Diagnosis support method, diagnosis support system, diagnosis support program, and computer-readable recording medium storing this diagnosis support program
PROBLEM TO BE SOLVED: To provide a method for supporting diagnosis of a disease by an endoscopic image of a digestive organ using a convolutional neural network (CNN). A diagnosis support method for a disease by an endoscopic image of a digestive organ using CNN according to the present invention corresponds to a first endoscopic image of the digestive organ and the first endoscopic image. Training CNN using at least one definitive diagnostic result of information corresponding to the positive or negative of the disease of the digestive organs, past disease, the level of severity, or the imaged site. The determined CNN is based on the second endoscopic image of the digestive system, the positive and/or negative probability of the disease of the digestive system, the probability of past disease, the level of severity of the disease, and the depth of the disease. At least one of the degree (infiltration depth) or the probability corresponding to the imaged site is output. [Selection diagram] Fig. 7【課題】畳み込みニューラルネットワーク（ＣＮＮ）を用いた消化器官の内視鏡画像による疾患の診断支援方法等を提供する。【解決手段】本発明のＣＮＮを用いた消化器官の内視鏡画像による疾患の診断支援方法は、前記消化器官の第１の内視鏡画像と、前記第１の内視鏡画像に対応する、前記消化器官の前記疾患の陽性又は陰性、過去の疾患、重症度のレベル、もしくは、撮像された部位に対応する情報の少なくとも１つの確定診断結果と、を用いてＣＮＮを訓練し、前記訓練されたＣＮＮは、消化器官の第２の内視鏡画像に基いて、当該消化器官の疾患の陽性及び／又は陰性の確率、過去の疾患の確率、疾患の重症度のレベル、疾患の深達度（浸潤深さ）、又は、撮像された部位に対応する確率の少なくとも１つを出力する。【選択図】図７
