Diagnosis assistance system and control method thereof

Abstract

The present invention relates to a diagnosis assistance system for assisting diagnosis for a plurality of diseases based on a fundus image, the diagnosis assistance system including: a fundus image obtaining unit configured to obtain a fundus image; a first processing unit configured to, for the fundus image, obtain a first result related to a first finding of a patient using a first neural network model, a second processing unit configured to, for the fundus image, obtain a second result related to a second finding of the patient using a second neural network model, a third processing unit configured to determine, on the basis of the first result and the second result, diagnostic information on the patient, and a diagnostic information output unit configured to provide the determined diagnostic information to a user.

What is claimed is: 
     
         1 . A diagnosis assistant device for assisting diagnosis of at least one clinical condition based on an eye image, comprising:
 a storage unit; and   at least one processor operably connected to the storage unit and configured to:
 obtain a result associated with the at least one clinical condition based on the eye image using a machine learning model, and 
 generate diagnosis assistant information based on the result. 
   
     
     
         2 . The diagnosis assistant device of  claim 1 ,
 wherein the result includes first result and second result,   wherein the first result is used to assist in diagnosing first clinical condition, and the second result is used to assist in diagnosing second clinical condition, and   wherein the first clinical condition and the second clinical condition are different clinical conditions each other.   
     
     
         3 . The diagnosis assistant device of  claim 2 ,
 wherein the first clinical condition is associated with an eye disease,   wherein the second clinical condition is associated with a systemic disease, and   wherein the systemic disease comprises at least one of hypertension, Alzheimer's disease, cytomegalovirus disease, stroke, arteriosclerosis or cardiovascular disease.   
     
     
         4 . The diagnosis assistant device of  claim 2 ,
 wherein the first clinical condition is associated with first systemic disease,   wherein the second clinical condition is associated with second systemic disease, and   wherein the first systemic disease or the second systemic disease comprises at least one of hypertension, Alzheimer's disease, cytomegalovirus disease, stroke, arteriosclerosis or cardiovascular disease.   
     
     
         5 . The diagnosis assistant device of  claim 2 ,
 wherein the machine learning model includes first machine learning model and second machine learning model, and   wherein the at least one processor is configured to obtain the first result based on the eye image using the first machine learning model and the second result based on the eye image using the second machine learning model.   
     
     
         6 . The diagnosis assistant device of  claim 1 , wherein the eye image includes at least one vessel of the eye. 
     
     
         7 . The diagnosis assistant device of  claim 1 , wherein the eye image includes a retinal image or a fundus image. 
     
     
         8 . The diagnosis assistant device of  claim 1 ,
 wherein the at least one processor is configured to obtain grade information including first grade or second grade based on the result,   wherein the first grade indicates a higher risk for the at least one clinical condition than the second grade, and   wherein the at least one processor is configured to provide guide information based on the obtained grade information.   
     
     
         9 . The diagnosis assistant device of  claim 8 ,
 wherein the at least one processor is configured to provide first guide information for treating the at least one clinical condition when the obtained grade information is the first grade.   
     
     
         10 . The diagnosis assistant device of  claim 8 ,
 wherein the at least one processor is configured to provide second guide information for future care plan for the at least one clinical condition when the obtained grade information is the second grade.   
     
     
         11 . The diagnosis assistant device of  claim 1 ,
 wherein the at least one processor is configured to obtain quality grade information of the eye image,   wherein the quality grade information includes first quality grade or second quality grade lower than the first quality grade, and   wherein the at least one processor is configured to provide the diagnosis assistant information when the obtained quality grade information is the first quality grade.   
     
     
         12 . The diagnosis assistant device of  claim 11 , wherein the diagnosis assistant information is not provided when the obtained quality grade information is the second quality grade. 
     
     
         13 . The diagnosis assistant device of  claim 11 , wherein the at least one processor is configured to require a new eye image when the obtained quality grade information is the second quality grade. 
     
     
         14 . The diagnosis assistant device of  claim 11 , wherein the at least one processor is configured to provide the diagnosis assistant information and the quality grade information. 
     
     
         15 . A method for assisting diagnosis of at least one clinical condition based on an eye image, the method comprising:
 obtaining a result associated with the at least one clinical condition based on the eye image using a machine learning model, and   generating diagnosis assistant information based on the result.   
     
     
         16 . The method of  claim 15 ,
 wherein the result includes first result and second result,   wherein the first result is used to assist in diagnosing first clinical condition, and the second result is used to assist in diagnosing second clinical condition, and   wherein the first clinical condition and the second clinical condition are different clinical conditions each other.   
     
     
         17 . The method of  claim 15 ,
 wherein the method further comprising obtaining grade information including first grade or second grade based on the result,   wherein the first grade indicates a higher risk for the at least one clinical condition than the second grade, and   wherein guide information is provided based on the obtained grade information.   
     
     
         18 . The method of  claim 15 ,
 wherein the method further comprising obtaining quality grade information of the eye image,   wherein the quality grade information includes first quality grade or second quality grade lower than the first quality grade, and   wherein the diagnosis assistant information is provided when the obtained quality grade information is the first quality grade.   
     
     
         19 . A non-transitory computer-readable recording medium storing instructions thereon, the instructions when executed by at least one processor cause the at least one processor to:
 obtain a result associated with at least one clinical condition based on an eye image using a machine learning model, and   generate diagnosis assistant information based on the result.