Rapid Polyp Classification in Colonoscopy Using Textural and Convolutional Features.

Colorectal cancer is the leading cause of cancer-associated morbidity and mortality worldwide. One of the causes of developing colorectal cancer is untreated colon adenomatous polyps. Clinically, polyps are detected in colonoscopy and the malignancies are determined according to the biopsy. To provide a quick and objective assessment to gastroenterologists, this study proposed a quantitative polyp classification via various image features in colonoscopy. The collected image database was composed of 1991 images including 1053 hyperplastic polyps and 938 adenomatous polyps and adenocarcinomas. From each image, textural features were extracted and combined in machine learning classifiers and machine-generated features were automatically selected in deep convolutional neural networks (DCNN). The DCNNs included AlexNet, Inception-V3, ResNet-101, and DenseNet-201. AlexNet trained from scratch achieved the best performance of 96.4% accuracy which is better than transfer learning and textural features. Using the prediction models, the malignancy level of polyps can be evaluated during a colonoscopy to provide a rapid treatment plan.

Deep learning for abdominal ultrasound: A computer-aided diagnostic system for the severity of fatty liver.

BACKGROUND: The prevalence of nonalcoholic fatty liver disease is increasing over time worldwide, with similar trends to those of diabetes and obesity. A liver biopsy, the gold standard of diagnosis, is not favored due to its invasiveness. Meanwhile, noninvasive evaluation methods of fatty liver are still either very expensive or demonstrate poor diagnostic performances, thus, limiting their applications. We developed neural network-based models to assess fatty liver and classify the severity using B-mode ultrasound (US) images. METHODS: We followed standards for reporting of diagnostic accuracy guidelines to report this study. In this retrospective study, we utilized B-mode US images from a consecutive series of patients to develop four-class, two-class, and three-class diagnostic prediction models. The images were eligible if confirmed by at least two gastroenterologists. We compared pretrained convolutional neural network models, consisting of visual geometry group (VGG)19, ResNet-50 v2, MobileNet v2, Xception, and Inception v2. For validation, we utilized 20% of the dataset resulting in >100 images for each severity category. RESULTS: There were 21,855 images from 2,070 patients classified as normal (N = 11,307), mild (N = 4,467), moderate (N = 3,155), or severe steatosis (N = 2,926). We used ResNet-50 v2 for the final model as the best ones. The areas under the receiver operating characteristic curves were 0.974 (mild steatosis vs others), 0.971 (moderate steatosis vs others), 0.981 (severe steatosis vs others), 0.985 (any severity vs normal), and 0.996 (moderate-to-severe steatosis/clinically abnormal vs normal-to-mild steatosis/clinically normal). CONCLUSION: Our deep learning models achieved comparable predictive performances to the most accurate, yet expensive, noninvasive diagnostic methods for fatty liver. Because of the discriminative ability, including for mild steatosis, significant impacts on clinical applications for fatty liver are expected. However, we need to overcome machine-dependent variation, motion artifacts, lacking of second confirmation from any other tools, and hospital-dependent regional bias.

Stool DNA test targeting methylated syndecan-2 (SDC2) as a noninvasive screening method for colorectal cancer.

Despite the steadily increasing worldwide incidence of colorectal cancer (CRC), an effective noninvasive approach for early detection of CRC is still under investigation. The guaiac-based fecal occult blood test (FOBT) and fecal immunochemical test (FIT) have gained popularity as noninvasive CRC screening tests owing to their convenience and relatively low costs. However, the FOBT and FIT have limited sensitivity and specificity. To develop a noninvasive tool for the detection of CRC, we investigated the sensitivity, specificity, and accuracy of a stool DNA test targeting methylated syndecan-2 (SDC2), which is frequently methylated in patients with CRC. The present study enrolled 62 patients diagnosed as having stage 0-IV CRC and 76 healthy participants between July 2018 and June 2019 from two institutions. Approximately 4.5 g of stool sample was collected from each participant for detection of human methylated SDC2 gene. In total, 48 of 62 (77.4%) patients with CRC showed positive results, whereas 67 out of 76 (88.2%) healthy participants showed negative results. The area under the curve of the receiver operating characteristic curve constructed was 0.872 for discrimination between patients with CRC and healthy individuals. The present study highlights the potential of the fecal methylated SDC2 test as a noninvasive detection method for CRC screening with a relatively favorable sensitivity of 77.4%, a specificity of 88.2% and a positive predictive value of 84.2% compared with other available fecal tests. Further multicenter clinical trials comprising subjects of varied ethnicities are required to validate this test for the mass screening of patients with CRC.