Model training method and electronic device

An electronic device, comprising:

• an input circuit, configured to obtain a training set, a validation set, and a test set, wherein the training set comprises a plurality of first human brain images identified as healthy, the validation set comprises a plurality of second human brain images identified as healthy, and the test set comprises a plurality of third human brain images identified as unhealthy;
• and
• a processor, coupled to the input circuit and configured to perform the following operations:
• establishing a brain age prediction model according to the training set, wherein the operation of establishing the brain age prediction model according to the training set further comprises:
• arranging an auto encoder, wherein the auto encoder comprises an encoder and a decoder;
• inputting the plurality of first human brain images into the auto encoder to adjust parameters of the encoder and the decoder until output whether a difference between images of the decoder and input images of the encoder are located within an image predetermined value;
• arranging the brain age prediction model, wherein the brain age prediction model comprises the encoder with the adjusted parameter and a plurality of fully connected layers;
• and
• inputting the plurality of first human brain images into the encoder with the adjusted parameter to obtain first compressed representation data and training the plurality of fully connected layers according to the first compressed representation data until whether a difference between the plurality of third predicted brain ages outputted by the brain age prediction model and actual ages of the plurality of first human brain images are located within the predetermined value respectively;
• adjusting at least one parameter in the brain age prediction model according to the validation set;
• inputting the plurality of third human brain images into the brain age prediction model with the adjusted at least one parameter to obtain a plurality of first predicted brain ages corresponding to the plurality of third human brain images respectively;
• determining whether the plurality of first predicted brain ages satisfy at least one first specific condition;
• and
• completing training of the brain age prediction model when the plurality of first predicted brain ages satisfy the at least one first specific condition, wherein the at least one first specific condition comprises whether a difference between the first predicted brain ages and actual brain ages are located within a predetermined value.