Anti-HBc IgG Levels: A Predictor of HBsAg Seroclearance in Chronic Hepatitis B Patients with Nucleos(t)ide Analogue-Induced HBeAg Seroclearance.

BACKGROUND/AIMS: We investigated the efficiency of the indirect ratio of anti-HBc IgG at predicting HBsAg seroclearance in patients with nucleos(t)ide analogue (NA)-induced HBeAg seroclearance. METHODS: We performed a retrospective study that included 366 chronic hepatitis B patients (March 2007 to December 2016) at a single tertiary hospital. These patients were HBsAg seropositive, and experienced NA-induced HBeAg seroclearance. The indirect ratio of light absorbance of anti-HBc IgG levels were measured with chemiluminescent microparticle immunoassay using the Architect Anti-HBc assay (Abbott Laboratories, IL, USA) as a qualitative method prior to antiviral therapy. We calculated the cumulative incidences of HBsAg seroclearance based on the anti-HBc IgG levels. RESULTS: After a 10-year follow-up, 48 patients experienced HBsAg seroclearance (13.1%). Thirty-three of 179 patients who had an indirect ratio of light absorbance of anti-HBc IgG < 11 RLU (relative light unit) showed HBsAg seroclearance (18.4%); 15 of 187 patients who had an indirect ratio of light absorbance of anti-HBc IgG ≥ 11 RLU showed HBsAg seroclerance (8.0%) (p = 0.003). In multivariate analysis, age, and ALT at the time of HBeAg seroclearance were predictors of HBsAg seroclearance. Especially, the relative risk of HBsAg seroclearance in patients with baseline anti-HBc IgG levels < 11 RLU was 2.213 (95% CI, 1.220-4.014), compared to that in patients with higher levels of anti-HBc IgG at baseline (p = 0.009). CONCLUSION: Using an indirect method for anti-HBc IgG levels, baseline anti-HBc IgG levels (< 11RLU), age (≥ 50 years), and ALT (≥ 40 IU/L) might be associated with HBsAg seroclearance in patients with NA-induced HBeAg seroclearance.

Prostate Cancer Detection using Deep Convolutional Neural Networks.

Prostate cancer is one of the most common forms of cancer and the third leading cause of cancer death in North America. As an integrated part of computer-aided detection (CAD) tools, diffusion-weighted magnetic resonance imaging (DWI) has been intensively studied for accurate detection of prostate cancer. With deep convolutional neural networks (CNNs) significant success in computer vision tasks such as object detection and segmentation, different CNN architectures are increasingly investigated in medical imaging research community as promising solutions for designing more accurate CAD tools for cancer detection. In this work, we developed and implemented an automated CNN-based pipeline for detection of clinically significant prostate cancer (PCa) for a given axial DWI image and for each patient. DWI images of 427 patients were used as the dataset, which contained 175 patients with PCa and 252 patients without PCa. To measure the performance of the proposed pipeline, a test set of 108 (out of 427) patients were set aside and not used in the training phase. The proposed pipeline achieved area under the receiver operating characteristic curve (AUC) of 0.87 (95[Formula: see text] Confidence Interval (CI): 0.84-0.90) and 0.84 (95[Formula: see text] CI: 0.76-0.91) at slice level and patient level, respectively.