A computer-readable recording medium that stores a disease diagnosis support method, a diagnosis support system, a diagnosis support program, and this diagnosis support program using endoscopic images of the digestive organs.

摘要

The method for supporting the diagnosis of a disease by the endoscopic image of the digestive organ using the convolutional neural network (CNN) of the embodiment of the present invention includes the first endoscopic image of the digestive organ and the first endoscopic image. The CNN was trained using at least one definitive diagnostic result of information corresponding to the positive or negative of the disease in the digestive organs, or the level of severity, corresponding to the endoscopic image, and the trained CNN Corresponds to the positive and / or negative probability of the disease in the digestive organ, the level of severity of the disease, or the invasion depth of the disease, based on the second endoscopic image of the digestive organ. Output at least one of the probabilities of doing so. According to the present embodiment, the subject's probability of positive and / or negative gastrointestinal disease, the level of severity of the disease, and the depth of invasion of the disease in a short period of time with substantially comparable accuracy to an endoscopist. Etc., and it becomes possible to select subjects who must make a definitive diagnosis separately in a short time.