Automatic detection and differentiation of small intestine lesions in capsule endoscopy

• Main Authors: AFONSO, JOU O PEDRO LIMA, NATAL JORGE RENATO MANUEL, MACEDO MANUEL GUILHERME GONCALVES DE, CASAL CARDOZO ELDER MANUEL, DA QUINTA COSTA DE MASCARENHAS, MIGUEL, JOS, PARENT MARCO PAUL LAGES, ANDRADE ANA PATRICIA RIBEIRO, FERREIRA, JOU O PEDRO SOUZA
• Format: Patent
• Language: Chinese; English
• Published: 29.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention relates to a computer-implemented method capable of automatically characterizing a small intestine lesion in a capsule endoscopy image, comprising detecting small intestine lesions in a medical image by classifying pixels as lesions or non-lesions using a convolutional image feature extraction step followed by an architecture classified and indexed into one or more categories. 本发明涉及一种能够自动表征胶囊式内窥镜检查图像中的小肠病变的计算机实现的方法，包括通过使用卷积图像特征提取步骤、随后是分类和索引到一个或多个类别中的体系结构将像素分类为病变或非病变来检测医学图像中的小肠病变。