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 classification of AMD and a second loss function value corresponding to a second classification of AMD, the first classification corresponds to a first group, and the second classification corresponds to one of the first group and a second group. The first loss function value is updated according to the second loss function value and a group penalty weight in response to the second classification corresponding to the second group 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 classification of the age-related macular degeneration and a second loss function value corresponding to a second classification of the age-related macular degeneration, the first classification corresponds to a first group, and the second classification corresponds to one of the first group and a second group, wherein the first classification and the second classification respectively correspond to different stages of the age-related macular degeneration;
generate a first penalty weight based on a first stage difference between the first classification and the second classification, wherein the first penalty weight is proportional to the stage difference;
update the first loss function value according to the second loss function value, the first penalty weight, and a group penalty weight in response to the second classification corresponding to the second group, 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 processor is further configured to:
update the first loss function value according to the second loss function value in response to the second classification corresponding to the first group, so as to generate the updated loss function vector.
3. The electronic device according to claim 1 , wherein the loss function vector further comprises a third loss function value corresponding to a third classification of the age-related macular degeneration, wherein the processor is further configured to:
generate a second penalty weight based on a second stage difference between the first classification and the third classification; 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.
4. The electronic device according to claim 3 , wherein the third classification corresponds to one of the first group and the second group, wherein the processor is further configured to:
update the first loss function value according to the third loss function value and the second penalty weight in response to the third classification corresponding to the first group, so as to generate the updated loss function vector; and
update the first loss function value according to the third loss function value, the second penalty weight, and the group penalty weight in response to the third classification corresponding to the second group, so as to generate the updated loss function vector.
5. The electronic device according to claim 3 , wherein the second stage difference is greater than the first stage difference, and the second penalty weight is greater than the first penalty weight.
6. The electronic device according to claim 1 , wherein the training data further comprises a fundus image annotated with an age-related macular degeneration stage, and the loss function vector corresponds to a binary cross entropy function.
7. The electronic device according to claim 1 , wherein the processor calculates a product of the second loss function value and the group penalty weight, so as to generate the updated loss function vector.
8. 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 classification of the age-related macular degeneration and a second loss function value corresponding to a second classification of the age-related macular degeneration, the first classification corresponds to a first group, and the second classification corresponds to one of the first group and a second group, wherein the first classification and the second classification respectively corresponding to different stages of the age-related macular degeneration;
generating a first penalty weight based on a first stage difference between the first classification and the second classification, wherein the first penalty weight is proportional to the stage difference;
updating the first loss function value according to the second loss function value, the first penalty weight, and a group penalty weight in response to the second classification corresponding to the second group, so as to generate an updated loss function vector; and
training the classification model according to the updated loss function vector.