Colonoscopy screening and colonoscopic polypectomy can decrease the incidence and mortality rate of colorectal cancer (CRC). The adenoma detection rate and accuracy of diagnosis of colorectal polyp which vary in different experienced endoscopists have impact on the colonoscopy protection effect of CRC. The work proposed a colorectal polyp image detection and classification system through grayscale images and deep learning. The system collected the data of CVC-Clinic and 1000 colorectal polyp images of Linkou Chang Gung Medical Hospital. The red-green-blue (RGB) images were transformed to 0 to 255 grayscale images. Polyp detection and classification were performed by convolutional neural network (CNN) model. Data for polyp detection was divided into five groups and tested by 5-fold validation. The accuracy of polyp detection was 95.1% for grayscale images which is higher than 94.1% for RGB and narrow-band images. The diagnostic accuracy, precision and recall rates were 82.8%, 82.5% and 95.2% for narrow-band images, respectively. The experimental results show that grayscale images achieve an equivalent or even higher accuracy of polyp detection than RGB images for lightweight computation. It is also found that the accuracy of polyp detection and classification is dramatically decrease when the size of polyp images small than 1600 pixels. It is recommended that clinicians could adjust the distance between the lens and polyps appropriately to enhance the system performance when conducting computer-assisted colorectal polyp analysis.

Background. The association between gallbladder (GB) disease and colorectal precancerous lesions remains elusive. This study sought to explore the association between GB disease and colorectal neoplasms at different locations. Methods. Patients who received general health checkup from January to December 2008 were included and subgrouped into three groups by polyp location: proximal, distal, and whole colon. GB disease and other known risk factors for colon cancer were compared and analyzed. Different types of polyps at different locations were further investigated. Results. Of a total of 3136 patients (1776 men and 1360 women; mean age, 49.3 years) who had colon polyps, 212 (6.8%) had GB stone and 512 (16.3%) had GB polyps. Patients in the proximal colon polyp group had higher rates of GB polyps and stones. GB polyps were independently associated with proximal colon polyps, including both hyperplastic polyps (odds ratio, 1.523; P=0.034) and adenomatous polyps (odds ratio, 1.351; P=0.048). No relationship between GB polyps and distal or any colon polyps was observed. Irrespective of the polyp location (i.e., proximal, distal, or any part of the colon), GB stone did not show any association with colon polyp. Conclusions. We suggested that GB polyps are associated with proximal colon polyps. Colonoscopy may be a more effective strategy for screening proximal precancerous lesions among patients with GB polyps. The association between GB disease and colon polyps demands further prospective investigation.

Colonoscopy is a valuable tool for preventing and reducing the incidence and mortality of colorectal cancer. Although several computer-aided colorectal polyp detection and diagnosis systems have been proposed for clinical application, many remain susceptible to interference problems, including low image clarity, unevenness, and low accuracy for the analysis of dynamic images; these drawbacks affect the robustness and practicality of these systems. This study proposed an intraprocedure alert system for colonoscopy examination developed on the basis of deep learning. The proposed system features blurred image detection, foreign body detection, and polyp detection modules facilitated by convolutional neural networks. The training and validation datasets included high-quality images and low-quality images, including blurred images and those containing folds, fecal matter, and opaque water. For the detection of blurred images and images containing folds, fecal matter, and opaque water, the accuracy rate was 96.2%. Furthermore, the study results indicated a per-polyp detection accuracy of 100% when the system was applied to video images. The recall rates for high-quality image frames and polyp image frames were 95.7% and 92%, respectively. The overall alert accuracy rate and the false-positive rate of low quality for video images obtained through per-frame analysis were 95.3% and 0.18%, respectively. The proposed system can be used to alert colonoscopists to the need to slow their procedural speed or to perform flush or lumen inflation in cases where the colonoscope is being moved too rapidly, where fecal residue is present in the intestinal tract, or where the colon has been inadequately distended.

How hepatatitis C virus (HCV) infection affects the interplay among abundant adipokines in the host remains unclear. A prospective study was conducted with 450 consecutive genotype 1 (G1) and G2 HCV patients who completed a course of anti-HCV therapy and underwent pre-therapy and 24-week post-therapy surveys to assess various profiles and levels of abundant adipokines, including leptin, adiponectin, and plasminogen activator inhibitor-1 (PAI-1). Before anti-HCV therapy, multivariate analyses showed gender to be associated with leptin and adiponectin levels, and BMI with leptin and PAI-1 levels. Among patients with a sustained virological response (SVR, n = 372), associations at 24 weeks post-therapy were as follows: gender and BMI with all adipokine levels; hepatic steatosis and aspartate aminotransferase to platelet ratio index with adiponectin levels; and HOMA-IR and HCV genotype with PAI-1 levels. Paired t-tests revealed increased post-therapeutic PAI-1 levels in G1 SVR patients and decreased adiponectin levels in all SVR patients compared to pre-therapeutic levels. HCV infection may obscure associations between abundant adipokines and metabolic/hepatic profiles. In SVR patients, a higher hierarchical status of PAI-1 versus adiponectin in affecting glucose metabolism was noted at 24 weeks post-therapy. Such genotype-non-specific adiponectin decreases and G1-specific PAI-1 increases warrant careful follow-up of HCV patients after SVR according to viral genotype.

Background/Objectives: Patients with inflammatory bowel disease (IBD) are at a higher risk of developing bone disorders. Awareness and understanding of the disease are crucial for prevention and early diagnosis. Currently, there is no research on the risk factors and knowledge of bone fragility in the population with IBD in Taiwan. This study aimed to evaluate the risk factors and self-assessed knowledge levels of bone health among patients with IBD in Taiwan. Methods: This single-center cross-sectional study included 59 adult patients. Clinical data, blood tests, bone mineral density (BMD), T-score, Z-score, and questionnaires covering self-assessed knowledge, fracture risks, and physical activity were assessed. The patients were divided into normal and low BMD groups. Results: Of all participants, eighteen (30.5%) had low BMD: six (10.2%) had BMD below the expected range, ten (16.9%) had osteopenia, and two (3.4%) had osteoporosis. Vitamin D insufficiency and deficiency were observed in 26.3% and 66.6% of the patients, respectively. According to multivariate analysis, age and sex hormone deficiency are strongly associated with low BMD. Educational interventions significantly improved the patients’ self-assessed knowledge levels. Conclusions: Age and sex hormone deficiency are significant factors contributing to low BMD in IBD patients. Not only women but also men with IBD who had symptoms of hypogonadism are at high risk for low BMD. Educational interventions improve self-assessment knowledge regarding the relationship between IBD and bone health.