KR20200072155A - coronary artery flow velocity approximation method based on 2D X-ray image - Google Patents
coronary artery flow velocity approximation method based on 2D X-ray image Download PDFInfo
- Publication number
- KR20200072155A KR20200072155A KR1020180160013A KR20180160013A KR20200072155A KR 20200072155 A KR20200072155 A KR 20200072155A KR 1020180160013 A KR1020180160013 A KR 1020180160013A KR 20180160013 A KR20180160013 A KR 20180160013A KR 20200072155 A KR20200072155 A KR 20200072155A
- Authority
- KR
- South Korea
- Prior art keywords
- ray image
- image
- flow velocity
- blood flow
- coronary artery
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 12
- 210000004351 coronary vessel Anatomy 0.000 title claims 2
- 230000017531 blood circulation Effects 0.000 claims abstract description 17
- 230000002792 vascular Effects 0.000 claims description 4
- 210000004204 blood vessel Anatomy 0.000 abstract description 14
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 238000002586 coronary angiography Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 10
- 230000002526 effect on cardiovascular system Effects 0.000 description 6
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 230000007488 abnormal function Effects 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5223—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data generating planar views from image data, e.g. extracting a coronal view from a 3D image
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Power Engineering (AREA)
- High Energy & Nuclear Physics (AREA)
- Optics & Photonics (AREA)
- Radiology & Medical Imaging (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Hematology (AREA)
- Cardiology (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
Description
X-ray coronary angiography 2차원 영상 모달리티는 기본적인 진단을 위해 필수적으로 촬영되는 영상이다. X-ray coronary angiography Two-dimensional image modality is an essential image for basic diagnosis.
이때 정성적으로 혈관의 흐름이 원활한지 시술자가 판단을 하는데 이와 더불어 정량적으로 혈류속도의 근사치를 구할 수 있는 방법을 제안하고자 한다.At this time, the operator judges whether the flow of blood vessels is qualitatively. In addition, we intend to propose a method to quantitatively approximate blood flow velocity.
혈류속도를 측정하기 위해서 기존에는 침습적인 방법으로 체내에서 장치를 사용하여 측정하였다. 그러나 침습적인 방법은 환자에게 부담이 되고 비용이 증가될 수밖에 없다. In order to measure blood flow velocity, it was previously measured using an apparatus in the body by an invasive method. However, invasive methods are burdensome to the patient and inevitably increase costs.
혈류속도는 모세혈관 혈관으로 혈액을 공급하는 심장의 기능을 판단 할 수 있는 하나의 척도로 사용될 수 있을 것으로 기대된다.Blood flow velocity is expected to be used as a measure of the ability of the heart to supply blood to capillaries.
가령, 혈류 속도가 느린 경우 혈액의 공급이 원활하지 않을 가능성을 제시 할 수 있으며, 혈류 속도가 빠르면 혈관이 딱딱한 것으로, 속도가 빠를수록 심혈관 질환을 일으키는 요인이 된다.For example, if the blood flow rate is slow, it may suggest that the blood supply may not be smooth, and if the blood flow rate is fast, the blood vessels are hard, and the higher the speed, the more it causes cardiovascular disease.
본 발명에 따르면 2D X-ray영상 기반 관상동맥 혈류속도 근사방법은 인코더 부분의 매 계층에서 filter의 receptive field 정보를 저장하고 있다가 디코더 부분의 매 계층에서 인코더 부분에서 저장한 정보를 수신하고, 상기 수신한 정보를 U-NET모델을 학습 모델로 설정하여 2D X-ray 이미지와 상기 이미지의 Ground truth를 인풋으로 넣어 학습을 시킨 후 혈관 확률맵을 아웃풋으로 구하는 것을 특징으로 할 수 있다.According to the present invention, the 2D X-ray image-based coronary blood flow approximation method stores receptive field information of a filter at every layer of the encoder part, and then receives information stored at the encoder part at each layer of the decoder part, The received information may be set as a learning model, a 2D X-ray image and ground truth of the image may be input as inputs, and then a learning probability map may be obtained as an output.
본 발명으로 인하여 기존의 심장의 기능이 정상인 환자들과 기능이 이상이 있는 환자들로부터 얻어진 혈류에 관한 정보들을 기반으로 진단시 환자의 측정된 혈류 속도를 가지고 심장의 기능을 간단히 판단 할 수 있는 보조 지표가 될 수 있는 효과가 기대된다.According to the present invention, based on information on blood flow obtained from patients with normal heart function and patients with abnormal function, it is possible to easily determine the function of the heart with the measured blood flow rate of the patient during diagnosis Expected to be an indicator.
도 1은 U-NET 모델을 이용한 학습을 나타낸 도면이다.
도 2는 Pixel 개수 측면에서 바라본 환자의 심혈관 혈류 속도 근사치를 나타낸 도면이다.
도 3은 속도 변화 구간 설정을 나타낸 도면이다.
도 4는 각 Frame에서의 2D X-ray이미지(위)와 U-NET 모델을 사용하여 추출한 혈관 맵과 혈관에 해당하는 pixel 개수를 나타낸 도면이다.
도 5는 
도 6은 인공지능을 이용하여 추출한 혈관 확률 맵 기반 실험과 Ground_Truth 기반의 실험 결과 비교를 나타낸 도면이다.1 is a diagram showing learning using a U-NET model.
2 is a diagram showing an approximation of the cardiovascular blood flow rate of a patient when viewed in terms of the number of pixels.
3 is a view showing a speed change section setting.
4 is a diagram showing the number of pixels corresponding to a blood vessel map and blood vessels extracted using a 2D X-ray image (above) and a U-NET model in each frame.
Figure 5
FIG. 6 is a diagram illustrating a comparison of experimental results based on a vascular probability map extracted using artificial intelligence and a Ground_Truth based experiment.
아래에서는 첨부한 도면을 참고로 하여 본 발명의 실시 예에 대하여 본 발명이 속하는 기술 분야에서 통상의 지식을 가진 자가 용이하게 실시할 수 있도록 상세히 설명한다. 그러나 본 발명은 여러 가지 상이한 형태로 구현될 수 있으며 여기에서 설명하는 실시 예에 한정되지 않는다.Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains may easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein.
그리고 도면에서 본 발명을 명확하게 설명하기 위해서 설명과 관계없는 부분은 생략하였으며, 명세서 전체를 통하여 유사한 부분에 대해서는 유사한 도면 부호를 붙였다.In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.
명세서 전체에서, 어떤 부분이 어떤 구성요소를 "포함"한다고 할 때, 이는 특별히 반대되는 기재가 없는 한 다른 구성 요소를 제외하는 것이 아니라 다른 구성요소를 더 포함할 수 있는 것을 의미한다.Throughout the specification, when a part “includes” a certain component, it means that the component may further include other components, not to exclude other components, unless otherwise stated.
이하, 도면을 참조하여 본 발명의 실시 예에 따른 2D X-ray영상 기반 관상동맥 혈류속도 근사방법에 대하여 설명한다.Hereinafter, a method for approximating a coronary blood flow velocity based on 2D X-ray images according to an embodiment of the present invention will be described with reference to the drawings.
도 1은 U-NET 모델을 이용한 학습을 나타낸 도면이다.1 is a diagram showing learning using a U-NET model.
2차원 X-ray 영상은 3차원 물체가 Homogeneous 좌표에 의하여 정사영되므로 여러 좌표들이 서로 겹쳐져서 강해지기도 하며, 거리에 따라 같은 혈관 내에서도 강도(intensity)가 다르게 나타날 수 있다.In a 2D X-ray image, since a 3D object is projected by Homogeneous coordinates, several coordinates overlap each other and become strong, and intensity may be different in the same blood vessel depending on the distance.
또한 2차원 X-ray 영상에는 수많은 잡음이 생기게 되는데, 이처럼 불규칙한 값의 분포를 띄는 2D X-ray 영상에서 매 픽셀마다 혈관에 해당하는지에 대한 확률값을 얻을 수 있다면 이 확률값은 영상에서 한 픽셀의 혈관정보가 될 수 있다.In addition, there is a lot of noise in the 2D X-ray image. In this 2D X-ray image with an irregular distribution of values, if a probability value of whether a blood vessel corresponds to every pixel can be obtained, this probability value is a blood vessel of one pixel in the image. It can be information.
본 발명에서는 인코더 부분의 매 계층에서 filter의 receptive field 정보를 저장하고 있다가 디코더 부분의 매 계층에서 인코더 부분에서 저장한 정보를 받음으로써 도 1과 같이 현재 의료영상 데이터 학습에서 가장 성능이 높다고 알려진 U-NET모델을 학습 모델로 설정하여, 도 1과 같이 2D X-ray 이미지와 그것의 Ground truth를 인풋으로 넣어 학습을 시킨 후 혈관 확률맵을 아웃풋으로 구할 수 있다.In the present invention, the receptive field information of the filter is stored at every layer of the encoder part, and the information stored at the encoder part is received at each layer of the decoder part. By setting the -NET model as a learning model, as shown in FIG. 1, a 2D X-ray image and its ground truth are input as inputs for training, and a blood vessel probability map can be obtained as an output.
도 2는 Pixel 개수 측면에서 바라본 환자의 심혈관 혈류 속도 근사치를 나타낸 도면이다.2 is a diagram showing an approximation of the cardiovascular blood flow rate of a patient when viewed in terms of the number of pixels.
인공지능을 통해 얻어진 혈관 확률맵들을 통하여 아래 수학식 1 과 같이 각 Frame 별로 혈관에 해당하는 픽셀의 개수를 구할 수 있다. Through the blood vessel probability maps obtained through artificial intelligence, as shown in
[수학식 1][Equation 1]
도 3은 속도 변화 구간 설정을 나타낸 도면이다.3 is a view showing a speed change section setting.
본 발명에서는 수학식 1을 통하여 얻은 각 Frame별 혈관에 해당하는 pixel의 개수를 이용하여 다음의 일련의 계산을 통하여 환자의 심혈관 혈류 속도의 근사치를 구할 수 있다.In the present invention, an approximate value of the cardiovascular blood flow rate of a patient may be obtained through the following series of calculations using the number of pixels corresponding to blood vessels for each frame obtained through
하지만 Pixel 개수 측면에서 바라본 환자의 심혈관 혈류 속도 근사치는 도 2와 같이 매우 다르게 나타나기 때문에 도 3과 같이 속도 변화구간을 기준점으로 사용하여 기준점 이전의 구간만을 고려하여 다음의 일련의 계산을 진행할 수 있다.However, since the approximation of the cardiovascular blood flow rate of the patient in terms of the number of pixels is very different as shown in FIG. 2, the following series of calculations may be performed by considering only the section before the reference point using the speed change section as the reference point as shown in FIG. 3.
도 4는 각 Frame에서의 2D X-ray이미지(위)와 U-NET 모델을 사용하여 추출한 혈관 맵과 혈관에 해당하는 pixel 개수를 나타낸 도면이다.4 is a diagram showing the number of pixels corresponding to a blood vessel map and blood vessels extracted using a 2D X-ray image (above) and a U-NET model in each frame.
먼저 각 Frame의 pixel의 개수를 거리 단위인 mm로 환산을 하기 위하여 수학식 2와 같이 픽셀의 개수에 x축과 y축의 scale factor인 
[수학식 2][Equation 2]
위와 같이 픽셀의 개수를 거리로 변환하게 되면 아래 수학식 (3)와 같이 각 Frame별 거리의 차이를 구할 수 있다.When the number of pixels is converted to a distance as above, the distance difference for each frame can be obtained as shown in Equation (3) below.
[수학식 3][Equation 3]
도 5는 
위 수학식 (3)을 통하여 얻은 각 Frame별 거리차이들 
본 발명의 일 실시 예에 따르면 일반적으로 2D X-ray angiography는 1초에 15회 촬영이 되므로, 위에서 구한 평균 속도는 
일반적으로 사람의 심혈관 혈류 속도는 
하지만 위의 범위는 부피 단위이기 때문에 도 5와 같은 방법을 통하여 거리 단위의 범위로 환산할 수 있다.However, since the above range is a volume unit, it can be converted into a range of distance units through the method shown in FIG. 5.
도 6은 인공지능을 이용하여 추출한 혈관 확률 맵 기반 실험과 Ground_Truth 기반의 실험 결과 비교를 나타낸 도면이다.FIG. 6 is a diagram illustrating a comparison of experimental results based on a vascular probability map extracted using artificial intelligence and a Ground_Truth based experiment.
본 발명의 일 실시 예에 따라 총 10명의 환자에 대하여 실험을 한 결과 인공지능을 통하여 혈관 확률맵을 추출하여 실험을 한 것과 실제 Ground_Truth와의 차이가 거의 없는 것을 도 6에서 볼 수 있다.As a result of experimenting on a total of 10 patients in accordance with an embodiment of the present invention, it can be seen in FIG. 6 that there is little difference between the experiment and the actual Ground_Truth extracted by extracting the vascular probability map through artificial intelligence.
최종적으로 본 특허에서 구한 최종 속도는 
본 발명의 실시 예는 이상에서 설명한 장치 및/또는 방법을 통해서만 구현이 되는 것은 아니며, 이상에서 본 발명의 실시 예에 대하여 상세하게 설명하였지만 본 발명의 권리범위는 이에 한정되는 것은 아니고 다음의 청구범위에서 정의하고 있는 본 발명의 기본 개념을 이용한 당업자의 여러 변형 및 개량 형태 또한 본 발명의 권리범위에 속하는 것이다.The embodiments of the present invention are not implemented only through the devices and/or methods described above, and the embodiments of the present invention have been described in detail above, but the scope of the present invention is not limited thereto, and the following claims Various modifications and improvements of those skilled in the art using the basic concept of the present invention defined in the above also belong to the scope of the present invention.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020180160013A KR20200072155A (en) | 2018-12-12 | 2018-12-12 | coronary artery flow velocity approximation method based on 2D X-ray image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020180160013A KR20200072155A (en) | 2018-12-12 | 2018-12-12 | coronary artery flow velocity approximation method based on 2D X-ray image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| KR20200072155A true KR20200072155A (en) | 2020-06-22 |
Family
ID=71142657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020180160013A KR20200072155A (en) | 2018-12-12 | 2018-12-12 | coronary artery flow velocity approximation method based on 2D X-ray image |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR20200072155A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114387436A (en) * | 2021-12-28 | 2022-04-22 | 北京安德医智科技有限公司 | Wall coronary artery detection method and device, electronic device and storage medium |
-
2018
- 2018-12-12 KR KR1020180160013A patent/KR20200072155A/en not_active Application Discontinuation
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114387436A (en) * | 2021-12-28 | 2022-04-22 | 北京安德医智科技有限公司 | Wall coronary artery detection method and device, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5828649B2 (en) | Image processing apparatus, image processing method, and computer program | |
| CN103839249B (en) | CT liver-perfusion image post-processing method and CT liver-perfusion method | |
| CN110522466B (en) | Method and device for determining the weight and/or body mass index of a patient | |
| JP2022539078A (en) | Systems and methods for guidance of motion conditioning devices using vascular roadmaps | |
| KR102030533B1 (en) | Image processing apparatus for adopting human body morphometric based on artificial neural network for sarcopenia and image processing method using the same | |
| CN109381205B (en) | Method for performing digital subtraction angiography, hybrid imaging device | |
| JP7041147B2 (en) | Systems and methods that characterize hepatic perfusion of contrast medium flow | |
| US10898267B2 (en) | Mobile FFR simulation | |
| US20220164953A1 (en) | 3d vessel centerline reconstruction from 2d medical images | |
| WO2020165120A1 (en) | Prediction of coronary microvascular dysfunction from coronary computed tomography | |
| KR20200072155A (en) | coronary artery flow velocity approximation method based on 2D X-ray image | |
| JP2010536456A (en) | Method for measuring flow in an object, particularly a lumen or blood vessel | |
| CN113226181B (en) | Method for calibrating X-ray projection geometry in X-ray cone beam computed tomography | |
| US20230076352A1 (en) | Systems and methods for image processing | |
| CN110555261A (en) | Digital three-generation simulation method and device for heart motion | |
| US20230022425A1 (en) | Apparatus, system, method and computer probram for providing a nuclear image of a region of interest of a patient | |
| US7116808B2 (en) | Method for producing an image sequence from volume datasets | |
| WO2008056305A1 (en) | Noise reduction of an image signal | |
| Kulathilake et al. | A segmentation method for extraction of main arteries from coronary cine-angiograms | |
| US20240164733A1 (en) | Subtraction imaging | |
| US11666299B2 (en) | Controlling a medical X-ray device | |
| US20220175332A1 (en) | Angiography derived coronary flow | |
| EP4177843A1 (en) | Image processing device, medical imaging system and computer program element | |
| JP2023547373A (en) | How to determine vascular fluid flow rate | |
| RU2644928C1 (en) | Method for determination of frames relating to circulation phases borders, during angiographic study (versions) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| E902 | Notification of reason for refusal | ||
| E601 | Decision to refuse application |