric in CT scans. Purpose To determine the extent of AARs using an artificial intelligence-based chest CT and assess the association of AARs with exacerbations over time. Materials and Methods In a secondary analysis of ever-smokers from the prospective, observational, multicenter COPDGene study, AARs were quantified using an artificial intelligence tool. The percentage of airways with AAR greater than 1 (a measure of airway dilatation) in each participant on chest CT scans was determined. Pulmonary exacerbations were prospectively determined through biannual follow-up (from July 2009 to September 2021). Multivariable zero-inflated regression models were used to assess the association between the percentage of airways with AAR greater than 1 and the total number of pulmonary exacerbations over follow-up. Covariates included demographics, lung function, and conventional CT parameters. Results Among 4192 participants (median age, 59 years; IQR, 52-67 years; 1878 men [45%]), 1834 had chronic obstructive pulmonary disease (COPD). During a 10-year follow-up and in adjusted models, the percentage of airways with AARs greater than 1 (quartile 4 vs 1) was associated with a higher total number of exacerbations (risk ratio [RR], 1.08; 95% CI: 1.02, 1.15; P = .01). In participants meeting clinical and imaging criteria of bronchiectasis (ie, clinical manifestations with ≥3% of AARs >1) versus those who did not, the RR was 1.37 (95% CI: 1.31, 1.43; P < .001). Among participants with COPD, the corresponding RRs were 1.10 (95% CI: 1.02, 1.18; P = .02) and 1.32 (95% CI: 1.26, 1.39; P < .001), respectively. Conclusion In ever-smokers with chronic obstructive pulmonary disease, artificial intelligence-based CT measures of bronchiectasis were associated with more exacerbations over time. Clinical trial registration no. NCT00608764 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Schiebler and Seo in this issue.

Clinical Predictors of Liver Fibrosis Presence and Progression in Human Immunodeficiency Virus-Associated Nonalcoholic Fatty Liver Disease.

BACKGROUND: Nonalcoholic fatty liver disease (NAFLD) affects more than one-third of people living with human immunodeficiency virus (HIV). Nonetheless, its natural history is poorly understood, including which patients are most likely to have a progressive disease course. METHODS: We leveraged a randomized trial of the growth hormone-releasing hormone analogue tesamorelin to treat NAFLD in HIV. Sixty-one participants with HIV-associated NAFLD were randomized to tesamorelin or placebo for 12 months with serial biopsies. RESULTS: In all participants with baseline biopsies (n = 58), 43% had hepatic fibrosis. Individuals with fibrosis had higher NAFLD Activity Score (NAS) (mean ± standard deviation [SD], 3.6 ± 2.0 vs 2.0 ± 0.8; P < .0001) and visceral fat content (mean ± SD, 284 ± 91 cm2 vs 212 ± 95 cm2; P = .005), but no difference in hepatic fat or body mass index. Among placebo-treated participants with paired biopsies (n = 24), 38% had hepatic fibrosis progression over 12 months. For each 25 cm2 higher visceral fat at baseline, odds of fibrosis progression increased by 37% (odds ratio, 1.37 [95% confidence interval, 1.03-2.07]). There was no difference in baseline NAS between fibrosis progressors and nonprogressors, though NAS rose over time in the progressor group (mean ± SD, 1.1 ± 0.8 vs -0.5 ± 0.6; P < .0001). CONCLUSIONS: In this longitudinal study of HIV-associated NAFLD, high rates of hepatic fibrosis and progression were observed. Visceral adiposity was identified as a novel predictor of worsening fibrosis. In contrast, baseline histologic characteristics did not relate to fibrosis progression.

Deep learning for automated segmentation of pelvic muscles, fat, and bone from CT studies for body composition assessment.

OBJECTIVE: To develop a deep convolutional neural network (CNN) to automatically segment an axial CT image of the pelvis for body composition measures. We hypothesized that a deep CNN approach would achieve high accuracy when compared to manual segmentations as the reference standard. MATERIALS AND METHODS: We manually segmented 200 axial CT images at the supra-acetabular level in 200 subjects, labeling background, subcutaneous adipose tissue (SAT), muscle, inter-muscular adipose tissue (IMAT), bone, and miscellaneous intra-pelvic content. The dataset was randomly divided into training (180/200) and test (20/200) datasets. Data augmentation was utilized to enlarge the training dataset and all images underwent preprocessing with histogram equalization. Our model was trained for 50 epochs using the U-Net architecture with batch size of 8, learning rate of 0.0001, Adadelta optimizer and a dropout of 0.20. The Dice (F1) score was used to assess similarity between the manual segmentations and the CNN predicted segmentations. RESULTS: The CNN model with data augmentation of N = 3000 achieved accurate segmentation of body composition for all classes. The Dice scores were as follows: background (1.00), miscellaneous intra-pelvic content (0.98), SAT (0.97), muscle (0.95), IMAT (0.91), and bone (0.92). Mean time to automatically segment one CT image was 0.07 s (GPU) and 2.51 s (CPU). CONCLUSIONS: Our CNN-based model enables accurate automated segmentation of multiple tissues on pelvic CT images, with promising implications for body composition studies.

Effects of tesamorelin on non-alcoholic fatty liver disease in HIV: a randomised, double-blind, multicentre trial.

BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) is a substantial cause of comorbidity in people with HIV and there are no proven pharmacological treatments for the disease in this population. We assessed the effects of tesamorelin on liver fat and histology in people with HIV and NAFLD. METHODS: This randomised, double-blind, multicentre study with identical placebo as a comparator was done in a hospital and a medical research centre in the USA. People with HIV infection and a hepatic fat fraction (HFF) of 5% or more by proton magnetic resonance spectroscopy were eligible. Participants were randomly assigned (1:1) to receive either tesamorelin 2 mg once daily or placebo once daily for 12 months, followed by a 6-month open-label phase during which all participants received tesamorelin 2 mg daily. The randomisation list was prepared by the study statistician using a permuted block algorithm within each stratum with randomly varying block sizes. The primary endpoint was change in HFF between baseline and 12 months. The primary safety endpoint was glucose. Analysis was by intention to treat using all available data. This trial is registered with ClinicalTrials.gov, number NCT02196831. FINDINGS: 61 patients were enrolled between Aug 20, 2015, and Jan 16, 2019, of whom 30 received tesamorelin and 30 received placebo. Patients receiving tesamorelin had a greater reduction of HFF than did patients receiving placebo, with an absolute effect size of -4·1% (95% CI -7·6 to -0·7, p=0·018), corresponding to a -37% (95% CI -67 to -7, p=0·016) relative reduction from baseline. After 12 months, 35% of individuals receiving tesamorelin and 4% receiving placebo had a HFF of less than 5% (p=0·0069). Changes in fasting glucose and glycated haemoglobin were not different between groups at 12 months. Individuals in the tesamorelin group experienced more localised injection site complaints than those in the placebo group, though none were judged to be serious. INTERPRETATION: Tesamorelin might be beneficial in people with HIV and NAFLD. Further studies are needed to determine the long-term effects of tesamorelin on liver histology. FUNDING: National Institutes of Health and National Institute of Allergy and Infectious Diseases.

A genome-wide assessment of adrenocorticotropin action in the Y1 mouse adrenal tumor cell line.

This report summarizes the genome-wide effects of ACTH on transcript accumulation in mouse adrenal Y1 cells and the relative contributions of the cAMP-, protein kinase C- and Ca(2+)-dependent signaling pathways to these actions of the hormone. ACTH affected the accumulation of 1386 transcripts, a much larger number than previously appreciated. The cAMP signaling pathway accounted for approximately 56% of the ACTH effects whereas the protein kinase C- and Ca(2+)-dependent pathways made smaller contributions to ACTH action. Approximately 38% of the ACTH-affected transcripts could not be assigned to these signaling pathways and thus represent candidates for regulation via other mechanisms. The set of ACTH-regulated transcripts included clusters with functions in steroid metabolism, cell proliferation and alternative splicing. Collectively, our results suggest that Y1 adrenal cells undergo extensive remodeling upon prolonged stimulation with ACTH. The functional implications of ACTH on alternative splicing are explored.

Global profiles of gene expression induced by adrenocorticotropin in Y1 mouse adrenal cells.

ACTH regulates the steroidogenic capacity, size, and structural integrity of the adrenal cortex through a series of actions involving changes in gene expression; however, only a limited number of ACTH-regulated genes have been identified, and these only partly account for the global effects of ACTH on the adrenal cortex. In this study, a National Institute on Aging 15K mouse cDNA microarray was used to identify genome-wide changes in gene expression after treatment of Y1 mouse adrenocortical cells with ACTH. ACTH affected the levels of 1275 annotated transcripts, of which 46% were up-regulated. The up-regulated transcripts were enriched for functions associated with steroid biosynthesis and metabolism; the down- regulated transcripts were enriched for functions associated with cell proliferation, nuclear transport and RNA processing, including alternative splicing. A total of 133 different transcripts, i.e. only 10% of the ACTH-affected transcripts, were represented in the categories above; most of these had not been described as ACTH-regulated previously. The contributions of protein kinase A and protein kinase C to these genome-wide effects of ACTH were evaluated in microarray experiments after treatment of Y1 cells and derivative protein kinase A-defective mutants with pharmacological probes of each pathway. Protein kinase A-dependent signaling accounted for 56% of the ACTH effect; protein kinase C-dependent signaling accounted for an additional 6%. These results indicate that ACTH affects the expression profile of Y1 adrenal cells principally through cAMP- and protein kinase A- dependent signaling. The large number of transcripts affected by ACTH anticipates a broader range of actions than previously appreciated.