Background: Capsule endoscopy (CE) is the first line for evaluation of patients with obscure gastrointestinal bleeding. A wide range of small intestinal vascular lesions with different hemorrhagic potential are frequently found in these patients. Nevertheless, reading CE exams is time-consuming and prone to errors. Convolutional neural networks (CNN) are artificial intelligence tools with high performance levels in image analysis. This study aimed to develop a CNN-based model for identification and differentiation of vascular lesions with distinct hemorrhagic potential in CE images.
Methods: The development of the CNN was based on a database of CE images. This database included images of normal small intestinal mucosa, red spots, and angiectasia/varices. The hemorrhagic risk was assessed by Saurin's classification. For CNN development, 11,588 images (9525 normal mucosa, 1026 red spots, and 1037 angiectasia/varices) were ultimately extracted. Two image datasets were created for CNN training and testing.
Results: The network was 91.8% sensitive and 95.9% specific for detection of vascular lesions, providing accurate predictions in 94.4% of cases. In particular, the CNN had a sensitivity and specificity of 97.1% and 95.3%, respectively, for detection of red spots. Detection of angiectasia/varices occurred with a sensitivity of 94.1% and a specificity of 95.1%. The CNN had a frame reading rate of 145 frames/sec.
Conclusions: The developed algorithm is the first CNN-based model to accurately detect and distinguish enteric vascular lesions with different hemorrhagic risk. CNN-assisted CE reading may improve the diagnosis of these lesions and overall CE efficiency.
Keywords: Capsule endoscopy; artificial intelligence; convolutional neural network; gastrointestinal bleeding; vascular lesions.
Copyright: © Hellenic Society of Gastroenterology.