Image processing apparatus and image processing method

An image processing method, including:

• acquiring medical image data;
• acquiring, in relation to the medical image data, first region information representing a first region;
• acquiring a first inference result by a first inference processing of applying a first inference model to first medical image data based on the medical image data, and a second inference result by a second inference processing of applying a second inference model to second medical image data based on the medical image data;
• and
• acquiring, on the basis of the first region information, second region information that is a region satisfying a predetermined condition, from at least regions based on the first inference result or regions based on the second inference result, wherein
• a region extending from the first region to outside of the first region, the region being among the regions based on the first inference result, or a region extending from the first region to the outside of the first region, the region being among the regions based on the second inference result, is acquired as the second region information that is the region satisfying the predetermined condition.

An image processing apparatus comprising processing circuitry configured to

• acquire medical image data;
• acquire, in relation to the medical image data, first region information representing a first region in a subject;
• acquire a first inference result that is a result of first inference processing using a first inference model for first medical image data based on the medical image data, the first inference model having been trained using training data corresponding to a head region of a subject;
• acquire a second inference result that is a result of second inference processing using a second inference model for second medical image data based on the medical image data, the second inference model having been trained using training data including at least training data corresponding to a region of the whole body including a head of a subject or training data corresponding to a region of the whole body excluding the head of the subject;
• and
• acquire an inference result for the medical image data by integrating the first inference result and the second inference result with each other on the basis of the first region information, wherein
• in a case where a region is:
• a region extending from a region corresponding to the first region information to outside of the region corresponding to the first region information, the region being among regions based on the first inference result;
• or a region extending from the region corresponding to the first region information to the outside of the region corresponding to the first region information, the region being among regions based on the second inference result, the processing circuitry is configured to integrate that region, as a region satisfying a predetermined condition, with the inference result for the medical image data.