Method and apparatus for training a deep learning based model for harmonic imaging

A method for training a model to perform harmonic imaging using ultrasound signals, the method comprising:

• inputting first ultrasound data into a neural network model configured to generate and output second ultrasound data;
• determining a first error by applying a first filter to a difference between the second ultrasound data and target ultrasound data;
• determining a second error by applying a second filter, different from the first filter, to the difference between the second ultrasound data and the target ultrasound data;
• determining a loss value based on the determined first error and the determined second error;
• and
• updating parameters of the neural network model based on the determined loss value to generate a trained neural network model, wherein
• the neural network model is a convolutional neural network (CNN).

An apparatus for performing harmonic imaging using ultrasound signals, the apparatus comprising:

• processing circuitry configured to
• obtain first ultrasound data,
• input the obtained first ultrasound data into a trained neural network to obtain second ultrasound data, wherein the trained neural network was trained using training input data, corresponding target data, and a loss function, the loss function calculating a loss value by
• determining a first error by applying a first filter to a difference between the output ultrasound data output from the neural network in response to inputting the training input data and the target ultrasound data,
• determining a second error by applying a second filter, different from the first filter, to the difference between the output ultrasound data and the target ultrasound data,
• determining the loss value using the loss function, which is a function of the determined first error and the determined second error, and
• updating parameters of the trained neural network based on the determined loss value, and
• output the second ultrasound data for displaying on a display, wherein
• the neural network model is a convolutional neural network (CNN).