Electronic device and method of training classification model for age-related macular degeneration
An electronic device and a method of training a classification model for age-related macular degeneration (AMD) are provided. The method includes the following steps. Training data is obtained. A loss function vector corresponding to the training data is calculated based on a machine learning algorithm, in which the loss function vector includes a first loss function value corresponding to a first stage of AMD and a second loss function value corresponding to a second stage of AMD. A first penalty weight is generated according to a stage difference between the first stage and the second stage. The first loss function value is updated according to the second loss function value and the first penalty weight, so as to generate an updated loss function vector. The classification model is trained according to the updated loss function vector.
1. An electronic device for training a classification model for age-related macular degeneration, comprising:
a transceiver; and
a processor, coupled to the transceiver, wherein the processor is configured to:
obtaining training data through the transceiver;
calculate a loss function vector corresponding to the training data based on a machine learning algorithm, wherein the loss function vector comprises a first loss function value corresponding to a first stage of the age-related macular degeneration and a second loss function value corresponding to a second stage of the age-related macular degeneration;
generate a first penalty weight according to a stage difference between the first stage and the second stage, wherein the first penalty weight is proportional to the stage difference;
update the first loss function value according to the second loss function value and the first penalty weight, so as to generate an updated loss function vector; and
train the classification model according to the updated loss function vector.
2. The electronic device according to claim 1 , wherein the loss function vector further comprises a third loss function value corresponding to a third stage of the age-related macular degeneration, wherein the processor is further configured to:
generate a second penalty weight according to a second stage difference between the first stage and the third stage; and
update the first loss function value according to the third loss function value and the second penalty weight, so as to generate the updated loss function vector.
3. The electronic device according to claim 2 , wherein the second stage difference is greater than the stage difference, and the second penalty weight is greater than the first penalty weight.
4. The electronic device according to claim 2 , wherein an updated loss function value in the update loss function vector comprises the second loss function value and a first product of the first penalty weight.
5. The electronic device according to claim 4 , wherein the updated loss function value further comprises the third loss function and a second product of the second penalty weight.
6. The electronic device according to claim 1 , wherein the training data comprises a fundus image annotated with an age-related macular degeneration stage.
7. The electronic device according to claim 6 , wherein the loss function vector corresponds to a binary cross entropy function.
8. The electronic device according to claim 7 , wherein the processor calculates a normalized probability vector corresponding to the training data based on the machine learning algorithm, generates an one-hot encoding vector corresponding to the age-related macular degeneration stage according to the annotation of the fundus image, and inputs the normalized probability vector and the one-hot encoding vector into the binary cross-entropy function, so as to generate the loss function vector.
9. A method of training a classification model for age-related macular degeneration, comprising:
obtaining training data;
calculating a loss function vector corresponding to the training data based on a machine learning algorithm, wherein the loss function vector comprises a first loss function value corresponding to a first stage of the age-related macular degeneration and a second loss function value corresponding to a second stage of the age-related macular degeneration;
generating a first penalty weight according to a stage difference between the first stage and the second stage, wherein the first penalty weight is proportional to the stage difference;
updating the first loss function value according to the second loss function value and the first penalty weight, so as to generate an updated loss function vector; and
training the classification model according to the updated loss function vector.