Device and method of medical image regression for the diagnosis of dementia

A technology related to a medical image regression analysis device and method for diagnosing dementia is disclosed. The medical image regression analysis device for diagnosing dementia includes: a feature extraction unit which extracts the feature map necessary for disease diagnosis from the input m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ABDULLAH AL WALID, YUN, IL DONG
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A technology related to a medical image regression analysis device and method for diagnosing dementia is disclosed. The medical image regression analysis device for diagnosing dementia includes: a feature extraction unit which extracts the feature map necessary for disease diagnosis from the input medical image; a medical information determination unit which determines the medical information value of the medical image using the feature map extracted from the feature extraction unit; and a deep mapping unit which receives the medical information value output from the medical information determination unit and outputs the corresponding diagnosis result value. The feature extraction unit and the medical information determination unit include an artificial neural network whose parameters are learned to optimize the objective function, including the correlation loss function. Compared to conventional diagnostic devices, a more accurate diagnosis of dementia can be made. 치매 진단을 위한 의료 영상 회귀분석 장치 및 방법에 관한 기술이 개시된다. 치매 진단을 위한 의료 영상 회귀분석 장치는, 입력받은 의료 영상에서 질병진단에 필요한 특징맵을 추출하는 특징추출부와 특징추출부에서 추출한 특징맵을 이용하여 의료 영상의 의료정보값을 결정하는 의료정보결정부와 의료정보결정부에서 출력된 의료정보값을 입력받아서 대응하는 진단결과값을 출력하는 심층매핑부를 포함한다. 특징추출부와 의료정보결정부는 상관관계 손실함수를 포함하는 목적함수를 최적화 시키도록 매개변수가 학습된 인공신경망을 포함하여, 종래의 진단 장치에 비해 보다 정확한 치매 진단을 할 수 있다.