Medical image processing apparatus, medical image processing method, computer-readable medical-image processing program, moving-object tracking apparatus, and radiation therapy system

A medical image processing apparatus comprising:

• a memory configured to store a parameter of a discriminator, the parameter being acquired by machine learning using a feature acquired from a specific image, wherein the specific image is a first image in which information having a correlation with a motion of a target portion to be radiated in an object satisfies a specific condition, and the first image is either entirety of a fluoroscopic image of the object or part of the fluoroscopic image;
• an image input interface configured to acquire another fluoroscopic image that is an image of the object and is different from the first image;
• a feature calculator configured to acquire a feature of a second image, wherein the second image is either entirety or part of the another fluoroscopic image acquired from the image input interface;
• and
• a determination-signal output interface configured to output a determination signal, the determination signal indicating a result of determination of the second image based on the parameter stored in the memory and the feature of the second image.