UViT-Seg: An Efficient ViT and U-Net-Based Framework for Accurate Colorectal Polyp Segmentation in Colonoscopy and WCE Images.

Colorectal cancer (CRC) stands out as one of the most prevalent global cancers. The accurate localization of colorectal polyps in endoscopy images is pivotal for timely detection and removal, contributing significantly to CRC prevention. The manual analysis of images generated by gastrointestinal screening technologies poses a tedious task for doctors. Therefore, computer vision-assisted cancer detection could serve as an efficient tool for polyp segmentation. Numerous efforts have been dedicated to automating polyp localization, with the majority of studies relying on convolutional neural networks (CNNs) to learn features from polyp images. Despite their success in polyp segmentation tasks, CNNs exhibit significant limitations in precisely determining polyp location and shape due to their sole reliance on learning local features from images. While gastrointestinal images manifest significant variation in their features, encompassing both high- and low-level ones, a framework that combines the ability to learn both features of polyps is desired. This paper introduces UViT-Seg, a framework designed for polyp segmentation in gastrointestinal images. Operating on an encoder-decoder architecture, UViT-Seg employs two distinct feature extraction methods. A vision transformer in the encoder section captures long-range semantic information, while a CNN module, integrating squeeze-excitation and dual attention mechanisms, captures low-level features, focusing on critical image regions. Experimental evaluations conducted on five public datasets, including CVC clinic, ColonDB, Kvasir-SEG, ETIS LaribDB, and Kvasir Capsule-SEG, demonstrate UViT-Seg's effectiveness in polyp localization. To confirm its generalization performance, the model is tested on datasets not used in training. Benchmarking against common segmentation methods and state-of-the-art polyp segmentation approaches, the proposed model yields promising results. For instance, it achieves a mean Dice coefficient of 0.915 and a mean intersection over union of 0.902 on the CVC Colon dataset. Furthermore, UViT-Seg has the advantage of being efficient, requiring fewer computational resources for both training and testing. This feature positions it as an optimal choice for real-world deployment scenarios.

Metabolic Bone Disease in Viral Cirrhosis: A Prospective Study.

Background/Aim. Metabolic Bone disorders are well-recognized extrahepatic complications of cirrhosis. The aim was to report their prevalence and the associated factors to their development in patients with viral cirrhosis. Patients and Methods. All consecutive patients with viral cirrhosis were prospectively enrolled. Parathyroid hormone, 25-hydroxyvitamin D, liver function, and phosphocalcic tests were measured in all patients. Bone mineral density was measured at the lumbar spine and total hip by dual-energy X-ray absorptiometry. Data were analyzed using SPSS software. Results. Forty-six cirrhotic patients were included with hepatitis C (87%) and hepatitis B (13%). The Child-Pugh score was grade A in 87% of cases and grade B in 13%. Thirty-seven patients had decreased bone mineral density with osteopenia in 24 patients and osteoporosis in 13 patients. Decreased 25-hydroxyvitamin D was found in 95.6% of cases. Bone disorders were significantly more frequent in old patients with low body mass index, long duration of liver disease, and low 25-hydroxyvitamin D level. None of these factors was an independent factor associated with bone disorders. Conclusion. Our study revealed a high prevalence of metabolic bone disorders among viral cirrhotic patients. Consequently, bone mineral density assessment should be performed systematically in all cirrhotic patients.

Safety and outcome using endoscopic dilatation for benign esophageal stricture without fluoroscopy.

AIM: To investigate the use of Savary-Gilliard marked dilators in tight esophageal strictures without fluoroscopy. METHODS: Seventy-two patients with significant dysphagia from benign strictures due to a variety of causes were dilated endoscopically. Patients with achalasia, malignant lesions or external compression were excluded. The procedure consisted of two parts. First, a guide wire was placed through video endoscopy and then dilatation was performed without fluoroscopy. In general, "the rule of three" was followed. Effective treatment was defined as the ability of patients, with or without repeated dilatations, to maintain a solid or semisolid diet for more than 12 mo. RESULTS: Six hundred and sixty two dilatations in a total of 72 patients were carried out. The success rate for placement of a guide wire was 100% and for dilatation 97%, without use of fluoroscopy, after 6 mo to 4 years of follow-up. The number of sessions per patient was between 1 and 7, with an average of 2 sessions. The ability of patients, after 1 or more sessions of dilatation, to maintain a solid or semisolid diet for more than 12 mo was obtained in 70 patients (95.8%). For very tight esophageal strictures, all patients improved clinically without complications after the endoscopic procedure without fluoroscopy, but we noted 3 failures. CONCLUSION: Dilatation using Savary-Gilliard dilators without fluoroscopy is safe and effective in the treatment of very tight esophageal strictures if performed with care.

Influence of steatosis on progression of fibrosis and virological response in chronic hepatitis C cases.

BACKGROUND AND STUDY AIMS: Hepatic steatosis seems to be frequently found histopathologically in chronic hepatitis C virus (HCV)-infected patients. The aim of this study is to determine the influence of steatosis on HCV disease severity (fibrosis) and to evaluate its impact on sustained virological response (SVR) to antiviral therapy. PATIENTS AND METHODS: From April 2008 to April 2010, 148 consecutive adults (87 females (59%) and 61 males (41%); mean age: 55.2 years) with HCV admitted for liver biopsy were included in this retrospective study. At least one element of metabolic syndrome was identified in all cases: Obesity (n=44), hyperlipidaemia (n=40), hypertension (n=29) and diabetes (n=21). Liver fibrosis was classified according to the Metavir score and hepatic steatosis described as following: S0: absent; S1: minimal (<30%); S2: moderate (30-60%); and S3: severe (>60%). Patients were divided into two groups: S0S1 group (absent or minimal steatosis) and S2S3 group (moderate to severe steatosis). Of the 148 patients, 53 were treated with pegylated interferon and ribavirin combination therapy. RESULTS: Steatosis was found in 40 patients (27%): S1 in 72.5%, S2 in 17.5% and S3 in 10% of cases. The distribution of patients according to the degree of fibrosis was as follows: in the S0S1 group, F1=12.4%, F2=36.5%, F3=21.1% and F4=21.1% and in the S2S3 group, F1=9%, F2=45.5%, F3=18.2% and F4=27.3%. There was no difference between the two groups regarding the degree of fibrosis (p≥0.80). The rate of SVR was 64%: 63% in the S0S1 group and 75% in the S2S3 group. The difference was not statistically significant (p=1). CONCLUSION: Steatosis was found in 25% of cases. Liver steatosis in chronic hepatitis C is not a negative prognostic factor of response to combined antiviral therapy. These results must be confirmed by a large series of patients.