PurposeThe nonalcoholic fatty liver disease is the most common liver abnormality. Up to date, liver biopsy is the reference standard for direct liver steatosis quantification in hepatic tissue samples. In this paper we propose a neural network-based approach for nonalcoholic fatty liver disease assessment in ultrasound.MethodsWe used the Inception-ResNet-v2 deep convolutional neural network pre-trained on the ImageNet dataset to extract high-level features in liver B-mode ultrasound image sequences. The steatosis level of each liver was graded by wedge biopsy. The proposed approach was compared with the hepatorenal index technique and the gray-level co-occurrence matrix algorithm. After the feature extraction, we applied the support vector machine algorithm to classify images containing fatty liver. Based on liver biopsy, the fatty liver was defined to have more than 5% of hepatocytes with steatosis. Next, we used the features and the Lasso regression method to assess the steatosis level.ResultsThe area under the receiver operating characteristics curve obtained using the proposed approach was equal to 0.977, being higher than the one obtained with the hepatorenal index method, 0.959, and much higher than in the case of the gray-level co-occurrence matrix algorithm, 0.893. For regression the Spearman correlation coefficients between the steatosis level and the proposed approach, the hepatorenal index and the gray-level co-occurrence matrix algorithm were equal to 0.78, 0.80 and 0.39, respectively.ConclusionsThe proposed approach may help the sonographers automatically diagnose the amount of fat in the liver. The presented approach is efficient and in comparison with other methods does not require the sonographers to select the region of interest.

No abstract

IntroductionRoux-en-Y gastric bypass (RYGB) is considered the gold standard bariatric procedure with documented safety and effectiveness. Laparoscopic sleeve gastrectomy (LSG) is a newer procedure being done with increasing frequency. Randomized comparisons of LSG and other bariatric procedures are limited. We present the results of the first prospective randomized trial comparing LSG and RYGB in the Polish population.AimTo assess the efficacy and safety of LSG versus RYGB in the treatment of morbid obesity and obesity-related comorbidities.Material and methodsSeventy-two morbidly obese patients were randomized to RYGB (36 patients) or LSG (36 patients). Both groups were comparable regarding age, gender, body mass index (BMI) and comorbidities. The follow-up period was at least 12 months. Baseline and 6 and 12 month outcomes were analyzed including assessment of percent excess weight lost (%EWL), reduction in BMI, morbidity (minor, major, early and late complications), mortality, reoperations, comorbidities and nutritional deficiencies.ResultsThere was no 30-day mortality and no significant difference in major complication rate (0% after RYGB and 8.3% after LSG, p > 0.05) or minor complication rate (16.6% after RYGB and 10.1% after LSG, p > 0.05). There were no early reoperations after RYGB and 2 after LSG (5.5%) (p > 0.05). Weight loss was significant after RYGB and LSG but there was no difference between both groups at 6 and 12 months of follow-up. At 12 months %EWL in RYGB and LSG groups reached 64.2% and 67.6% respectively (p > 0.05). There was no significant difference in the overall prevalence of comorbidities and nutritional deficiencies.ConclusionsBoth LSG and RYGB produce significant weight loss at 6 and 12 months after surgery. The procedures are equally effective with regard to %EWL, reduction in BMI and amelioration of comorbidities at 6 and 12 months of follow-up. Laparoscopic sleeve gastrectomy and RYGB are comparably safe techniques with no significant differences in minor and major complication rates at 6 and 12 months.

Patients with NASH undergoing RYGB are more susceptible to early transient deterioration of liver function than after SG.

Introduction Roux-en-Y gastric bypass (RYGB) and laparoscopic sleeve gastrectomy (LSG) are the two most frequently performed bariatric operations. These two types of metabolic surgery alter the anatomy and function of digestive tract producing significant weight loss in morbidly obese patients but may lead to malnutrition. Aim Analysis of incidence and severity of malnutrition after bariatric surgery in patients submitted to RYGB or LSG during 12 months of follow-up. Material and Methods Retrospective study of 98 patients after RYGB (n = 47) or LSG (n = 51) assessed for nutritional deficiencies during 12 months after surgery was conducted. The differences in body mass index (BMI) and blood tests including erythrocytes, haemoglobin, total protein, albumin, iron, ferritin, transferrin, vitamin B12, folic acid, calcium and phosphorus concentrations were compared between groups before the operations and at 1 and 12 months. Results Nutritional deficiencies were common before surgery with prevalence up to 19.6% for albumin in the LSG group. Median preoperative BMI levels and albumin concentrations were higher in the RYGB group compared to the LSG group, but there was no difference in percent excess weight loss (%EWL) at 1 and 12 months between LSG and RYGB. One month after LSG erythrocyte count, haemoglobin, iron, ferritin and transferrin levels were significantly higher than in the RYGB group. These differences subsided at 12 months. At 12 months, only the prevalence of vitamin B 12 deficiency was significantly higher in the RYGB group. Conclusion Both RYGB and LSG lead to nutritional deficiencies despite different properties of operations and similar %EWL during follow-up.