Two-dimensional Convolutional Neural Network Using Quantitative US for Noninvasive Assessment of Hepatic Steatosis in NAFLD.

Background Quantitative US (QUS) using radiofrequency data analysis has been recently introduced for noninvasive evaluation of hepatic steatosis. Deep learning algorithms may improve the diagnostic performance of QUS for hepatic steatosis. Purpose To evaluate a two-dimensional (2D) convolutional neural network (CNN) algorithm using QUS parametric maps and B-mode images for diagnosis of hepatic steatosis, with the MRI-derived proton density fat fraction (PDFF) as the reference standard, in patients with nonalcoholic fatty liver disease (NAFLD). Materials and Methods: Consecutive adult participants with suspected NAFLD were prospectively enrolled at a single academic medical center from July 2020 to June 2021. Using radiofrequency data analysis, two QUS parameters (tissue attenuation imaging [TAI] and tissue scatter-distribution imaging [TSI]) were measured. On B-mode images, hepatic steatosis was graded using visual scoring (none, mild, moderate, or severe). Using B-mode images and two QUS parametric maps (TAI and TSI) as input data, the algorithm estimated the US fat fraction (USFF) as a percentage. The correlation between the USFF and MRI PDFF was evaluated using the Pearson correlation coefficient. The diagnostic performance of the USFF for hepatic steatosis (MRI PDFF ≥5%) was evaluated using receiver operating characteristic curve analysis and compared with that of TAI, TSI, and visual scoring. Results Overall, 173 participants (mean age, 51 years ± 14 [SD]; 96 men) were included, with 126 (73%) having hepatic steatosis (MRI PDFF ≥5%). USFF correlated strongly with MRI PDFF (Pearson r = 0.86, 95% CI: 0.82, 0.90; P < .001). For diagnosing hepatic steatosis (MRI PDFF ≥5%), the USFF yielded an area under the receiver operating characteristic curve of 0.97 (95% CI: 0.93, 0.99), higher than those of TAI, TSI, and visual scoring (P = .015, .006, and < .001, respectively), with a sensitivity of 90% (95% CI: 84, 95 [114 of 126]) and a specificity of 91% (95% CI: 80, 98 [43 of 47]) at a cutoff value of 5.7%. Conclusion A deep learning algorithm using quantitative US parametric maps and B-mode images accurately estimated the hepatic fat fraction and diagnosed hepatic steatosis in participants with nonalcoholic fatty liver disease. ClinicalTrials.gov registration nos. NCT04462562, NCT04180631 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Sidhu and Fang in this issue.

Accuracy assessment of measuring component position after total ankle arthroplasty using a conventional method.

BACKGROUND: This study was to assess the accuracy of measuring the tibial and talar components position and to investigate the outlier rate of each component and predisposing factors related to component malalignment after total ankle arthroplasty (TAA) using a conventional method. METHODS: One hundred fifty consecutive primary total ankle arthroplasty were performed using the three-component HINTEGRA prosthesis for ankle end-stage osteoarthritis. Radiographic analysis for the accuracy of component position in coronal and sagittal plane was conducted at postoperative 6 months. Additionally, the accuracy of component position was evaluated according to presence of preoperative deformity or joint incongruency. RESULTS: The mean postoperative coronal angles of the tibial and talar components (α and γ) were 91.9° and 91.3°. The mean postoperative sagittal angles of the tibial and talar components (ß and δ angle) were 84.6° and 91.7°. In the coronal plane, 16 (10.7%) tibial components and 15 (10.0%) talar components showed outliers greater than 5°. In sagittal plane, 15 (10.0%) tibial components and 29 (19.3%) talar components showed outliers greater than 5°. There was no meaningful increase of the outlier rate regarding presence of preoperative deformity or joint incongruency. CONCLUSIONS: In conventional method of TAA, the outlier rate of the tibial and talar components was about 10 to 20%, especially, the outlier rate of talar component in sagittal plane was up to 20%. Therefore, careful attention should be paid to implant the talar component in conventional TAA.

Exposure and toxicity assessment of ultrafine particles from nearby traffic in urban air in seoul, Korea.

OBJECTIVES: We investigated the particle mass size distribution and chemical properties of air pollution particulate matter (PM) in the urban area and its capacity to induce cytotoxicity in human bronchial epithelial (BEAS-2B) cells. METHODS: To characterize the mass size distributions and chemical concentrations associated with urban PM, PM samples were collected by a 10-stage Micro-Orifice Uniform Deposit Impactor close to nearby traffic in an urban area from December 2007 to December 2009. PM samples for in vitro cytotoxicity testing were collected by a mini-volume air sampler with PM10 and PM2.5 inlets. RESULTS: The PM size distributions were bi-modal, peaking at 0.18 to 0.32 and 1.8 to 3.2 µm. The mass concentrations of the metals in fine particles (0.1 to 1.8 µm) accounted for 45.6 to 80.4% of the mass concentrations of metals in PM10. The mass proportions of fine particles of the pollutants related to traffic emission, lead (80.4%), cadmium (69.0%), and chromium (63.8%) were higher than those of other metals. Iron was the dominant transition metal in the particles, accounting for 64.3% of the PM10 mass in all the samples. We observed PM concentration-dependent cytotoxic effects on BEAS-2B cells. CONCLUSIONS: We found that exposure to PM2.5 and PM10 from a nearby traffic area induced significant increases in protein expression of inflammatory cytokines (IL-6 and IL-8). The cell death rate and release of cytokines in response to the PM2.5 treatment were higher than those with PM10. The combined results support the hypothesis that ultrafine particles from vehicular sources can induce inflammatory responses related to environmental respiratory injury.

Quantitative color assessment of dermoscopy images using perceptible color regions.

BACKGROUND: Dermoscopy is a non-invasive in vivo skin imaging technique that assists dermatologists in diagnosing melanoma. However, the use of dermoscopy for diagnosis requires extensive training since this approach often provides extremely complex and subjective information. The presence of an imperceptible color difference in dermoscopy images is one of the serious problems associated with the use of this technique. This imperceptible color difference leads to inaccurate lesion extraction at the borders and hinders the assessment of lesion features. Therefore, objective and quantitative assessment based on perceptible color differences is important for the diagnosis of melanoma using dermoscopy. METHODS: In this study, we developed a method for assessing colors in a lesion. Twenty-seven perceptible color regions based on the multi-thresholding method in each color channel were constructed, and dominant color region (DCR), bluish dominant region (BDR), and the number of colors were assessed as three diagnostic parameters from these perceptible color regions on 150 dermoscopy images. RESULTS/CONCLUSION: Diagnostic accuracy was calculated by combination of three diagnostic parameters derived from DCR, BDR, and the number of colors. Diagnostic accuracy with 73.33% sensitivity and 90.67% specificity was obtained in case of positive features in more than two parameters.