A5047486551- Gastric Cancer Management and Outcomes
- Esophageal Cancer Research and Treatment
- Colorectal Cancer Screening and Detection
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Helicobacter pylori-related gastroenterology studies
- Gastrointestinal Bleeding Diagnosis and Treatment
- Esophageal and GI Pathology
- AI in cancer detection
- Image Retrieval and Classification Techniques
- Gastrointestinal Tumor Research and Treatment
- Pancreatic and Hepatic Oncology Research
- Inflammatory Bowel Disease
- Brain Tumor Detection and Classification
- Mycobacterium research and diagnosis
- Ultrasound and Hyperthermia Applications
Toshima Hospital
2019-2020
RELX Group (Netherlands)
2019
The role of artificial intelligence in the diagnosis Helicobacter pylori gastritis based on endoscopic images has not been evaluated. We constructed a convolutional neural network (CNN), and evaluated its ability to diagnose H. infection.A 22-layer, deep CNN was pre-trained fine-tuned dataset 32,208 either positive or negative for (first CNN). Another trained using classified according 8 anatomical locations (secondary A separate test data set (11,481 from 397 patients) by CNN, 23...
Background and Aim Although small‐bowel angioectasia is reported as the most common cause of bleeding in patients frequently diagnosed by capsule endoscopy ( CE ) with obscure gastrointestinal bleeding, a computer‐aided detection method has not been established. We developed an artificial intelligence system deep learning that can automatically detect images. Methods trained convolutional neural network CNN based on Single Shot Multibox Detector using 2237 images angioectasia. assessed its...
Background and Aim To examine whether our convolutional neural network ( CNN ) system based on deep learning can reduce the reading time of endoscopists without oversight abnormalities in capsule‐endoscopy process. Methods Twenty videos entire small‐bowel capsule endoscopy procedure were prepared, each which included 0–5 lesions mucosal breaks (erosions or ulcerations). At another institute, two processes compared: (A) endoscopist‐alone readings (B) endoscopist after first screening by...
Background and aim: We recently reported the role of artificial intelligence in diagnosis Helicobacter pylori (H. pylori) gastritis on basis endoscopic images. However, that study included only H. pylori-positive -negative patients, excluding patients after pylori-eradication. In this study, we constructed a convolutional neural network (CNN) evaluated its ability to ascertain all infection statuses.Methods: A deep CNN was pre-trained fine-tuned dataset 98,564 images from 5236 (742...
Abstract Background and Aim Conventional endoscopy for the early detection of esophageal esophagogastric junctional adenocarcinoma (E/J cancer) is limited because lesions are asymptomatic, associated changes in mucosa subtle. There no reports on artificial intelligence (AI) diagnosis E/J cancer from Asian countries. Therefore, we aimed to develop a computerized image analysis system using deep learning cancers. Methods A total 1172 images 166 pathologically proven superficial cases 2271...
Stratifying gastric cancer (GC) risk and endoscopy findings in high-risk individuals may provide effective surveillance for GC. We developed a computerized image- analysis system endoscopic images to stratify the of GC.The was trained using taken during examinations with non-magnified white-light imaging. Patients were classified as (patients GC), moderate-risk current or past Helicobacter pylori infection atrophy), low-risk no history H. atrophy). After selection, 20,960, 17,404, 68,920...
OBJECTIVES: A superficial nonampullary duodenal epithelial tumor (SNADET) is defined as a mucosal or submucosal sporadic of the duodenum that does not arise from papilla Vater. SNADETs rarely metastasize to lymph nodes, and most can be treated endoscopically. However, are sometimes missed during esophagogastroduodenoscopic examination. In this study, we constructed convolutional neural network (CNN) evaluated its ability detect SNADETs. METHODS: deep CNN was pretrained fine-tuned using...