WO2023133933A1 - 超声颅脑标准面成像和异常区域自动检测显示方法 - Google Patents

超声颅脑标准面成像和异常区域自动检测显示方法 Download PDF

Info

Publication number
WO2023133933A1
WO2023133933A1 PCT/CN2022/073404 CN2022073404W WO2023133933A1 WO 2023133933 A1 WO2023133933 A1 WO 2023133933A1 CN 2022073404 W CN2022073404 W CN 2022073404W WO 2023133933 A1 WO2023133933 A1 WO 2023133933A1
Authority
WO
WIPO (PCT)
Prior art keywords
standard
ultrasonic
plane
feature data
surface model
Prior art date
Application number
PCT/CN2022/073404
Other languages
English (en)
French (fr)
Inventor
范列湘
蔡泽杭
李斌
吴钟鸿
王煜
林锦豪
周晓明
陈少辉
陈炜武
郭境峰
陈伊婕
陈梓淳
Original Assignee
汕头市超声仪器研究所股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 汕头市超声仪器研究所股份有限公司 filed Critical 汕头市超声仪器研究所股份有限公司
Publication of WO2023133933A1 publication Critical patent/WO2023133933A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
    • A61B8/0808—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the brain
    • A61B8/0816—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the brain using echo-encephalography
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
    • A61B8/0808—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the brain
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/13—Tomography
    • A61B8/14—Echo-tomography
    • A61B8/145—Echo-tomography characterised by scanning multiple planes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
    • A61B8/4477—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device using several separate ultrasound transducers or probes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/46—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient
    • A61B8/461—Displaying means of special interest
    • A61B8/466—Displaying means of special interest adapted to display 3D data
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/523—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for generating planar views from image data in a user selectable plane not corresponding to the acquisition plane
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/30—Polynomial surface description
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/48—Diagnostic techniques
    • A61B8/483—Diagnostic techniques involving the acquisition of a 3D volume of data
    • 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
    • G06T2207/10132—Ultrasound image
    • 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
    • G06T2207/10132—Ultrasound image
    • G06T2207/10136—3D ultrasound image
    • 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
    • G06T2207/30016—Brain

Definitions

  • the invention relates to the field of ultrasonic detection, in particular to an ultrasonic cranial standard surface imaging and abnormal area automatic detection and display method.
  • Brain ultrasonography is a routine clinical practice and is mainly used in the clinical monitoring of newborns. It is mainly used for intraventricular hemorrhage, pericerebral hemorrhage infarction, ventriculomegaly after hemorrhage, and fluidic pericerebral leukomalacia/paralysis after hemorrhage.
  • sonographers rely on knowledge and experience to identify abnormalities in images.
  • using computer to automatically analyze and diagnose images can reduce the burden of doctors' diagnosis and improve efficiency.
  • the results of analyzing and diagnosing brain ultrasound images using traditional image processing techniques and popular machine learning methods are not ideal, and there are problems such as low recognition accuracy and error-prone.
  • the purpose of the present invention is to provide a method for standard ultrasonic imaging of cranial brain and automatic detection and display of abnormal areas, specifically to provide a method that can automatically determine and extract standard ultrasonic images using cranial ultrasonic images, and utilize the symmetry of standard ultrasonic images A method for detecting abnormal regions and segmenting and displaying them.
  • the present invention adopts the following technical solution: a method for standard ultrasonic cranial imaging and automatic detection and display of abnormal regions, including the following steps: S01. Constructing a cranial surface model based on the ultrasonic image obtained by ultrasonic scanning of the cranial brain.
  • step S04 Calculating the histogram or the gray level co-occurrence matrix of the ultrasonic image of the standard plane extracted in step S03, and performing normalization processing to extract feature data.
  • the reference feature data in step S05 is the feature data extracted in accordance with step S04 from standard ultrasonic images that are clinically confirmed to have no abnormalities.
  • step S04 the ultrasonic image of the standard plane is divided into two symmetrical parts. Carry out the calculation of histogram or gray scale co-occurrence matrix respectively in each area again, and do normalization processing to extract feature data; The feature data is calculated for similarity comparison.
  • step S05 the feature data obtained by extracting two mutually symmetrical regions is also compared with the feature data obtained by extracting the feature data obtained by step S04 as the reference feature data of the standard ultrasound image clinically confirmed to have no abnormalities.
  • the calculation of the pair, and the segmentation and display of the abnormal area are respectively carried out according to step S06.
  • a 3D ultrasonic image scan is performed on the cranium, detection is performed based on the obtained 3D ultrasonic image, and a curved surface model of the cranium is constructed.
  • a 2D ultrasonic image scan is performed on the brain, and the collected 2D ultrasonic images are detected using gray scale or gray scale plus gray scale gradient values to detect the cranium and skull.
  • the boundary of the internal tissue of the brain, and the boundary between the cranium and the internal tissue of the cranium detected by multi-frame 2D ultrasound images is filtered and fitted to construct a complete cranial surface model.
  • the present invention has the advantages of: building a curved surface model of the cranium by detecting the edge of the cranium, and establishing a coordinate system with this model, so that the ultrasonic image of the standard plane can be quickly determined from the ultrasonic image obtained by scanning; at the same time, the symmetry of the ultrasonic image of the standard plane can be used It can quickly and accurately detect abnormal areas in ultrasound images and display them in segments, providing efficient and accurate image analysis for cranial ultrasound scans.
  • Embodiment 1 a method for standard ultrasound imaging of the brain and automatic detection and display of abnormal regions, comprising the following steps: S01. Constructing a cranial surface model based on the ultrasound image obtained by ultrasonic scanning of the brain.
  • step S04 Calculating the histogram or the gray level co-occurrence matrix of the ultrasonic image of the standard plane extracted in step S03, and performing normalization processing to extract feature data.
  • the reference feature data in step S05 is the feature data extracted according to step S04 from the standard ultrasonic image that is clinically confirmed to have no abnormalities.
  • a 3D ultrasonic image scan of the cranium can be performed, and detection can be performed based on the obtained 3D ultrasonic image to construct a curved surface model of the cranium; a 2D ultrasonic image scan can also be performed on the cranium, and the The collected 2D ultrasound images use grayscale or grayscale plus grayscale gradient values to detect the boundary between the cranium and the internal tissue of the cranium, and use the boundary between the cranium and the internal tissue of the cranium detected by multi-frame 2D ultrasound images to filter and Fitting constructs a complete skull surface model.
  • Embodiment 2 a method for standard ultrasound imaging of the cranium and automatic detection and display of abnormal regions, comprising the following steps: S01. Constructing a cranial surface model based on the ultrasound image obtained by ultrasonic scanning of the cranium.
  • step S04 Calculating the histogram or the gray level co-occurrence matrix of the ultrasonic image of the standard plane extracted in step S03, and performing normalization processing to extract feature data.
  • step S03 the standard plane ultrasonic image extracted in step S03 is symmetrical with respect to the median sagittal plane or the median coronal plane
  • step S04 the standard plane ultrasonic image is divided into two mutually symmetrical regions and then respectively performed Calculation of histogram or gray-level co-occurrence matrix, and normalization processing to extract feature data
  • step S05 feature data extracted from two mutually symmetrical regions of the standard plane ultrasound image are used as reference feature data for similarity Alignment calculations.
  • a 3D ultrasonic image scan of the cranium can be performed, and detection can be performed based on the obtained 3D ultrasonic image to construct a curved surface model of the cranium; a 2D ultrasonic image scan can also be performed on the cranium, and the The collected 2D ultrasound images use grayscale or grayscale plus grayscale gradient values to detect the boundary between the cranium and the internal tissue of the cranium, and use the boundary between the cranium and the internal tissue of the cranium detected by multi-frame 2D ultrasound images to filter and Fitting constructs a complete skull surface model.
  • Embodiment 3 a method for standard ultrasound imaging of the cranium and automatic detection and display of abnormal regions, comprising the following steps: S01. Constructing a cranial surface model based on the ultrasound image obtained by ultrasonic scanning of the cranium.
  • step S04 Calculating the histogram or the gray level co-occurrence matrix of the ultrasonic image of the standard plane extracted in step S03, and performing normalization processing to extract feature data.
  • step S04 the standard plane ultrasonic image is divided into two mutually symmetrical regions and then respectively performed Calculation of the histogram or gray level co-occurrence matrix, and normalization processing to extract the feature data; in step S05, the feature data obtained by extracting two mutually symmetrical areas and the standard ultrasound image clinically confirmed to have no abnormalities
  • the feature data extracted according to step S04 is used as the reference feature data to calculate the similarity comparison, and then the feature data extracted from the two mutually symmetrical regions of the standard plane ultrasonic image are used as reference feature data to calculate the similarity comparison ; Then segment and display the abnormal area according to step S06 respectively in the two comparison methods, so as to obtain a more comprehensive and accurate abnormal area detection result.
  • a 3D ultrasonic image scan of the cranium can be performed, and detection can be performed based on the obtained 3D ultrasonic image to construct a curved surface model of the cranium; a 2D ultrasonic image scan can also be performed on the cranium, and the The collected 2D ultrasound images use grayscale or grayscale plus grayscale gradient values to detect the boundary between the cranium and the internal tissue of the cranium, and use the boundary between the cranium and the internal tissue of the cranium detected by multi-frame 2D ultrasound images to filter and Fitting constructs a complete skull surface model.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Pathology (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Graphics (AREA)
  • Neurology (AREA)
  • Quality & Reliability (AREA)
  • General Engineering & Computer Science (AREA)
  • Gynecology & Obstetrics (AREA)
  • Mathematical Physics (AREA)
  • Physiology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Mathematical Analysis (AREA)
  • Algebra (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)
  • Surgical Instruments (AREA)

Abstract

一种超声颅脑标准面成像和异常区域自动检测显示方法。方法包括：将对颅脑进行扫查得到的超声图像进行边缘检测构建头盖骨曲面模型，根据头盖骨曲面模型确定并提取标准面超声图像，并利用标准面超声图像的对称性进行相似度比对，以此得到异常区域并进行分割显示。通过对头盖骨边缘进行检测以构建头盖骨曲面模型，以此模型建立坐标系，从而可以从扫查得到的超声图像中快速确定标准面超声图像；同时利用标准面超声图像的对称性进行相似度比对，可以快速准确地检测超声图像中的异常区域并分割显示出来，为颅脑超声扫查提供高效准确的图像分析。　

Description

超声颅脑标准面成像和异常区域自动检测显示方法 技术领域
本发明涉及超声检测领域，尤其涉及一种超声颅脑标准面成像和异常区域自动检测显示方法。
 背景技术
颅脑超声扫查是一项常规临床实践，被主要应用于新生儿的临床监护中。其主要用于脑室内出血、脑周出血梗塞、出血后脑室扩张、出血后液性脑周白质软化/麻痹等。在传统技术中，超声医生依靠知识和经验来识别图像的异常情况。随着计算机技术的不断发展，利用计算机对图像进行自动分析和诊断可以为医生的诊断减轻负担并提高效率。然而采用传统的图像处理技术和目前流行的机器学习方法对颅脑超声图像进行分析和诊断的效果并不理想，存在识别精度低、容易出错等问题。
 技术问题
本发明的目的在于提供一种超声颅脑标准面成像和异常区域自动检测显示方法，具体在于提供一种可利用颅脑超声图像自动确定并提取标准面超声图像，并利用标准面超声图像的对称性对异常区域进行检测并分割显示的方法。
为达到上述目的，本发明采用如下技术方案：一种超声颅脑标准成像和异常区域自动检测显示方法，包括如下步骤：S01、根据对颅脑进行超声扫查得到的超声图像构建头盖骨曲面模型。
S02、根据步骤S01构建的头盖骨曲面模型确定该头盖骨曲面模型的正中矢状面和正中冠状面，同时将正中矢状面和正中冠状面与头盖骨曲面模型的交点标记为坐标原点，并建立坐标系。
S03、在构建的头盖骨曲面模型和坐标系上标出设定的标准面的位置，并从扫查得到的超声图像中找到对应于临床定义的多个标准面位置的超声图像并提取出来。
S04、将步骤S03提取出来的标准面超声图像进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据。
S05、将提取的特征数据与参考特征数据进行相似度比对的计算。
S06、当提取的特征数据与参考特征数据存在差异时，则提取出差异处对应的灰阶值，并以该灰机值为引导，在对应的标准面超声图像上分割出异常区域并显示。
具体的，步骤S05中参考特征数据为临床确认无异常情况的标准面超声图像按照步骤S04提取得到的特征数据。
在另一种方案中，若步骤S03中提取出的标准面超声图像为相对于正中矢状面或正中冠状面对称时，则在步骤S04中将该标准面超声图像分为互相对称的两个区域再分别进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据；并在步骤S05中将该标准面超声图像两个互相对称的区域提取的特征数据互为参考特征数据进行相似度比对的计算。
具体的，在步骤S05中，还同时将两个互相对称的区域提取得到的特征数据与临床确认无异常情况的标准面超声图像按照步骤S04提取得到的特征数据作为的参考特征数据进行相似度比对的计算，并分别按照步骤S06进行异常区域的分割和显示。
具体的，步骤S01中构建头盖骨曲面模型时，对颅脑进行3D超声图像扫查并根据得到的3D超声图像进行检测并构建头盖骨曲面模型。
在另一种方案中，步骤S01中构建头盖骨曲面模型时，对颅脑进行2D超声图像扫查，对采集得到的2D超声图像利用灰阶或灰阶加灰阶梯度值的方式检测头盖骨与颅脑内部组织的边界，并利用多帧2D超声图像检测得到的头盖骨与颅脑内部组织的边界进行滤波和拟合构建完整的头盖骨曲面模型。
本发明的优点在于： 通过对头盖骨边缘进行检测以构建头盖骨曲面模型，以此模型建立坐标系，从而可以从扫查得到的超声图像中快速确定标准面超声图像；同时利用标准面超声图像的对称性进行相似度比对，可以快速准确地检测超声图像中的异常区域并分割显示出来，为颅脑超声扫查提供高效准确的图像分析。
 附图说明
附图1为实施例1-3中头盖骨曲面模型及正中矢状面、正中冠状面和坐标系的位置关系图。
 具体实施方式
实施例1，一种超声颅脑标准成像和异常区域自动检测显示方法，包括如下步骤：S01、根据对颅脑进行超声扫查得到的超声图像构建头盖骨曲面模型。
S02、根据步骤S01构建的头盖骨曲面模型确定该头盖骨曲面模型的正中矢状面和正中冠状面，同时将正中矢状面和正中冠状面与头盖骨曲面模型的交点标记为坐标原点，并建立坐标系。
S03、在构建的头盖骨曲面模型和坐标系上标出设定的标准面的位置，并从扫查得到的超声图像中找到对应于临床定义的多个标准面位置的超声图像并提取出来。
S04、将步骤S03提取出来的标准面超声图像进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据。
S05、将提取的特征数据与参考特征数据进行相似度比对的计算。
S06、当提取的特征数据与参考特征数据存在差异时，则提取出差异处对应的灰阶值，并以该灰机值为引导，在对应的标准面超声图像上分割出异常区域并显示。
在本实施例中，步骤S05中参考特征数据为临床确认无异常情况的标准面超声图像按照步骤S04提取得到的特征数据。
具体的，步骤S01中构建头盖骨曲面模型时，可以对颅脑进行3D超声图像扫查并根据得到的3D超声图像进行检测并构建头盖骨曲面模型；也可以对颅脑进行2D超声图像扫查，对采集得到的2D超声图像利用灰阶或灰阶加灰阶梯度值的方式检测头盖骨与颅脑内部组织的边界，并利用多帧2D超声图像检测得到的头盖骨与颅脑内部组织的边界进行滤波和拟合构建完整的头盖骨曲面模型。
实施例2，一种超声颅脑标准成像和异常区域自动检测显示方法，包括如下步骤：S01、根据对颅脑进行超声扫查得到的超声图像构建头盖骨曲面模型。
S02、根据步骤S01构建的头盖骨曲面模型确定该头盖骨曲面模型的正中矢状面和正中冠状面，同时将正中矢状面和正中冠状面与头盖骨曲面模型的交点标记为坐标原点，并建立坐标系。
S03、在构建的头盖骨曲面模型和坐标系上标出设定的标准面的位置，并从扫查得到的超声图像中找到对应于临床定义的多个标准面位置的超声图像并提取出来。
S04、将步骤S03提取出来的标准面超声图像进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据。
S05、将提取的特征数据与参考特征数据进行相似度比对的计算。
S06、当提取的特征数据与参考特征数据存在差异时，则提取出差异处对应的灰阶值，并以该灰机值为引导，在对应的标准面超声图像上分割出异常区域并显示。
其中，若步骤S03中提取出的标准面超声图像为相对于正中矢状面或正中冠状面对称时，则在步骤S04中将该标准面超声图像分为互相对称的两个区域再分别进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据；并在步骤S05中将该标准面超声图像两个互相对称的区域提取的特征数据互为参考特征数据进行相似度比对的计算。
具体的，步骤S01中构建头盖骨曲面模型时，可以对颅脑进行3D超声图像扫查并根据得到的3D超声图像进行检测并构建头盖骨曲面模型；也可以对颅脑进行2D超声图像扫查，对采集得到的2D超声图像利用灰阶或灰阶加灰阶梯度值的方式检测头盖骨与颅脑内部组织的边界，并利用多帧2D超声图像检测得到的头盖骨与颅脑内部组织的边界进行滤波和拟合构建完整的头盖骨曲面模型。
实施例3，一种超声颅脑标准成像和异常区域自动检测显示方法，包括如下步骤：S01、根据对颅脑进行超声扫查得到的超声图像构建头盖骨曲面模型。
S02、根据步骤S01构建的头盖骨曲面模型确定该头盖骨曲面模型的正中矢状面和正中冠状面，同时将正中矢状面和正中冠状面与头盖骨曲面模型的交点标记为坐标原点，并建立坐标系。
S03、在构建的头盖骨曲面模型和坐标系上标出设定的标准面的位置，并从扫查得到的超声图像中找到对应于临床定义的多个标准面位置的超声图像并提取出来。
S04、将步骤S03提取出来的标准面超声图像进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据。
S05、将提取的特征数据与参考特征数据进行相似度比对的计算。
S06、当提取的特征数据与参考特征数据存在差异时，则提取出差异处对应的灰阶值，并以该灰机值为引导，在对应的标准面超声图像上分割出异常区域并显示。
其中，若步骤S03中提取出的标准面超声图像为相对于正中矢状面或正中冠状面对称时，则在步骤S04中将该标准面超声图像分为互相对称的两个区域再分别进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据；在步骤S05中，先将两个互相对称的区域提取得到的特征数据与临床确认无异常情况的标准面超声图像按照步骤S04提取得到的特征数据作为的参考特征数据进行相似度比对的计算，再将该标准面超声图像两个互相对称的区域提取的特征数据互为参考特征数据进行相似度比对的计算；然后将两种比对方式分别按照步骤S06进行异常区域的分割和显示，以此得到更全面更准确的异常区域检测结果。
具体的，步骤S01中构建头盖骨曲面模型时，可以对颅脑进行3D超声图像扫查并根据得到的3D超声图像进行检测并构建头盖骨曲面模型；也可以对颅脑进行2D超声图像扫查，对采集得到的2D超声图像利用灰阶或灰阶加灰阶梯度值的方式检测头盖骨与颅脑内部组织的边界，并利用多帧2D超声图像检测得到的头盖骨与颅脑内部组织的边界进行滤波和拟合构建完整的头盖骨曲面模型。
当然，以上仅为本发明较佳实施方式，并非以此限定本发明的使用范围，故，凡是在本发明原理上做等效改变均应包含在本发明的保护范围内。

Claims (6)

  1. 一种超声颅脑标准成像和异常区域自动检测显示方法，其特征在于，包括如下步骤：
    S01、根据对颅脑进行超声扫查得到的超声图像构建头盖骨曲面模型；
    S02、根据步骤S01构建的头盖骨曲面模型确定该头盖骨曲面模型的正中矢状面和正中冠状面，同时将正中矢状面和正中冠状面与头盖骨曲面模型的交点标记为坐标原点，并建立坐标系；
    S03、在构建的头盖骨曲面模型和坐标系上标出设定的标准面的位置，并从扫查得到的超声图像中找到对应于临床定义的多个标准面位置的超声图像并提取出来；
    S04、将步骤S03提取出来的标准面超声图像进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据；
    S05、将提取的特征数据与参考特征数据进行相似度比对的计算；
    S06、当提取的特征数据与参考特征数据存在差异时，则提取出差异处对应的灰阶值，并以该灰机值为引导，在对应的标准面超声图像上分割出异常区域并显示。
  2. 根据权利要求1所述的一种超声颅脑标准面成像和异常区域自动检测显示方法，其特征在于：所述步骤S05中参考特征数据为临床确认无异常情况的标准面超声图像按照步骤S04提取得到的特征数据。
  3. 根据权利要求1所述的一种超声颅脑标准面成像和异常区域自动检测显示方法，其特征在于：若步骤S03中提取出的标准面超声图像为相对于正中矢状面或正中冠状面对称时，则在步骤S04中将该标准面超声图像分为互相对称的两个区域再分别进行直方图或灰度共生矩阵的计算，并做归一化处理以提取特征数据；并在步骤S05中将该标准面超声图像两个互相对称的区域提取的特征数据互为参考特征数据进行相似度比对的计算。
  4. 根据权利要求3所述的一种超声标准面成像和异常区域自动检测显示方法，其特征在于：在步骤S05中，还同时将两个互相对称的区域提取得到的特征数据与临床确认无异常情况的标准面超声图像按照步骤S04提取得到的特征数据作为的参考特征数据进行相似度比对的计算，并分别按照步骤S06进行异常区域的分割和显示。
  5. 根据权利要求1-4任一项所述的一种超声标准面成像和异常区域自动检测显示方法，其特征在于：所述步骤S01中构建头盖骨曲面模型时，对颅脑进行3D超声图像扫查并根据得到的3D超声图像进行检测并构建头盖骨曲面模型。
  6. 根据权利要求1-4任一项所述的一种超声标准面成像和异常区域自动检测显示方法，其特征在于：所述步骤S01中构建头盖骨曲面模型时，对颅脑进行2D超声图像扫查，对采集得到的2D超声图像利用灰阶或灰阶加灰阶梯度值的方式检测头盖骨与颅脑内部组织的边界，并利用多帧2D超声图像检测得到的头盖骨与颅脑内部组织的边界进行滤波和拟合构建完整的头盖骨曲面模型。。
PCT/CN2022/073404 2022-01-14 2022-01-24 超声颅脑标准面成像和异常区域自动检测显示方法 WO2023133933A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210042598.5 2022-01-14
CN202210042598.5A CN114418981A (zh) 2022-01-14 2022-01-14 超声颅脑标准面成像和异常区域自动检测显示方法

Publications (1)

Publication Number Publication Date
WO2023133933A1 true WO2023133933A1 (zh) 2023-07-20

Family

ID=81274379

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/073404 WO2023133933A1 (zh) 2022-01-14 2022-01-24 超声颅脑标准面成像和异常区域自动检测显示方法

Country Status (3)

Country Link
US (1) US20230225700A1 (zh)
CN (1) CN114418981A (zh)
WO (1) WO2023133933A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070280518A1 (en) * 2003-12-12 2007-12-06 Nowinski Wieslaw L Method and Apparatus for Identifying Pathology in Brain Images
CN110322550A (zh) * 2015-02-16 2019-10-11 深圳迈瑞生物医疗电子股份有限公司 三维成像数据的显示处理方法和三维超声成像方法及系统
CN111368586A (zh) * 2018-12-25 2020-07-03 深圳迈瑞生物医疗电子股份有限公司 超声成像方法及系统
CN111462055A (zh) * 2020-03-19 2020-07-28 沈阳先进医疗设备技术孵化中心有限公司 颅骨检测方法及装置
CN113077479A (zh) * 2021-03-25 2021-07-06 深圳市铱硙医疗科技有限公司 急性缺血性脑卒中病灶自动分割方法、系统、终端及介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070280518A1 (en) * 2003-12-12 2007-12-06 Nowinski Wieslaw L Method and Apparatus for Identifying Pathology in Brain Images
CN110322550A (zh) * 2015-02-16 2019-10-11 深圳迈瑞生物医疗电子股份有限公司 三维成像数据的显示处理方法和三维超声成像方法及系统
CN111368586A (zh) * 2018-12-25 2020-07-03 深圳迈瑞生物医疗电子股份有限公司 超声成像方法及系统
CN111462055A (zh) * 2020-03-19 2020-07-28 沈阳先进医疗设备技术孵化中心有限公司 颅骨检测方法及装置
CN113077479A (zh) * 2021-03-25 2021-07-06 深圳市铱硙医疗科技有限公司 急性缺血性脑卒中病灶自动分割方法、系统、终端及介质

Also Published As

Publication number Publication date
CN114418981A (zh) 2022-04-29
US20230225700A1 (en) 2023-07-20

Similar Documents

Publication Publication Date Title
Loizou A review of ultrasound common carotid artery image and video segmentation techniques
EP3164062B1 (en) Detecting tooth wear using intra-oral 3d scans
Aggarwal et al. Feature extraction and LDA based classification of lung nodules in chest CT scan images
CN110338840B (zh) 三维成像数据的显示处理方法和三维超声成像方法及系统
EP2365356B1 (en) Three-dimensional (3D) ultrasound system for scanning object inside human body and method for operating 3D ultrasound system
TWI473598B (zh) Breast ultrasound image scanning and diagnostic assistance system
Molinari et al. Hypothesis validation of far-wall brightness in carotid-artery ultrasound for feature-based IMT measurement using a combination of level-set segmentation and registration
CN110279433A (zh) 一种基于卷积神经网络的胎儿头围自动精确测量方法
WO2024067527A1 (zh) 一种髋关节角度检测系统和方法
CN103455821B (zh) 基于bi-rads的图像分析装置和方法
Loizou et al. Segmentation of atherosclerotic carotid plaque in ultrasound video
JP5624505B2 (ja) 画像処理装置
Zeng et al. TUSPM-NET: A multi-task model for thyroid ultrasound standard plane recognition and detection of key anatomical structures of the thyroid
WO2023133935A1 (zh) 超声颅脑异常区域自动检测及显示方法
JP2011251113A (ja) ３次元超音波診断装置およびその操作方法
CN115690556B (zh) 一种基于多模态影像学特征的图像识别方法及系统
CN111481233B (zh) 胎儿颈项透明层厚度测量方法
WO2023133933A1 (zh) 超声颅脑标准面成像和异常区域自动检测显示方法
Somasundaram et al. Fetal head localization and fetal brain segmentation from MRI using the center of gravity
WO2023133929A1 (zh) 一种基于超声的人体组织对称性检测分析方法
Cao et al. Liver fibrosis identification based on ultrasound images
Nirmala et al. Clinical decision support system for early prediction of Down syndrome fetus using sonogram images
Ni et al. Angle closure glaucoma detection using fractal dimension index on SS-OCT images
Nirmala et al. Measurement of nuchal translucency thickness in first trimester ultrasound fetal images for detection of chromosomal abnormalities
CN110916724A (zh) 一种基于闭环最短路径的b超图像胎儿头围检测方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22919579

Country of ref document: EP

Kind code of ref document: A1