Medical image processing apparatus, medical image processing method, and medical image processing program
A determination processing unit determines a disease region in a medical image including an axisymmetric structure. A first determination section of the determination processing unit generates a feature amount map of the medical image from the medical image. A second determination section second inverts the feature amount map with reference to a symmetry axis to generate an inverted feature amount map. A third determination section superimposes the feature amount map and the inverted feature amount map on each other and determines the disease region in the medical image using the feature amount map and the inverted feature amount map superimposed on each other.
1. A medical image processing apparatus, comprising:
a central processing unit (CPU) to determine a disease region in a medical image including an axisymmetric structure,
wherein the CPU has:
a first determination section, to be executed by the CPU, to generate a feature amount map of the medical image from the medical image;
a second determination section, to be executed by the CPU, to invert the feature amount map with reference to a symmetry axis of the feature amount map to generate an inverted feature amount map; and
a third determination section, to be executed by the CPU, to superimpose the feature amount map and the inverted feature amount map on each other and to determine the disease region in the medical image using the feature amount map and the inverted feature amount map superimposed on each other, and
wherein the feature amount map has lower resolution than the medical image.
2. The medical image processing apparatus according to claim 1 ,
wherein each of the first determination section, the second determination section, and the third determination section is a neural network having at least one processing layer.
3. The medical image processing apparatus according to claim 1 ,
wherein the medical image is a CT image of a brain, and the disease region is a disease region within the brain.
4. The medical image processing apparatus according to claim 3 ,
wherein the disease region is a bleeding region or an infarct region.
5. The medical image processing apparatus according to claim 1 , further comprising:
a display controller to display the medical image in which the disease region is determined on a display unit.
6. A medical image processing method for determining a disease region in a medical image including an axisymmetric structure with a determination processing unit, the method comprising:
generating a feature amount map of the medical image from the medical image;
inverting the feature amount map with reference to a symmetry axis of the feature amount map to generate an inverted feature amount map; and
superimposing the feature amount map and the inverted feature amount map on each other and determining the disease region in the medical image using the feature amount map and the inverted feature amount map superimposed on each other,
wherein the feature amount map has lower resolution than the medical image.
7. A non-transitory computer-readable storage medium that stores a medical image processing program causing a computer to execute processing for determining a disease region in a medical image including an axisymmetric structure, the program causing the computer to execute:
a step of generating a feature amount map of the medical image from the medical image;
a step of inverting the feature amount map with reference to a symmetry axis of the feature amount map to generate an inverted feature amount map; and
a step of superimposing the feature amount map and the inverted feature amount map on each other and determining the disease region in the medical image using the feature amount map and the inverted feature amount map superimposed on each other,
wherein the feature amount map has lower resolution than the medical image.