IP Library Granted Patent US 12688558
Granted Patent B2
US 12688558 · App. 18/175,566 · Granted Jul 21, 2026

Subtraction image processing apparatus, subtraction image processing method, and non-transitory storage medium

Inventor: Toshimizu Yamane (Tokyo, JP)
Assignee: CANON KABUSHIKI KAISHA
G06T5/70G06T5/50G06T7/0014G06T2207/20221G06T2207/20224G06T2207/30012
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12688558
App. No.
18/175,566
Granted
Jul 21, 2026
Kind
B2
Abstract

An image processing apparatus includes: an obtaining unit configured to obtain a first medical image and a second medical image collected from an object; an identification unit configured to identify a plurality of sites of the object included in the first medical image; and a subtraction image generation unit configured to generate a subtraction image between the first medical image and the second medical image by calculating, for each of a plurality of pixels forming the first medical image, a subtraction value with respect to a pixel, corresponding to the pixel, on the second medical image by a subtraction generation method corresponding to a site based on the result of the identification unit.

Claims (34)

1 . An image processing apparatus comprising:

a processor; and

a memory including instructions, which when executed by the processor, cause the image processing apparatus to perform operations comprising:

obtaining a first medical image and a second medical image collected from an object;

executing registration processing between the first medical image and the second medical image and obtain registered first and second medical images;

storing a pair of programs in association with a first subtraction generation method and a second subtraction generation method in which a degree of at least one of noise reduction processing for reduction of an artifact caused by a partial volume effect and emphasis processing is higher than that of the first subtraction generation method in the memory;

identifying a plurality of anatomical sites of interest within the object included in the first medical image; and

generating a subtraction image between the registered first and second medical images by calculating, for each of a plurality of pixels forming the registered first and second medical images, a subtraction value with respect to a pixel, corresponding to the pixel, on the second medical image by a selected, on a per-pixel basis, subtraction generation method out of the first subtraction generation method and the second subtraction generation method in association with the pair of programs stored in the memory based on the anatomical site identified,

wherein generating the subtraction image between the registered first and second medical images includes:

generating a plurality of partial images respectively corresponding to anatomical sites from the first medical image based on identification results of the plurality of anatomical sites;

generating a plurality of partial subtraction images by applying, to each of the plurality of partial images, a subtraction generation method corresponding to each anatomical site of the anatomical sites; and

generating the subtraction image by integrating the plurality of partial subtraction images.

2 . The apparatus according to to claim 1 , wherein each of the plurality of partial subtraction images partially includes different pixel values.

3 . The apparatus according to claim 1 , wherein the first subtraction generation method is applied to a pixel corresponding to an inside of a spinal canal, and the second subtraction generation method is applied to a pixel corresponding to an outside of the spinal canal.

4 . The apparatus according to claim 3 , wherein

the first subtraction generation method is simple subtraction processing between a pixel value of the first medical image and a pixel value of the second medical image.

5 . The apparatus according to claim 1 , wherein the first subtraction generation method is applied to a pixel corresponding to a vertebra region excluding an inside of a spinal canal or a peripheral region of the vertebra region, and the second subtraction generation method is applied to a pixel outside corresponding to a vertebra region including the inside of the spinal canal or the peripheral region of the vertebra region.

6 . The apparatus according to claim 5 , wherein

the first subtraction generation method is subtraction processing including high density emphasis processing of attenuating a subtraction value of a relative low pixel value region, and

the second subtraction generation method is subtraction processing including high density emphasis processing of strengthening a degree of attenuating the subtraction value, as compared with the first subtraction generation method.

7 . The apparatus according to claim 1 , wherein generating the subtraction image between the registered first and second medical images includes generating a binary subtraction image by binarizing a subtraction value of a pixel in accordance with the anatomical site.

8 . The apparatus according to claim 7 , further comprising:

generating a fusion image by superimposing the binary subtraction image on one of the subtraction image, the first medical image, or the second medical image.

9 . An image processing method comprising:

obtaining a first medical image and a second medical image collected from an object;

identifying a plurality of anatomical sites of interest within the object included in the first medical image;

executing registration processing between the first medical image and the second medical image and obtaining registered first and second medical images;

reading out a selected one of a pair of programs stored in a memory in association with a first subtraction generation method and a second subtraction generation method in which a degree of at least one of noise reduction processing for reduction of an artifact caused by a partial volume effect and emphasis processing is higher than that of the first subtraction generation method; and

generating a subtraction image between the registered first and second medical images and the second medical image by calculating, for each of a plurality of pixels forming the first medical image, a subtraction value with respect to a pixel, corresponding to the pixel, on the second medical image by a selected, on a per-pixel basis, subtraction generation method out of the first subtraction generation method and the second subtraction generation method in association with the pair of programs stored in the memory based on the anatomical site identified in a step of the identifying,

wherein generating the subtraction image between the registered first and second medical images includes:

generating a plurality of partial images respectively corresponding to anatomical sites from the first medical image based on identification results of the plurality of anatomical sites;

generating a plurality of partial subtraction images by applying, to each of the plurality of partial images, a subtraction generation method corresponding to each anatomical site of the anatomical sites; and

generating the subtraction image by integrating the plurality of partial subtraction images.

10 . A non-transitory storage medium storing an image processing program for causing a computer to execute an image processing method according to claim 9 .