Automated detection of small bowel lesions based on capsule endoscopy using deep learning algorithm.

BACKGROUND: In order to overcome the challenges of lesion detection in capsule endoscopy (CE), we improved the YOLOv5-based deep learning algorithm and established the CE-YOLOv5 algorithm to identify small bowel lesions captured by CE. METHODS: A total of 124,678 typical abnormal images from 1,452 patients were enrolled to train the CE-YOLOv5 model. Then 298 patients with suspected small bowel lesions detected by CE were prospectively enrolled in the testing phase of the study. Small bowel images and videos from the above 298 patients were interpreted by the experts, non-experts and CE-YOLOv5, respectively. RESULTS: The sensitivity of CE-YOLOv5 in diagnosing vascular lesions, ulcerated/erosive lesions, protruding lesions, parasite, diverticulum, active bleeding and villous lesions based on CE videos was 91.9 %, 92.2 %, 91.4 %, 93.1 %, 93.3 %, 95.1 %, and 100 % respectively. Furthermore, CE-YOLOv5 achieved specificity and accuracy of more than 90 % for all lesions. Compared with experts, the CE-YOLOv5 showed comparable overall sensitivity, specificity and accuracy (all P > 0.05). Compared with non-experts, the CE-YOLOv5 showed significantly higher overall sensitivity (P < 0.0001) and overall accuracy (P < 0.0001), and a moderately higher overall specificity (P = 0.0351). Furthermore, the time for AI-reading (5.62 ± 2.81 min) was significantly shorter than that for the other two groups (both P < 0.0001). CONCLUSIONS: CE-YOLOv5 diagnosed small bowel lesions in CE videos with high sensitivity, specificity and accuracy, providing a reliable approach for automated lesion detection in real-world clinical practice.

Facile Preparation of a Superhydrophobic iPP Microporous Membrane with Micron-Submicron Hierarchical Structures for Membrane Distillation.

A facile method combining micro-molding with thermally-induced phase separation (TIPS) to prepare superhydrophobic isotacticpolypropylene (iPP) microporous membranes with micron-submicron hierarchical structures is proposed in this paper. In this study, the hydrophobicity of the membrane was controlled by changing the size of micro-structures on the micro-structured mold and the temperature of the cooling bath. The best superhydrophobicity was achieved with a high water contact angle (WCA) of 161° and roll-off angle of 2°, which was similar to the lotus effect. The permeability of the membrane was greatly improved and the mechanical properties were maintained. The membrane prepared by the new method and subjected to 60h vacuum membrane distillation (VMD) was compared with a conventional iPP membrane prepared via the TIPS process. The flux of the former membrane was 31.2 kg/m2·h, and salt rejection was always higher than 99.95%, which was obviously higher than that of the latter membrane. The deposition of surface fouling on the former membrane was less and loose, and that of the latter membrane was greater and steady, which was attributed to the micron-submicron hierarchical structure of the former and the single submicron-structure of the latter. Additionally, the new method is expected to become a feasible and economical method for producing an ideal membrane for membrane distillation (MD) on a large scale.