Image processor, image processing method, and image processing program

An image processing device and image processing technology, applied in image data processing, image enhancement, image analysis and other directions, can solve problems such as being unsuitable for health diagnosis purposes, judgment, and inability to detect

Inactive Publication Date: 2019-03-01
KONICA MINOLTA INC
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In this regard, the conventional technology of Patent Document 1 cannot detect other than specific lesion patterns such as tuberculosis diagnosis, and is not suitable for the above-mentioned health diagnosis application.
In other words, in the

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processor, image processing method, and image processing program
  • Image processor, image processing method, and image processing program
  • Image processor, image processing method, and image processing program

Examples

Experimental program
Comparison scheme
Effect test

Deformed example 1

[0106] Figure 7 It is a figure which shows an example of the recognizer M concerning the modification 1.

[0107] The diagnostic unit 20 according to Modification 1 differs from the above in that it divides the entire image area of ​​a medical image into a plurality of image areas (here, divided into 9 parts D1a to D1i) and calculates the degree of normality for each image area. The implementation is different.

[0108] The aspect related to Modification 1 can be realized, for example, by providing a classifier M for performing image analysis for each image region of a medical image. exist Figure 7 , there are 9 different classifiers Ma~Mi provided to correspond to the 9 image regions D1a~D1i respectively. In addition, the classifier M for performing image analysis may be provided for each internal organ part of the medical image.

[0109] The display control unit 30 according to Modification 1, for example, associates the degree of normality calculated for each image re...

Deformed example 2

[0113] Figure 8 It is a figure which shows an example of the identifier M concerning the modification 2.

[0114] The diagnosis unit 20 according to this modification 2 is different from the above-mentioned embodiment in that it calculates the normality for each pixel region of a medical image (representing a region forming one pixel or a region of a plurality of pixels forming one division. The same applies hereinafter). different ways.

[0115] The aspect of Modification 2 can be realized, for example, by providing an output element for each pixel area of ​​a medical image in the recognition unit Nb of CNN (also referred to as R-CNN).

[0116] The display control unit 30 according to Modification 2, for example, correlates the normality of each pixel region with the position of the pixel region in the medical image, and displays it on the display device 300 . At this time, the display control unit 30 expresses, for example, the normality conversion of each pixel area as c...

Deformed example 3

[0120] The image processing device 100 according to Modification 3 differs from the above-described embodiment in the configuration of the display control unit 30 .

[0121] The display control unit 30 sets the order in which the plurality of medical images are displayed on the display device 300 based on the respective normality degrees of the plurality of medical images, for example, after calculating the normality of the plurality of medical images. Then, the display control unit 30 outputs, for example, the medical image data D1 and the normality data D2 to the display device 300 in a set order.

[0122] In this way, for example, among a plurality of medical images, those with a higher possibility of being in an abnormal state are displayed on the display device 300 in order, so that a subject with a high necessity or urgency can receive a formal diagnosis by a doctor or the like. .

[0123] In addition, the display control unit 30 may set whether to display a plurality o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention aims to provide an image processor, which is more suitable for carrying out comprehensive diagnosis based on medical images. An image processor diagnosing a medical image of a diagnostictarget region of a subject imaged by a medical image capturer, includes: an image acquirer acquiring the medical image; and a diagnoser analyzing the medical image using a classifier that has alreadyfinished learning and calculating an index indicating a probability of the medical image corresponding to any of categories of lesion patterns, wherein in the classifier, to perform the learning process, in a learning process using the medical image that has been diagnosed not to correspond to any of the categories of lesion patterns, a first value indicating a normal state is set as a correct value of the index, and in a learning process using the medical image that has been diagnosed to correspond to any of the categories of lesion patterns, a second value indicating an abnormal state is set as a correct value of the index.

Description

technical field [0001] The present disclosure relates to an image processing device, an image processing method, and an image processing program. Background technique [0002] Computer-Aided Diagnosis (Computer-Aided Diagnosis: hereinafter) is known in which a computer performs image analysis of a medical image of a diagnostic object part of an object and presents an abnormal region in the medical image to assist a doctor in diagnosis. Also known as "CAD"). [0003] CAD typically diagnoses whether a specific lesion pattern (eg, tuberculosis or nodule) occurs in a medical image. For example, the prior art related to Patent Document 1 discloses a method of judging whether or not there is an abnormal shadow pattern of a nodule in a chest simple X-ray image. [0004] prior art literature [0005] patent documents [0006] Patent Document 1: Specification of US Patent No. 5740268 [0007] By the way, in health diagnosis, unlike special diagnosis such as tuberculosis screenin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): A61B6/00G06V10/764
CPCA61B6/5205A61B6/5211A61B6/463A61B6/50A61B6/5217A61B8/5223G06T7/0012G06T2207/10116G06T2207/20084G06T2207/30061G06T2207/30096G16H50/30G06V10/454G06V2201/03G06V10/82G06V10/764G06T7/0014G06T2207/20081G06T2207/20021G16H30/40G06F18/2415
Inventor 小林刚
Owner KONICA MINOLTA INC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap