| CPC G06T 7/0012 (2013.01) [G06F 40/143 (2020.01); G06N 3/08 (2013.01); G06T 7/13 (2017.01); G06T 7/136 (2017.01); G06T 7/90 (2017.01); G16H 15/00 (2018.01); G06T 2207/20021 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30081 (2013.01); G06T 2207/30096 (2013.01)] | 16 Claims |
|
1. A diagnosis result generation system comprising:
a marking information generation module configured to generate marking information expressing a result of diagnosing whether a disease exists in biometric tissue provided on a slide of which a biometric image is obtained therefrom, wherein the marking information includes disease state information of each pixel of the biometric tissue provided on the slide;
a contour extraction module configured to extract at least one contour from the marking information;
a machine-readable and human-readable generation module configured to generate a machine-readable and human-readable document including outer line information of each of the at least one extracted contour;
a diagnosis system configured to output a result of diagnosing whether a disease exists using the slide, the neural network, and the machine-readable and human-readable document generated by the machine-readable and human-readable generation module; and
a diagnosis result determination system configured to read and analyze the result of diagnosing output by the diagnosis system and to determine a diagnosis of the patient accordingly,
wherein the marking information generation module generates the marking information on the basis of the diagnosis result output from the diagnosis system,
wherein the diagnosis system includes:
a patch neural network configured to generate a patch-level diagnosis result indicating whether a disease exists in each of predetermined patches generated by dividing the biometric image obtained from the slide in a predetermined size;
a heatmap generation module configured to generate a patch-level heatmap image corresponding to the slide on the basis of the patch-level diagnosis result of each of a plurality of patches included in the biometric image obtained from the slide;
a tissue mask generation module configured to generate a tissue mask image corresponding to the biometric image obtained from the slide on the basis of a Hue-Saturation-Value (HSV) model corresponding to the biometric image obtained from the slide; and
a diagnosis result visualization module configured to generate a diagnosis result of the slide on the basis of the patch-level heatmap image and the tissue mask image.
|