Mascarenhas Miguel, Mendes Francisco, Ribeiro Tiago, Afonso João, Marílio Cardoso Pedro, Martins Miguel, Cardoso Hélder, Andrade Patrícia, Ferreira João, Mascarenhas Saraiva Miguel, Macedo Guilherme
Department of Gastroenterology, Precision Medicine Unit, São João University Hospital, Porto, Portugal.
WGO Gastroenterology and Hepatology Training Center, Porto, Portugal.
GE Port J Gastroenterol. 2024 Aug 21;31(6):408-418. doi: 10.1159/000539837. eCollection 2024 Dec.
Capsule endoscopy (CE) is a minimally invasive exam suitable of panendoscopic evaluation of the gastrointestinal (GI) tract. Nevertheless, CE is time-consuming with suboptimal diagnostic yield in the upper GI tract. Convolutional neural networks (CNN) are human brain architecture-based models suitable for image analysis. However, there is no study about their role in capsule panendoscopy.
Our group developed an artificial intelligence (AI) model for panendoscopic automatic detection of pleomorphic lesions (namely vascular lesions, protuberant lesions, hematic residues, ulcers, and erosions). 355,110 images (6,977 esophageal, 12,918 gastric, 258,443 small bowel, 76,772 colonic) from eight different CE and colon CE (CCE) devices were divided into a training and validation dataset in a patient split design. The model classification was compared to three CE experts' classification. The model's performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and area under the precision-recall curve.
The binary esophagus CNN had a diagnostic accuracy for pleomorphic lesions of 83.6%. The binary gastric CNN identified pleomorphic lesions with a 96.6% accuracy. The undenary small bowel CNN distinguished pleomorphic lesions with different hemorrhagic potentials with 97.6% accuracy. The trinary colonic CNN (detection and differentiation of normal mucosa, pleomorphic lesions, and hematic residues) had 94.9% global accuracy.
DISCUSSION/CONCLUSION: We developed the first AI model for panendoscopic automatic detection of pleomorphic lesions in both CE and CCE from multiple brands, solving a critical interoperability technological challenge. Deep learning-based tools may change the landscape of minimally invasive capsule panendoscopy.
胶囊内镜检查（CE）是一种微创检查，适用于对胃肠道（GI）进行全内镜评估。然而，CE耗时较长，对上消化道的诊断率欠佳。卷积神经网络（CNN）是基于人类大脑结构的模型，适用于图像分析。然而，尚无关于其在胶囊全内镜检查中作用的研究。
我们团队开发了一种人工智能（AI）模型，用于全内镜自动检测多形性病变（即血管病变、隆起性病变、血性残留物、溃疡和糜烂）。来自八个不同的CE和结肠CE（CCE）设备的355,110张图像（6,977张食管图像、12,918张胃图像、258,443张小肠图像、76,772张结肠图像）在患者分割设计中被分为训练和验证数据集。将该模型的分类与三位CE专家的分类进行比较。通过其灵敏度、特异性、准确性、阳性预测值、阴性预测值和精确召回曲线下面积来评估该模型的性能。
二元食管CNN对多形性病变的诊断准确率为83.6%。二元胃CNN识别多形性病变的准确率为96.6%。十一元小肠CNN区分具有不同出血潜能的多形性病变的准确率为97.6%。三元结肠CNN（正常黏膜、多形性病变和血性残留物的检测与区分）的整体准确率为94.9%。
讨论/结论：我们开发了首个用于从多个品牌的CE和CCE中全内镜自动检测多形性病变的AI模型，解决了关键的互操作性技术挑战。基于深度学习的工具可能会改变微创胶囊全内镜检查的局面。
