Method of, and apparatus for, segmentation of structures in medical images

A method for segmentation of medical image data, comprising:

• obtaining a first set of image data representing a first medical image and a second set of image data, different from the first set of image data, representing a second medical image, wherein at least one structure is represented in both the first set of image data and the second set of image data;
• determining a classification of a first type of feature from the first set of image data, the first type of feature comprising at least one of a calcification and a stent, the first set of image data comprising non-contrast data;
• determining a classification of a second type of feature from the second set of image data, the second type of feature comprising a vessel tissue type, and the second set of image data comprising at least one of subtraction data and contrast data;
• and
• identifying image data representing the structure in dependence on both the classification of the first type of feature from the first set of image data and the classification of the second type of feature from the second set of image data.