KR20190125592A - 3D Blood Vessel Construction Method using medical images - Google Patents
3D Blood Vessel Construction Method using medical images Download PDFInfo
- Publication number
- KR20190125592A KR20190125592A KR1020180049580A KR20180049580A KR20190125592A KR 20190125592 A KR20190125592 A KR 20190125592A KR 1020180049580 A KR1020180049580 A KR 1020180049580A KR 20180049580 A KR20180049580 A KR 20180049580A KR 20190125592 A KR20190125592 A KR 20190125592A
- Authority
- KR
- South Korea
- Prior art keywords
- coronary artery
- generating
- dimensional
- image
- blood vessels
- Prior art date
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 31
- 238000010276 construction Methods 0.000 title 1
- 238000000034 method Methods 0.000 claims abstract description 36
- 210000004351 coronary vessel Anatomy 0.000 claims abstract description 23
- 238000003325 tomography Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract 1
- 238000002591 computed tomography Methods 0.000 description 13
- 238000010801 machine learning Methods 0.000 description 5
- 230000003902 lesion Effects 0.000 description 3
- 201000000057 Coronary Stenosis Diseases 0.000 description 2
- 206010011089 Coronary artery stenosis Diseases 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000002216 heart Anatomy 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- CVOFKRWYWCSDMA-UHFFFAOYSA-N 2-chloro-n-(2,6-diethylphenyl)-n-(methoxymethyl)acetamide;2,6-dinitro-n,n-dipropyl-4-(trifluoromethyl)aniline Chemical compound CCC1=CC=CC(CC)=C1N(COC)C(=O)CCl.CCCN(CCC)C1=C([N+]([O-])=O)C=C(C(F)(F)F)C=C1[N+]([O-])=O CVOFKRWYWCSDMA-UHFFFAOYSA-N 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013170 computed tomography imaging Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000002600 positron emission tomography Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 210000004291 uterus Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
- G06T15/20—Perspective computation
- G06T15/205—Image-based rendering
-
- 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
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Veterinary Medicine (AREA)
- Geometry (AREA)
- Biophysics (AREA)
- High Energy & Nuclear Physics (AREA)
- Computing Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Pulmonology (AREA)
- Optics & Photonics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Computer Graphics (AREA)
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
Description
본 발명은 의료 영상을 처리하여 혈관의 3차원 형상을 생성하는 방법에 관한 것이다. 보다 상세하게는 복수의 2차원 단층 영상을 처리하여 혈관의 3차원 형상을 생성하는 방법에 관한 것이다.The present invention relates to a method of generating a three-dimensional shape of a blood vessel by processing a medical image. More particularly, the present invention relates to a method of generating a three-dimensional shape of a blood vessel by processing a plurality of two-dimensional tomographic images.
의료 영상 처리 장치는 비침습적으로 인체의 내부 구조를 보여줄 수 있는 영상을 취득하는 장치이다. 의료 영상 처리 장치에서 출력되는 의료 영상을 분석하여 환자의 질병 진단에 이용할 수 있다.The medical image processing apparatus is a device for acquiring an image that can non-invasively show the internal structure of the human body. The medical image output from the medical image processing apparatus may be analyzed and used to diagnose a disease of the patient.
의료 영상을 촬영 및 처리하기 위한 장치로는 MRI(Magnetic Resonance Imaging)장치, 컴퓨터 단층촬영(CT: Computed Tomography) 장치, 엑스레이 장치 또는 초음파 장치 등이 있다. 의료 영상 처리 장치 중 컴퓨터 단층촬영(CT) 장치는 인체의 단면 영상을 촬영할 수 있다. CT 장치로 촬영된 영상의 분해능(resolution)은 대략 0.7mm 정도로, 직경이 수 밀리 미터(mm:millimeter) 크기를 갖는 혈관들의 영상을 정밀하게 촬영하기 어렵다. 또한, 관상동맥과 같은 심장에 분포하는 혈관은 심장 박동에 의해서 움직이므로 정확한 혈관의 영상을 얻기가 어렵다. 심장 CT 영상에는 모션 아티팩트(motion artifact)와 같은 다양한 아티팩트가 나타난다. Devices for photographing and processing medical images include magnetic resonance imaging (MRI) devices, computed tomography (CT) devices, x-ray devices, or ultrasound devices. The CT apparatus of the medical image processing apparatus may photograph a cross-sectional image of a human body. The resolution of an image taken with a CT device is about 0.7 mm, and it is difficult to accurately capture an image of blood vessels having a diameter of several millimeters. In addition, since blood vessels distributed in the heart, such as coronary arteries, are moved by the heartbeat, it is difficult to obtain an accurate image of the blood vessels. Cardiac CT images show various artifacts, such as motion artifacts.
관상 동맥 협착과 같은 혈관의 병변을 진단하고 분석하기 위하여는 복수의 2차원 단층 이미지를 처리하여 혈관의 3차원 형상 모델을 생성하는 것이 필요하다. 특히 정확하고, 신속한 진단을 위하여는 정확하고 신속하게 혈관의 3차원 모델을 생성하는 방법이 필요하다.In order to diagnose and analyze lesions of blood vessels such as coronary artery stenosis, it is necessary to generate a three-dimensional shape model of blood vessels by processing a plurality of two-dimensional tomographic images. In particular, accurate and rapid diagnosis requires a method of generating a three-dimensional model of blood vessels accurately and quickly.
최근 딥런닝(DeepLearning) 또는 기계학습(Maching learning) 기법을 활용한 의료영상처리 기술이 개발되고 있다. 특히, X-ray, 초음파, CT(Computed Tomography), MRI(Magnetic Resonance Imaging), PET(Positron Emission Tomography) 등의 기기들로부터 획득된 의료 영상에 딥런닝 기법을 적용하여 질병을 진단하고자 하는 개발이 진행되고 있다. 즉, 딥런닝 기법을 이용하여 의료 영상에 나타난 조직이 정상인지 비정상인지, 종양의 경우 양성인지 음성인지 분류하는보조 진단시스템이 개발되어 있으며, 영상의학과 의사가 영상을 판독하는 수준까지 발전된 것으로 알려져 있다. Recently, medical image processing technology using deep learning or machine learning techniques has been developed. In particular, the development of diagnosing diseases by applying deep learning techniques to medical images obtained from devices such as X-ray, ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) It's going on. In other words, an auxiliary diagnostic system has been developed that uses deep running techniques to classify normal or abnormal tissues on a medical image and positive or negative for tumors. .
이러한 병변의 유무를 자동으로 분류하기 위한 알고리즘으로 naive bayes, SVM(Support Vector Machine), ANN(Artificial Neural Network), HMM(Hidden Markov Model) 등의 알고지즘이 알려져 있다. 또한, 이러한 분류에 기계학습(machine learning) 알고리즘을 사용할 수 있으며, 기계학습 알고리즘은 은 크게 지도학습(Supervised Learning)과 비지도학습(Unsupervised Learning) 알고리즘으로 분류 된다.Algorithms such as naive bayes, support vector machines (SVMs), artificial neural networks (ANNs), and hidden markov models (HMMs) are known as algorithms for automatically classifying the presence or absence of such lesions. In addition, machine learning algorithms can be used for this classification, and machine learning algorithms are classified into supervised learning and unsupervised learning algorithms.
딥 런닝 또는 기계학습 알고리즘을 이용하여 의료 영상을 처리하여 혈관의 3차원 모델을 자동으로 생성한 기술은 개발되어 있지 않다. 본 발명은 복수의 단층 의료 영상을 처리하여 혈관의 3차원 모델을 자동으로 생성하는 방법을 제공하는 것을 목적으로 한다.No technology has been developed for automatically generating three-dimensional models of blood vessels by processing medical images using deep running or machine learning algorithms. An object of the present invention is to provide a method for automatically generating a three-dimensional model of blood vessels by processing a plurality of tomography medical images.
본 발명에 따른 혈관의 3차원 모델 생성 방법은 컴퓨터 시스템을 이용하여 혈관의 3차원 모델을 생성하는 방법이다. 본 발명에 따른 방법은 복수의 2차원 단층 영상을 입력받는 단계와, 입력받은 복수의 2차원 단층 영상을 전처리하여 관상동맥이 위치하는 영역을 표시하여 학습 이미지 데이타를 생성하는 단계와, 생성된 학습 이미지 데이타로 학습하여 관상동맥 특징 이미지 예측 모델을 생성하는 단계와, 복수의 2차원 단층 이미지를 상기 생성된 관상동맥 특징 이미지 예측 모델에 입력하여 관상동맥 특징 표시 복수의 2차원 단층 이미지를 출력 받는 단계를 포함하고, 상기 출력된 관상동맥 특징 표시 복수의 2차원 단층이미지를 이용하여 관상동맥 3차원 형상을 생성하는 단계를 포함한다. 상기 관상동맥 특징 이미지 예측모델을 학습하는 단계는 FCN(Fully Convolutional Network) 알고리즘 또는 지도학습(Supervised Learning) 알고리즘을 사용한다.The method of generating a three-dimensional model of a blood vessel according to the present invention is a method of generating a three-dimensional model of a blood vessel using a computer system. The method according to the present invention comprises the steps of receiving a plurality of two-dimensional tomography images, pre-processing the plurality of received two-dimensional tomography images to display the region where the coronary artery is located to generate training image data, and generated learning Generating coronary feature image prediction models by learning from the image data, and receiving a plurality of 2D tomographic images by inputting a plurality of two-dimensional tomographic images to the generated coronary feature image prediction model. And generating a coronary artery 3D shape by using the output coronary artery feature display plurality of 2D tomography images. The learning of the coronary artery feature image prediction model uses a fully convolutional network (FCN) algorithm or a supervised learning algorithm.
본 발명에 따르면, 관상 동맥 협착과 같은 혈관의 병변을 정확하고 신속하게 진단하고 분석할 수 있도록 복수의 2차원 단층 이미지를 처리하여 혈관의 3차원 형상 모델을 생성하는 방법이 제공된다.According to the present invention, there is provided a method of generating a three-dimensional shape model of blood vessels by processing a plurality of two-dimensional tomographic images to accurately and quickly diagnose and analyze vessel lesions such as coronary artery stenosis.
도 1은 본 발명에 적용되는 FCN 알고리즘을 나타내는 개략도
도 2는 2차원 단층 이미지의 학습 이미지와 예측 모델로부터 출력된 혈관 영역 표시 이미지
도 3은 본 발명에 따른 방법을 나타내는 흐름도
도 4는 예측 모델을 이용하여 혈관의 3차원 형상을 생성하는 방법을 나타내는 흐름도1 is a schematic diagram showing an FCN algorithm applied to the present invention
2 is an image of a vessel region displayed from a training image and a prediction model of a 2D tomography image
3 is a flow chart illustrating a method according to the invention.
4 is a flowchart illustrating a method of generating a three-dimensional shape of a blood vessel using a predictive model.
본 명세서에서 "영상"은 이산적인 영상 요소들(예를 들어, 2차원 영상에 있어서의 픽셀들 및 3차원 영상에 있어서의 복셀들)로 구성된 다차원(multi-dimensional) 데이터를 의미할 수 있다. 예를 들어, 영상은 CT 촬영 장치 에 의해 획득된 대상체의 의료 영상 등을 포함할 수 있다.As used herein, "image" may mean multi-dimensional data composed of discrete image elements (eg, pixels in a 2D image and voxels in a 3D image). For example, the image may include a medical image of the object acquired by the CT imaging apparatus.
본 명세서에서 "CT(Computed Tomography) 영상"란 대상체에 대한 적어도 하나의 축을 중심으로 회전하며 대상체를 촬영함으로써 획득된 복수개의 엑스레이 영상들의 합성 영상을 의미할 수 있다. 본 명세서에서 "대상체(object)"는 사람 또는 동물, 또는 사람 또는 동물의 일부를 포함할 수 있다. 예를 들어, 대상체는 간, 심장, 자궁, 뇌, 유방, 복부 등의 장기, 또는 혈관을 포함할 수 있다 또한, "대상체"는 팬텀(phantom)을 포함할 수도 있다. 팬텀은 생물의 밀도와 실효 원자 번호에 아주 근사한 부피를 갖는 물질을 의미하는 것으로, 신체와 유사한 성질을 갖는 구형(sphere)의 팬텀을 포함할 수 있다.In the present specification, a "computed tomography (CT) image" may mean a composite image of a plurality of X-ray images obtained by photographing an object while rotating about at least one axis of the object. As used herein, an "object" may include a person or animal, or part of a person or animal. For example, the subject may include organs such as the liver, heart, uterus, brain, breast, abdomen, or blood vessels. The “subject” may also include a phantom. Phantom means a material having a volume very close to the density and effective atomic number of an organism, and may include a sphere phantom having properties similar to the body.
본 명세서에서 "사용자"는 의료 전문가로서 의사, 간호사, 임상 병리사, 의료 영상 전문가 등이 될 수 있으며, 의료 장치를 수리하는 기술자가 될 수 있으나, 이에 한정되지 않는다.As used herein, a "user" may be a doctor, a nurse, a clinical pathologist, a medical imaging professional, or the like, and may be a technician who repairs a medical device, but is not limited thereto.
CT 시스템은 대상체에 대하여 단면 영상을 제공할 수 있으므로, 일반적인 X-ray 촬영 기기에 비하여 대상체의 내부 구조(예컨대, 신장, 폐 등의 장기 등)가 겹치지 않게 표현할 수 있다는 장점이 있다. CT 시스템은, 예를 들어, 2mm 두께 이하의 영상데이터를 초당 수십, 수백 회 획득하여 가공함으로써 대상체에 대하여 비교적 정확한 단면 영상을 제공할 수 있다 종래에는 대상체의 가로 단면만으로 표현된다는 문제점이 있었지만, 다음과 같은 여러 가지 영상 재구성 기법의 등장에 의하여 극복되었다 3차원 재구성 영상기법들로는 다음과 같은 기법들이 있다.Since the CT system may provide a cross-sectional image of the object, an internal structure of the object (for example, an organ such as a kidney and a lung) may be overlapped with each other, compared to a general X-ray imaging apparatus. For example, a CT system can provide a relatively accurate cross-sectional image of an object by acquiring and processing image data having a thickness of 2 mm or less tens or hundreds of times per second. It was overcome by the emergence of various image reconstruction techniques such as the following three-dimensional reconstruction image techniques.
- SSD(Shade surface display): 초기 3차원 영상기법으로 일정 HU값을 가지는 복셀들만 나타내도록 하는 기법-SSD (Shade surface display): An initial three-dimensional imaging technique to display only voxels having a certain HU value
- MIP(maximum intensity projection)/MinIP(minimum intensity projection): 영상을 구성하는 복셀 중에서 가장 높은 또는 낮은 HU값을 가지는 것들만 나타내는 3D 기법Maximum intensity projection (MIP) / minimum intensity projection (MinIP): A 3D technique that shows only those having the highest or lowest HU value among the voxels constituting the image.
- VR(volume rendering): 영상을 구성하는 복셀들을 관심영역별로 색 및 투과도를 조절할 수 있는 기법-VR (volume rendering): A technique that can adjust the color and transmittance of the voxels constituting the image by region of interest
- 가상내시경(Virtual endoscopy): VR 또는 SSD 기법으로 재구성한 3차원 영상에서 내시경적 관찰이 가능한 기법-Virtual endoscopy: A technique capable of endoscopic observation in three-dimensional images reconstructed by VR or SSD
- MPR(multi planar reformation): 다른 단면 영상으로 재구성하는 영상 기법 사용자가 원하는 방향으로의 자유자제의 재구성이 가능하다-Multi planar reformation (MPR): An image technique for reconstructing into different cross-sectional images. It is possible to reconstruct freedom in the direction desired by the user.
- Editing: VR에서 관심부위를 보다 쉽게 관찰하도록 주변 복셀들을 정리하는 여러 가지 기법Editing: Various techniques for arranging surrounding voxels to make it easier to observe the point of interest in VR.
- VOI(voxel of interest): 선택 영역만을 VR로 표현하는 기법-VOI (voxel of interest): a technique of expressing only a selected area in VR
종래 CT 단층 촬영 이미지로 3차원 복셀을 형성하고 복셀을 처리하여 혈관의 3차원 형상을 생성하고 있다. 그러나 본 발명의 방법은 복셀을 처리하여 혈관의 3차원 형상을 생성하지 않는다.Conventionally, a three-dimensional voxel is formed from a CT tomography image and the voxel is processed to generate a three-dimensional shape of a blood vessel. However, the method of the present invention does not process voxels to produce three-dimensional shapes of blood vessels.
본 발명에 따른 혈관의 3차원 모델 생성 방법은 복수의 2차원 단층 영상을 이용하여 혈관의 3차원 형상을 생성한다.The three-dimensional model generation method of the blood vessel according to the present invention generates a three-dimensional shape of the blood vessel using a plurality of two-dimensional tomography images.
도 1에 도시된 것과 같이, 혈관의 영역이 표시된 2차원 단층 영상으로 기계학습을 하여 혈관 영역이 표시된 2차원 단층 영상을 얻을 수 있는 모델을 학습한다. 모델 학습에는 FCN(Fully Convolutional Network) 알고리즘이 이용된다. FCN 모델은 convolutional 하단 pooling layer의 값들을 upsampling해 적절히 mix하는 방법을 사용해 출력을 class 값이 아닌 pixel heat map이 나오도록 하는 방법을 사용한다. FCN 모델 기반으로 입력(raw CT image)과 결과(임상 검증 된 관상동맥 분할 image)로 이루어지는 쌍의 데이터를 이용해 학습시켜서 전역 최적함수에 근접하는 알고리즘을 구현한다.As shown in FIG. 1, a machine learning method is performed on a two-dimensional tomography image displaying a region of blood vessels, thereby learning a model for obtaining a two-dimensional tomography image displaying a region of blood vessels. Fully convolutional network (FCN) algorithm is used for model training. The FCN model uses a method of upsampling the values of the convolutional bottom pooling layer and mixing them appropriately so that the output is a pixel heat map rather than a class value. Based on the FCN model, we train a pair of data consisting of input (raw CT image) and results (clinical validated coronary artery segmentation image) to implement an algorithm that approximates the global optimal function.
도 2에는 2차원 단층 이미지에 혈관 영역을 표시한 학습 이미지와 이미지 예측 모델로부터 출력된 예측 이미지가 도시되어 있다.FIG. 2 illustrates a training image in which a blood vessel region is displayed on a two-dimensional tomography image, and a prediction image output from an image prediction model.
도 3 및 도 4 에는 본 발명에 따른 방법의 흐름도가 도시되어 있다. 본 발명에 따른 3차원 혈관 모델 생성방법은 복수의 2차원 단층 영상을 입력받는 단계와, 입력받은 복수의 2차원 단층 영상을 전처리하여 관상동맥이 위치하는 영역을 표시하여 학습 이미지 데이타를 생성하는 단계를 포함한다.3 and 4 show flowcharts of the method according to the invention. In the method of generating a 3D blood vessel model according to the present invention, a step of receiving a plurality of 2D tomography images and preprocessing the plurality of input 2D tomography images to generate a training image data by displaying a region where a coronary artery is located It includes.
또한, 생성된 학습 이미지 데이타로 학습하여 관상동맥 특징 이미지 예측 모델을 생성하는 단계와, 복수의 2차원 단층 이미지를 상기 생성된 관상동맥 특징 이미지 예측 모델에 입력하여 관상동맥 특징 표시 복수의 2차원 단층 이미지를 출력 받는 단계를 포함한다.The method may further include generating a coronary feature image prediction model by learning from the generated training image data, and inputting a plurality of two-dimensional tomographic images to the generated coronary feature image prediction model to display a coronary artery feature display. Receiving an image.
또한, 상기 출력된 관상동맥 특징 표시 복수의 2차원 단층이미지를 이용하여 관상동맥 3차원 형상을 생성하는 단계를 포함한다. 상기 관상동맥 특징 이미지 예측모델을 학습하는 단계는 FCN(Fully Convolutional Network) 알고리즘 또는 지도학습(Supervised Learning) 알고리즘을 사용한다.The method may further include generating a coronary artery 3D shape using the output coronary artery feature display plurality of 2D tomography images. The learning of the coronary artery feature image prediction model uses a fully convolutional network (FCN) algorithm or a supervised learning algorithm.
Claims (2)
복수의 2차원 단층 영상을 입력받는 단계와,
입력받은 복수의 2차원 단층 영상을 전처리하여 관상동맥이 위치하는 영역을 표시하여 학습 이미지 데이타를 생성하는 단계와,
생성된 학습 이미지 데이타로 학습하여 관상동맥 특징 이미지 예측 모델을 생성하는 단계와,
복수의 2차원 단층 이미지를 상기 생성된 관상동맥 특징 이미지 예측 모델에 입력하여 관상동맥 특징 표시 복수의 2차원 단층 이미지를 출력 받는 단계를 포함하고,
상기 출력된 관상동맥 특징 표시 복수의 2차원 단층이미지를 이용하여 관상동맥 3차원 형상을 생성하는 단계를 포함하는 혈관의 3차원 모델 생성 방법.Using a computer system to generate a three-dimensional model of blood vessels,
Receiving a plurality of two-dimensional tomographic images;
Generating a training image data by pre-processing a plurality of input 2D tomography images to display an area where a coronary artery is located;
Learning from the generated training image data to generate a coronary feature image prediction model;
Inputting a plurality of 2D tomographic images to the generated coronary feature image prediction model and receiving a plurality of 2D tomographic images displaying coronary artery features;
And generating a coronary artery three-dimensional shape using the output coronary artery feature display plurality of two-dimensional tomography images.
상기 관상동맥 특징 이미지 예측모델을 학습하는 단계는 FCN(Fully Convolutional Network) 알고리즘 또는 지도학습(Supervised Learning) 알고리즘을 사용하는 혈관의 3차원 모델 생성 방법.The method of claim 1,
The training of the coronary artery feature image prediction model may include generating a three-dimensional model of a blood vessel using a fully convolutional network (FCN) algorithm or a supervised learning algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020180049580A KR20190125592A (en) | 2018-04-30 | 2018-04-30 | 3D Blood Vessel Construction Method using medical images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020180049580A KR20190125592A (en) | 2018-04-30 | 2018-04-30 | 3D Blood Vessel Construction Method using medical images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| KR20190125592A true KR20190125592A (en) | 2019-11-07 |
Family
ID=68579114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020180049580A KR20190125592A (en) | 2018-04-30 | 2018-04-30 | 3D Blood Vessel Construction Method using medical images |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR20190125592A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037170A (en) * | 2020-07-23 | 2020-12-04 | 上海交通大学附属第六人民医院 | Method and device for detecting vascular stenosis and computer storage medium |
| KR20220005326A (en) * | 2020-07-06 | 2022-01-13 | 메디컬아이피 주식회사 | Method for analyzing human tissue based on medical image and apparatus therefor |
| KR20220125853A (en) * | 2021-03-04 | 2022-09-15 | 에이아이메딕(주) | Method for generating a three-dimensional blood vessel model from two dimensional angiographic images using deep learning |
| KR20230059454A (en) * | 2021-10-26 | 2023-05-03 | 이화여자대학교 산학협력단 | Deep learning based vascular invasion classification method for pancreatic cancer using endoscopic ultrasound image and analysis apparatus |
-
2018
- 2018-04-30 KR KR1020180049580A patent/KR20190125592A/en not_active Application Discontinuation
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20220005326A (en) * | 2020-07-06 | 2022-01-13 | 메디컬아이피 주식회사 | Method for analyzing human tissue based on medical image and apparatus therefor |
| WO2022010075A1 (en) * | 2020-07-06 | 2022-01-13 | 메디컬아이피 주식회사 | Method for analyzing human tissue on basis of medical image and device thereof |
| CN112037170A (en) * | 2020-07-23 | 2020-12-04 | 上海交通大学附属第六人民医院 | Method and device for detecting vascular stenosis and computer storage medium |
| KR20220125853A (en) * | 2021-03-04 | 2022-09-15 | 에이아이메딕(주) | Method for generating a three-dimensional blood vessel model from two dimensional angiographic images using deep learning |
| KR20230059454A (en) * | 2021-10-26 | 2023-05-03 | 이화여자대학교 산학협력단 | Deep learning based vascular invasion classification method for pancreatic cancer using endoscopic ultrasound image and analysis apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11806189B2 (en) | Three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging | |
| US11847781B2 (en) | Systems and methods for medical acquisition processing and machine learning for anatomical assessment | |
| US20230033594A1 (en) | System and method for image-based object modeling using multiple image acquisitions or reconstructions | |
| US9514530B2 (en) | Systems and methods for image-based object modeling using multiple image acquisitions or reconstructions | |
| US10098602B2 (en) | Apparatus and method for processing a medical image of a body lumen | |
| JP5295562B2 (en) | Flexible 3D rotational angiography-computed tomography fusion method | |
| KR20190125592A (en) | 3D Blood Vessel Construction Method using medical images | |
| US10580181B2 (en) | Method and system for generating color medical image based on combined color table | |
| KR102032611B1 (en) | Method and application for determining cardiovascular disease using ct image | |
| KR20130023735A (en) | Method and apparatus for generating organ medel image | |
| Tmenova et al. | CycleGAN for style transfer in X-ray angiography | |
| US10032293B2 (en) | Computed tomography (CT) apparatus and method of reconstructing CT image | |
| KR20160050326A (en) | Image processing apparatus and image processing method, and ultrasound apparatus | |
| EP2886057B1 (en) | Medical imaging apparatus and method of reconstructing medical image | |
| KR20190125793A (en) | 3D Blood Vessel Construction Method using medical images | |
| Mahmood et al. | Rapid segmentation of thoracic organs using u-net architecture | |
| Wang | Medical Imaging in Increasing Dimensions | |
| Di Ruberto et al. | Special Issue on Image Processing Techniques for Biomedical Applications | |
| Seyyedi et al. | Evaluation of low-dose CT perfusion for the liver using reconstruction of difference | |
| Wu et al. | Stationary multi-source AI-powered real-time tomography (SMART) | |
| Grace Anabela | Three-dimensional (3D) reconstruction of ultrasound foetal images using visualisation toolkit (VTK)/Grace Anabela Henry Dusim | |
| Grandhe et al. | Fusion Based Integrated Advance Magnetic Visualization of MRI 3D Images Using Advance Matlab Tools | |
| Chen | Development and validation of vascular image processing techniques for image-guided neurovascular surgery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A201 | Request for examination | ||
| E902 | Notification of reason for refusal | ||
| E601 | Decision to refuse application |