Medical image processing apparatus, medical image processing method, and X-ray CT apparatus

A medical image processing method comprising:

• acquiring first projection data obtained by performing non-contrast scanning on a first imaging region of a subject, and second projection data obtained by performing contrast scanning on the first imaging region;
• extracting third projection data corresponding to a second imaging region in the first imaging region from the second projection data;
• reconstructing a first reconstruction image based on the first projection data, a second reconstruction image based on the second projection data, and a third reconstruction image based on a difference between the first projection data and the third projection data;
• and
• deriving the second reconstruction image as a processing result from the first projection data and the third projection data as processing targets, using a model trained with training data in which the first reconstruction image and the third reconstruction image are set to input data and the second reconstruction image is set to correct answer data.

An X-ray CT apparatus comprising processing circuitry configured to:

• acquire first projection data obtained by performing non-contrast scanning on a first imaging region of a subject, and second projection data obtained by performing contrast scanning on the first imaging region;
• extract third projection data corresponding to a second imaging region in the first imaging region from the second projection data;
• reconstruct a first reconstruction image based on the first projection data, a second reconstruction image based on the second projection data, and a third reconstruction image based on a difference between the first projection data and the third projection data;
• and
• derive the second reconstruction image as a processing result from the first projection data and the third projection data as processing targets, using a model trained with training data in which the first reconstruction image and the third reconstruction image are set to input data and the second reconstruction image is set to correct answer data.