Eye care device and method for assessing and predicting dementia

An eye care device, comprising:

• a retinal layer thickness detection system, comprising:
• an image capturing unit configured to capture a target optical coherence tomographic image of a subject;
• and
• a processor electrically connected to the image capturing unit and storing a program, wherein the program detects a retinal layer thickness of the subject when the program is executed by the processor, and the program comprises:
• a reference database obtaining module configured to obtain a reference database, wherein the reference database comprises a plurality of reference optical coherence tomographic images;
• a reference image pre-processing module configured to duplicate each of the plurality of reference optical coherence tomographic images and mark a cell segmentation line of each of retinal layers, so as to obtain a plurality of control optical coherence tomographic images;
• a reference feature selecting module configured to analyze each of the plurality of reference optical coherence tomographic images, and obtain at least one reference image feature from each of the plurality of reference optical coherence tomographic images, so as to obtain a plurality of the reference image features;
• a training module configured to train with the plurality of the reference image features through a convolution neural network learning classifier to reach convergence, so as to obtain a retinal layer thickness detection model;
• a confirming module configured to output a plurality of marked optical coherence tomographic images by the retinal layer thickness detection model, and to compare each of the plurality of marked optical coherence tomographic images with corresponding one of the plurality of control optical coherence tomographic images, so as to confirm an accuracy of the retinal layer thickness detection model;
• a target feature selecting module configured to analyze the target optical coherence tomographic images, and obtain at least one target image feature;
• a marking module configured to analyze the target image feature by the retinal layer thickness detection model, so as to output a marked target optical coherence tomographic image;
• and
• a calculating module configured to calculate a cell thickness of each of the retinal layers in the marked target optical coherence tomographic image, and to compare the cell thickness of each of the retinal layers with a clinical test data of the subject by a regression analysis model, so as to calculate an assessing grade representing a possibility of the subject having dementia;
• and
• an electronic device connected to the retinal layer thickness detection system through telecommunication;
• wherein the clinical test data comprises a computed tomographic image, a nuclear magnetic resonance image and a blood test value of the subject.