Open the doors to panendoscopy. That is the motto of the article published by Ribeiro et al, “Artificial intelligence and colon capsule endoscopy: Automatic detection of ulcers and erosions using a convolutional neural network”, published on the high impact Journal of Gastroenterology and Hepatology. Panendoscopic methods, including techniques of colon capsule endoscopy provide a breakthrough in the care of patients with gastrointestinal diseases, particularly those afflicted by inflammatory bowel disease. In this study, our group reports top tier results of algorithm, which achieved a sensitivity of 97%, a specificity of 100% and an overall accuracy of 100%. These results are potentiated by high frame reading capacity (90 frames per second), making this algorithm suitable for application to full-length videos.
This study consolidates the ever-growing ambition of our group to provide accurate patient and doctor-friendly alternatives to conventional endoscopic methods, particularly for patients who require regular endoscopic follow up. AI is changing the landscape in gastrointestinal endoscopy.
You can find the article here.
In press // J Gastroenterology Hepatol 2022 37(12):2282-2288 // Dec 2022