Linkedin

Esophagogastroduodenoscopy (EGD) is the gold standard for diagnosis and follow up of gastric protruding lesions. Nevertheless, it is an invasive procedure, often not tolerated by patients. Capsule endoscopy (CE) has emerged as a minimally invasive, patient friendly alternative to EGD. The application of artificial intelligence (AI) for automatic analysis of CE images has provided promising results. Convolutional Neural Networks (CNN) are a multi-layer artificial intelligence architecture with high performance levels for image analysis. The application of these automated algorithms for detection of gastric protruding lesions in CE images has not been explored. This pilot study aimed to develop and test a CNN for automatic detection gastric protruding lesions in CE images.

Material and Methods:A CNN was developed based on a total of 890 CE images (180 images containing gastric protruding lesions and 710 showing normal mucosa). Training (80%, n=712) and validation (20%, n=178)) datasets were constructed. The output provided by the network was compared to a consensus classification provided by two gastroenterologists with experience in CE. The sensitivity, specificity, accuracy, positive predictive and negative predictive values (PPV and NPV, respectively) and area under the curve (AUC) were calculated.Results: After optimizing the architecture of the network, our model automatically detected gastric protruding lesions with an accuracy of 93.8%. Our CNN had a sensitivity, specificity, PPV and NPV of 83.3%, 96.5%, 85.7%, and 95.8%, respectively. The CNN analyzed the validation dataset in 3 seconds, at a rate of approximately 56 frames per second.Conclusions: Our pioneerCNN detected gastric protruding lesions with high accuracy. The development of these systems may boost the diagnostic efficiency of CE for the detection non-small bowel lesions, thus expanding the indications for its use.

 
 

Pesquisa

Ano

Título

Autores

Termos

Tipo de Comunicação