Deep learning assists detection of esophageal cancer and precursor lesions in a prospective, randomized controlled study.

Endoscopy is the primary modality for detecting asymptomatic esophageal squamous cell carcinoma (ESCC) and precancerous lesions. Improving detection rate remains challenging. We developed a system based on deep convolutional neural networks (CNNs) for detecting esophageal cancer and precancerous lesions [high-risk esophageal lesions (HrELs)] and validated its efficacy in improving HrEL detection rate in clinical practice (trial registration ChiCTR2100044126 at www.chictr.org.cn). Between April 2021 and March 2022, 3117 patients ≥50 years old were consecutively recruited from Taizhou Hospital, Zhejiang Province, and randomly assigned 1:1 to an experimental group (CNN-assisted endoscopy) or a control group (unassisted endoscopy) based on block randomization. The primary endpoint was the HrEL detection rate. In the intention-to-treat population, the HrEL detection rate [28 of 1556 (1.8%)] was significantly higher in the experimental group than in the control group [14 of 1561 (0.9%), P = 0.029], and the experimental group detection rate was twice that of the control group. Similar findings were observed between the experimental and control groups [28 of 1524 (1.9%) versus 13 of 1534 (0.9%), respectively; P = 0.021]. The system's sensitivity, specificity, and accuracy for detecting HrELs were 89.7, 98.5, and 98.2%, respectively. No adverse events occurred. The proposed system thus improved HrEL detection rate during endoscopy and was safe. Deep learning assistance may enhance early diagnosis and treatment of esophageal cancer and may become a useful tool for esophageal cancer screening.

Reactive Oxygen Species Induce Fatty Liver and Ischemia-Reperfusion Injury by Promoting Inflammation and Cell Death.

Liver transplantation is the ultimate method for treating end-stage liver disease. With the increasing prevalence of obesity, the number of patients with non-alcoholic fatty liver, a common cause of chronic liver disease, is on the rise and may become the main cause of liver transplantation in the future. With the increasing gap between the number of donor livers and patients waiting for liver transplantation and the increasing prevalence of non-alcoholic fatty liver, the proportion of steatosis livers among non-standard donor organs is also increasing. Ischemia-reperfusion injury has historically been the focus of attention in the liver transplantation process, and severe ischemia-reperfusion injury leads to adverse outcomes of liver transplantation. Studies have shown that the production of reactive oxygen species and subsequent oxidative stress play a key role in the pathogenesis of hepatic ischemia and reperfusion injury and non-alcoholic fatty liver. Furthermore, the sensitivity of fatty liver transplantation to ischemia-reperfusion injury has been suggested to be related to the production of reactive oxygen species (ROS) and oxidative stress. In ischemia-reperfusion injury, Kupffer cell and macrophage activation along with mitochondrial damage and the xanthine/xanthine oxidase system promote marked reactive oxygen species production and the inflammatory response and apoptosis, resulting in liver tissue injury. The increased levels of ROS and lipid peroxidation products, vicious circle of ROS and oxidative stress along with mitochondrial dysfunction promoted the progress of non-alcoholic fatty liver. In contrast to the non-fatty liver, a non-alcoholic fatty liver produces more reactive oxygen species and suffers more serious oxidative stress when subjected to ischemia-reperfusion injury. We herein review the effects of reactive oxygen species on ischemia-reperfusion injury and non-alcoholic fatty liver injury as well as highlight several treatment approaches.

Use of Artificial Intelligence to Improve the Quality Control of Gastrointestinal Endoscopy.

With the rapid development of science and technology, artificial intelligence (AI) systems are becoming ubiquitous, and their utility in gastroenteroscopy is beginning to be recognized. Digestive endoscopy is a conventional and reliable method of examining and diagnosing digestive tract diseases. However, with the increase in the number and types of endoscopy, problems such as a lack of skilled endoscopists and difference in the professional skill of doctors with different degrees of experience have become increasingly apparent. Most studies thus far have focused on using computers to detect and diagnose lesions, but improving the quality of endoscopic examination process itself is the basis for improving the detection rate and correctly diagnosing diseases. In the present study, we mainly reviewed the role of AI in monitoring systems, mainly through the endoscopic examination time, reducing the blind spot rate, improving the success rate for detecting high-risk lesions, evaluating intestinal preparation, increasing the detection rate of polyps, automatically collecting maps and writing reports. AI can even perform quality control evaluations for endoscopists, improve the detection rate of endoscopic lesions and reduce the burden on endoscopists.

[Trabecular bone micro-architecture in adolescent idiopathic scoliosis compared between concave and convex site of the facet joints].

OBJECTIVE: To evaluate the trabecular bone micro-structure from different sites of spine in adolescent idiopathic scoliosis patients. The target site consisted of the bilateral facet joints from apical vertebrae and from end vertebrae. METHODS: Nine AIS patients with mean age 14.9 years (range 12-17 years) and mean Cobb angle 56 degrees (ranged 48 degrees-84 degrees) were recruited into this study. Corrective surgery was indicated to these patients, and facet joint biopsies were collected during decortications for spinal fusion. Biopsy consents were obtained from patients. Bone specimens were fixed with routine histology procedures and scanned by micro computer tomography (muCT40, Scanco Medical, Switzerland). Ten pairs of facet joint were harvested from apical vertebrae and 12 pairs from end vertebrae. Three-dimensional reconstructed images with the resolution of 20 microm were achieved for histomorphometric analysis. RESULTS: The values of BV/TV (0.268 vs. 0.354, P < 0.05), TbTh (0.20 vs. 0.24, P < 0.05), TbSP (0.66 vs. 0.56, P < 0.05) and BS/BV (12.7 vs. 10.4, P < 0.05) between convex and concave side at the apex area were significantly different. No difference was found in any structural parameters between left and right side at end area, and upper thoracic (T5, 6) and thoracolumbar (T12, L1). CONCLUSION: Due to asymmetric compression and tension shared between convex and concave side, more bone and thicker and more profound trabecular bones are observed in the concave side than in the convex side, which seems to resist the progression of spinal curvature. This finding suggests that the provocative factors which cause the progression of the curve in certain patients may not lie in the bone component of spine.