Ribeiro Tiago, Saraiva Miguel Mascarenhas, Ferreira João P S, Cardoso Hélder, Afonso João, Andrade Patrícia, Parente Marco, Jorge Renato Natal, Macedo Guilherme
Department of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro (Tiago Ribeiro, Miguel Mascarenhas Saraiva, Hélder Cardoso, João Afonso, Patrícia Andrade, Guilherme Macedo).
WGO Gastroenterology and Hepatology Training Center (Tiago Ribeiro, Miguel Mascarenhas Saraiva, Hélder Cardoso, João Afonso, Patrícia Andrade, Guilherme Macedo).
Ann Gastroenterol. 2021 Nov-Dec;34(6):820-828. doi: 10.20524/aog.2021.0653. Epub 2021 Jul 2.
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.
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.
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.
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.
胶囊内镜检查（CE）是评估不明原因胃肠道出血患者的一线检查方法。在这些患者中经常发现一系列具有不同出血风险的小肠血管病变。然而，解读CE检查耗时且容易出错。卷积神经网络（CNN）是在图像分析方面具有高性能水平的人工智能工具。本研究旨在开发一种基于CNN的模型，用于识别和区分CE图像中具有不同出血风险的血管病变。
CNN的开发基于CE图像数据库。该数据库包括正常小肠黏膜、红点以及血管扩张/静脉曲张的图像。出血风险通过索林分类法进行评估。为了开发CNN，最终提取了11588张图像（9525张正常黏膜、1026张红点以及1037张血管扩张/静脉曲张）。创建了两个图像数据集用于CNN训练和测试。
该网络检测血管病变的敏感性为91.8%，特异性为95.9%，在94.4%的病例中提供了准确的预测。特别是，CNN检测红点的敏感性和特异性分别为97.1%和95.3%。检测血管扩张/静脉曲张的敏感性为94.1%，特异性为95.1%。CNN的帧读取速率为145帧/秒。
所开发的算法是首个基于CNN的模型，能够准确检测和区分具有不同出血风险的肠道血管病变。CNN辅助的CE解读可能会改善这些病变的诊断以及整体CE效率。
