CPC G06T 7/0012 (2013.01) [A61B 5/02 (2013.01); A61B 5/4842 (2013.01); A61B 5/7275 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 40/18 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30041 (2013.01); G06T 2207/30048 (2013.01); G06T 2207/30204 (2013.01); G06V 40/14 (2022.01)] | 27 Claims |
1. A diagnosis assistance method, comprising:
obtaining a retinal image of a retina of a testee;
obtaining renal failure diagnosis assistance information for diagnosing a renal failure of the testee based on the retinal image and a renal failure diagnosis assistance deep neural network model, the renal failure diagnosis assistance deep neural network model storing correlations between retinal images and renal failure diagnosis assistance information and including at least one convolution neural network layer; and
outputting the renal failure diagnosis assistance information of the testee,
wherein the renal failure diagnosis assistance information includes at least one of (i) grade information which includes a grade selected from a plurality of grades indicating an extent of risk of the renal failure, (ii) score information for determining a risk of the renal failure and (iii) risk information which indicates whether the testee is included in a risk group for the renal failure or not,
wherein the outputting the renal failure diagnosis assistant information of the testee, further comprises, outputting instruction information determined based on the renal failure diagnosis assistance information,
wherein the instruction information is determined based on a pre-stored renal failure diagnosis assistant information-instruction information relation, and
wherein the renal failure diagnosis assistant information-instruction information relation includes a possible medical treatment for the testee corresponding to the renal failure diagnosis assistant information.
|