Disclosed are a system and method which enable a diagnosis of a predetermined disease (for example, prostate cancer), when an image of biological tissue is input, by learning by means of a neural network and using the learned neural network, and visualize so as to accurately locate a tissue part which is diagnosed to be diseased. According to an aspect of the present invention, provided is a system for disease diagnosis which is implemented in a system comprising a processor and a storage device for storing a neural network and in which a slide which is a biometric image and the neural network are used. The system for diagnosis comprises: a patch neural network for generating a patch-level diagnostic result of whether or not a disease is present in each of predetermined patches formed by dividing a slide into a predetermined size; a heat map generation module for generating a patch-level heat map image corresponding to the slide on the basis of the patch diagnostic results of the respective multiple patches comprised in the slide; a tissue mask generation module for generating a tissue mask image corresponding to the slide on the basis of a hue-saturation-value (HSV) model corresponding to the slide; and a visualization module for generating a disease diagnostic visualization image corresponding to the slide on the basis of the patch-level heat map image and the tissue mask image.Système et procédé qui permettent un diagnostic d'une maladie prédéfinie (par exemple, un cancer de la prostate), lorsqu'une image de tissu biologique est entrée, par apprentissage à l'aide d'un réseau neuronal et par utilisation du réseau neuronal appris, et visualisent de façon à localiser avec précision une partie de tissu qui est diagnostiquée comme étant malade. Selon un aspect de la présente invention, l'invention concerne un système de diagnostic de maladie qui est mis en oeuvre dans un système comprenant un processeur et un dispositif de stockage pour stocker un réseau neuronal et d