WO2023133935A1 - 超声颅脑异常区域自动检测及显示方法 - Google Patents

超声颅脑异常区域自动检测及显示方法 Download PDF

Info

Publication number
WO2023133935A1
WO2023133935A1 PCT/CN2022/073430 CN2022073430W WO2023133935A1 WO 2023133935 A1 WO2023133935 A1 WO 2023133935A1 CN 2022073430 W CN2022073430 W CN 2022073430W WO 2023133935 A1 WO2023133935 A1 WO 2023133935A1
Authority
WO
WIPO (PCT)
Prior art keywords
cranial
image
surface model
cranium
ultrasonic
Prior art date
Application number
PCT/CN2022/073430
Other languages
English (en)
French (fr)
Inventor
范列湘
蔡泽杭
李德来
吴钟鸿
王煜
林锦豪
周晓明
陈少辉
陈炜武
郭境峰
李斌
陈伊婕
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 WO2023133935A1 publication Critical patent/WO2023133935A1/zh
Priority to US18/610,676 priority Critical patent/US20240225587A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/68—Analysis of geometric attributes of symmetry
    • 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
    • A61B8/46—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
    • A61B8/48—Diagnostic techniques
    • A61B8/483—Diagnostic techniques involving the acquisition of a 3D volume of 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
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • 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
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/174—Segmentation; Edge detection involving the use of two or more images
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30008—Bone
    • 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
    • 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
    • G06T2207/30196—Human being; Person

Definitions

  • the invention relates to the field of ultrasonic detection, in particular to a method for automatic detection and display of ultrasonic brain abnormalities.
  • Ultrasound brain scan is a routine clinical practice, especially in the clinical monitoring of newborns is widely used.
  • Ultrasonic cranial scan is mainly used for the diagnosis of intraventricular hemorrhage, pericerebral hemorrhage infarction, ventriculomegaly after hemorrhage, and fluid pericranial leukomalacia/paralysis after hemorrhage.
  • ultrasound doctors rely on knowledge and experience to identify abnormalities in images; with the continuous development of computer technology, using computers to automatically analyze and diagnose images can reduce the burden on doctors' diagnosis and improve efficiency.
  • the reason why traditional processing and popular machine learning methods cannot be effectively applied to cranial ultrasound image analysis and diagnosis lies in the complexity of cranial ultrasound image itself.
  • the gray scale value of the new bleeding point is a high gray scale value, and its range is close to or higher than the gray scale of normal tissue.
  • the gray scale of old bleeding points is low gray scale value, and its range is lower than that of normal tissue.
  • the object of the present invention is to provide a method for automatic detection and display of abnormal areas of the brain by ultrasound, in particular to provide a method for automatic detection and display of abnormal areas of the brain by ultrasound that can improve the diagnostic accuracy.
  • the present invention adopts the following technical scheme: a method for automatic detection and display of abnormal areas of the brain by ultrasound, comprising the following steps: S01, first constructing a curved surface model of the skull, and constructing the model according to the ultrasound image obtained by ultrasonic scanning of the brain Surface model of the skull.
  • S02. Perform cranial edge detection on the 2D ultrasonic image obtained by ultrasonic scanning of the cranium to obtain a cranial edge curve of the 2D image.
  • step S04 According to the position of the 2D image obtained in step S03 on the curved skull model, it is judged whether the 2D image is symmetrical with respect to the midsagittal plane or the median coronal plane of the curved skull model.
  • step S05 Mark the 2D images that are symmetrical with respect to the median sagittal plane or the median coronal plane of the cranial curved surface model in step S04, and select 2D images from them for analysis according to analysis requirements.
  • S07. Determine whether there is a difference between the two regions according to the calculated similarity. If there is a difference, extract the corresponding gray scale value of the difference, and use the gray scale value as a guide to segment and mark the abnormal area and display it.
  • the boundary between the skull and brain tissue is detected by using grayscale or grayscale plus grayscale gradient values, and the boundary curve is obtained after filtering and fitting the boundary.
  • the cranium is scanned by 3D ultrasonic images, and the obtained 3D ultrasonic images are scanned by using gray scale or gray scale plus gray scale gradient values
  • the boundary is detected, and the boundary is filtered and fitted to obtain the skull surface model.
  • 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 used for filtering and fitting to construct a complete cranial surface model.
  • the advantages of the present invention are: by establishing a cranial surface model, and detecting the cranial boundary curve of the 2D ultrasonic image, using the cranial boundary curve and the cranial surface model to fit the specific position of the 2D ultrasonic image to select a symmetric 2D ultrasonic image , using the symmetry of the 2D ultrasound image to detect abnormal areas and display them in segments, thereby effectively improving the accuracy of abnormal area identification and detection.
  • Embodiment 1 a method for automatic detection and display of abnormal areas of the brain by ultrasound, comprising the following steps: S01. First construct a curved surface model of the cranium, and construct a curved surface model of the skull according to the ultrasound image obtained by ultrasonic scanning of the brain.
  • S02. Perform cranial edge detection on the 2D ultrasonic image obtained by ultrasonic scanning of the cranium to obtain a cranial edge curve of the 2D image.
  • step S04 According to the position of the 2D image obtained in step S03 on the curved skull model, it is judged whether the 2D image is symmetrical with respect to the midsagittal plane or the median coronal plane of the curved skull model.
  • step S05 Mark the 2D images that are symmetrical with respect to the median sagittal plane or the median coronal plane of the cranial curved surface model in step S04, and select 2D images from them for analysis according to analysis requirements.
  • S07. Determine whether there is a difference between the two regions according to the calculated similarity. If there is a difference, extract the corresponding gray scale value of the difference, and use the gray scale value as a guide to segment and mark the abnormal area and display it.
  • the boundary between the skull and the intracranial tissue is detected by using grayscale or grayscale plus grayscale gradient values, and the boundary is filtered and fitted to obtain the cranial edge curve;
  • the skull in the cranial image has a strong emission, and it presents a high grayscale value in the image.
  • the edge of the image formed after detection is easy to detect.
  • the skull and the brain can be detected by using grayscale or grayscale plus grayscale gradient value together. organizational boundaries.
  • the cranium is scanned by 3D ultrasonic images, and the boundary between the cranium and the intracranial tissue is determined on the obtained 3D ultrasonic images by using grayscale or grayscale plus grayscale gradient values. Detect, and filter and fit the boundary to obtain the skull surface model.
  • Embodiment 2 a method for automatic detection and display of abnormal areas of the brain by ultrasound, comprising the following steps: S01. First construct a curved surface model of the skull, and construct a curved surface model of the skull according to the ultrasound image obtained by ultrasonic scanning of the brain.
  • S02. Perform cranial edge detection on the 2D ultrasonic image obtained by ultrasonic scanning of the cranium to obtain a cranial edge curve of the 2D image.
  • step S04 According to the position of the 2D image obtained in step S03 on the curved skull model, it is judged whether the 2D image is symmetrical with respect to the midsagittal plane or the median coronal plane of the curved skull model.
  • step S05 Mark the 2D images that are symmetrical with respect to the median sagittal plane or the median coronal plane of the cranial curved surface model in step S04, and select 2D images from them for analysis according to analysis requirements.
  • S07. Determine whether there is a difference between the two regions according to the calculated similarity. If there is a difference, extract the corresponding gray scale value of the difference, and use the gray scale value as a guide to segment and mark the abnormal area and display it.
  • the boundary between the skull and the intracranial tissue is detected by using grayscale or grayscale plus grayscale gradient values, and the boundary is filtered and fitted to obtain the cranial edge curve;
  • the skull in the cranial image has a strong emission, and it presents a high grayscale value in the image.
  • the edge of the image formed after detection is easy to detect.
  • the skull and the brain can be detected by using grayscale or grayscale plus grayscale gradient value together. organizational boundaries.
  • the cranium is scanned with 2D ultrasound images, and the acquired 2D ultrasound images are detected using grayscale or grayscale plus grayscale gradient values to detect the boundary between the cranium and the internal tissues of the cranium , and use the multi-frame 2D ultrasound image to detect the boundary between the cranium and the internal tissue of the cranium for filtering and fitting to construct a complete cranial surface model.

Landscapes

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

Abstract

一种超声颅脑异常区域自动检测及显示方法，涉及超声检测领域。该方法包括：先构建头盖骨曲面模型，然后对2D超声图像进行边缘检测得到头盖骨边缘曲线，利用边缘曲线与头盖骨曲面模型进行拟合确定2D超声图像的位置以判断该2D图像是否具备对称特性，最后利用2D图像的对称特性对互相对称的两个区域进行相似度比对计算，以此确定是否存在异常区域及其位置。该方法优点在于：先建立头盖骨曲面模型，并对2D超声图像检测头盖骨边界曲线，利用头盖骨边界曲线与头盖骨曲面模型进行拟合以确定2D图像的具体位置以选取具备对称特性的2D图像，利用2D图像的对称性进行异常区域的检测并分割显示出来，从而有效提高异常区域检测的准确率。

Description

超声颅脑异常区域自动检测及显示方法 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异常区域自动检测及显示方法。
 背景技术
超声颅脑扫查是一箱常规临床实践，尤其在新生儿临床监护中被广泛应用。超声颅脑扫查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/麻痹等症状的诊断。传统诊断中，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，传统处理和流行的机器学习方法不能有效应用于颅脑超声图像分析和诊断的原因在于颅脑超声图像本身的复杂性。这个复杂性表现在颅脑图像的灰阶值在出现异常时有不确定性，即新出血点的灰阶为高灰阶值，其范围接近或高于正常组织的灰阶。成旧的出血点的灰阶为低灰阶值，其范围低于正常组织的灰阶。
 技术问题
本发明的目的在于提供一种超声颅脑异常区域自动检测及显示方法，具体在于提供一种可提高诊断准确率的超声颅脑异常区域自动检测显示方法。
为达到上述目的，本发明采用如下技术方案：一种超声颅脑异常区域自动检测及显示方法，包括如下步骤：S01、先构建头盖骨曲面模型，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、将对颅脑进行超声扫查得到的2D超声图像进行头盖骨边缘检测，得到该2D图像的头盖骨边缘曲线。
S03、将步骤S02得到的2D图像的头盖骨边缘曲线与步骤S01得到的头盖骨曲面模型进行适配以确定该2D图像在头盖骨曲面模型上的位置。
S04、根据步骤S03得到的2D图像在头盖骨曲面模型上的位置判断该2D图像是否相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性。
S05、将步骤S04中相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性的2D图像进行标记，并根据分析需求从其中选取2D图像进行分析。
S06、对2D图像进行分析时，先将该2D图像分成互相对称的两个区域，分别对两个区域的图像做直方图统计或求灰度共生矩阵得到统计数据，接着对两个区域的统计数据做归一化处理提取特征数据，然后对两个区域的特征数据进行相似度比对计算。
S07、根据计算得到的相似度判断两个区域是否存在差异，若存在差异，则提取差异处对应的灰阶值，并以该灰阶值作为引导，将异常区域进行分割标记并显示出来。
具体的，步骤S02中对2D图像进行边缘检测时，利用灰阶或灰阶加灰阶梯度值检测头骨与颅脑内组织的边界，并对该边界进行滤波拟合后得到头盖骨边缘曲线。
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，并利用灰阶或灰阶加灰阶梯度值的方式对得到的3D超声图像进行头盖骨与颅脑内组织的边界检测，并对边界进行滤波拟合得到头盖骨曲面模型。
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拟合构建完整的头盖骨曲面模型。
本发明的优点在于：通过建立头盖骨曲面模型，并对2D超声图像检测头盖骨边界曲线，利用头盖骨边界曲线与头盖骨曲面模型进行拟合以确定2D超声图像的具体位置以选取具备对称特性的2D超声图像，利用2D超声图像的对称性进行异常区域的检测并分割显示出来，从而有效提高异常区域识别检测的准确率。
 附图说明
附图1为实施例1或2中2D图像的头盖骨边缘曲线与头盖骨曲面模型的拟合示意图。
 具体实施方式
实施例1，一种超声颅脑异常区域自动检测及显示方法，包括如下步骤：S01、先构建头盖骨曲面模型，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、将对颅脑进行超声扫查得到的2D超声图像进行头盖骨边缘检测，得到该2D图像的头盖骨边缘曲线。
S03、将步骤S02得到的2D图像的头盖骨边缘曲线与步骤S01得到的头盖骨曲面模型进行适配以确定该2D图像在头盖骨曲面模型上的位置。
S04、根据步骤S03得到的2D图像在头盖骨曲面模型上的位置判断该2D图像是否相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性。
S05、将步骤S04中相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性的2D图像进行标记，并根据分析需求从其中选取2D图像进行分析。
S06、对2D图像进行分析时，先将该2D图像分成互相对称的两个区域，分别对两个区域的图像做直方图统计或求灰度共生矩阵得到统计数据，接着对两个区域的统计数据做归一化处理提取特征数据，然后对两个区域的特征数据进行相似度比对计算。
S07、根据计算得到的相似度判断两个区域是否存在差异，若存在差异，则提取差异处对应的灰阶值，并以该灰阶值作为引导，将异常区域进行分割标记并显示出来。
其中，步骤S02中对2D图像进行边缘检测时，利用灰阶或灰阶加灰阶梯度值检测头骨与颅脑内组织的边界，并对该边界进行滤波拟合后得到头盖骨边缘曲线；由于超声颅脑图像的头骨有很强的发射，在图像中呈现高灰阶值，检测后形成的图像其边缘容易检测，利用灰阶或者灰阶加灰阶梯度值一起可以检测到头骨与颅脑内组织的边界。
其中，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，并利用灰阶或灰阶加灰阶梯度值的方式对得到的3D超声图像进行头盖骨与颅脑内组织的边界检测，并对边界进行滤波拟合得到头盖骨曲面模型。
实施例2，一种超声颅脑异常区域自动检测及显示方法，包括如下步骤：S01、先构建头盖骨曲面模型，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、将对颅脑进行超声扫查得到的2D超声图像进行头盖骨边缘检测，得到该2D图像的头盖骨边缘曲线。
S03、将步骤S02得到的2D图像的头盖骨边缘曲线与步骤S01得到的头盖骨曲面模型进行适配以确定该2D图像在头盖骨曲面模型上的位置。
S04、根据步骤S03得到的2D图像在头盖骨曲面模型上的位置判断该2D图像是否相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性。
S05、将步骤S04中相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性的2D图像进行标记，并根据分析需求从其中选取2D图像进行分析。
S06、对2D图像进行分析时，先将该2D图像分成互相对称的两个区域，分别对两个区域的图像做直方图统计或求灰度共生矩阵得到统计数据，接着对两个区域的统计数据做归一化处理提取特征数据，然后对两个区域的特征数据进行相似度比对计算。
S07、根据计算得到的相似度判断两个区域是否存在差异，若存在差异，则提取差异处对应的灰阶值，并以该灰阶值作为引导，将异常区域进行分割标记并显示出来。
其中，步骤S02中对2D图像进行边缘检测时，利用灰阶或灰阶加灰阶梯度值检测头骨与颅脑内组织的边界，并对该边界进行滤波拟合后得到头盖骨边缘曲线；由于超声颅脑图像的头骨有很强的发射，在图像中呈现高灰阶值，检测后形成的图像其边缘容易检测，利用灰阶或者灰阶加灰阶梯度值一起可以检测到头骨与颅脑内组织的边界。
其中，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 (4)

  1. 一种超声颅脑异常区域自动检测及显示方法，其特征在于，包括如下步骤：
    S01、先构建头盖骨曲面模型，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、将对颅脑进行超声扫查得到的2D超声图像进行头盖骨边缘检测，得到该2D图像的头盖骨边缘曲线；
    S03、将步骤S02得到的2D图像的头盖骨边缘曲线与步骤S01得到的头盖骨曲面模型进行适配以确定该2D图像在头盖骨曲面模型上的位置；
    S04、根据步骤S03得到的2D图像在头盖骨曲面模型上的位置判断该2D图像是否相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性；
    S05、将步骤S04中相对于头盖骨曲面模型的正中矢状面或正中冠状面呈对称特性的2D图像进行标记，并根据分析需求从其中选取2D图像进行分析；
    S06、对2D图像进行分析时，先将该2D图像分成互相对称的两个区域，分别对两个区域的图像做直方图统计或求灰度共生矩阵得到统计数据，接着对两个区域的统计数据做归一化处理提取特征数据，然后对两个区域的特征数据进行相似度比对计算；
    S07、根据计算得到的相似度判断两个区域是否存在差异，若存在差异，则提取差异处对应的灰阶值，并以该灰阶值作为引导，将异常区域进行分割标记并显示出来。
  2. 根据权利要求1所述的一种超声颅脑异常区域自动检测及显示方法，其特征在于：步骤S02中对2D图像进行边缘检测时，利用灰阶或灰阶加灰阶梯度值检测头骨与颅脑内组织的边界，并对该边界进行滤波拟合后得到头盖骨边缘曲线。
  3. 根据权利要求1或2所述的一种超声颅脑异常区域自动检测及显示方法，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，并利用灰阶或灰阶加灰阶梯度值的方式对得到的3D超声图像进行头盖骨与颅脑内组织的边界检测，并对边界进行滤波拟合得到头盖骨曲面模型。
  4. 根据权利要求1或2所述的一种超声颅脑异常区域自动检测及显示方法，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拟合构建完整的头盖骨曲面模型。
PCT/CN2022/073430 2022-01-14 2022-01-24 超声颅脑异常区域自动检测及显示方法 WO2023133935A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/610,676 US20240225587A1 (en) 2022-01-14 2024-03-20 Ultrasound automated detection and display method of cranial abnormal regions

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210042593.2A CN114399493B (zh) 2022-01-14 2022-01-14 超声颅脑异常区域自动检测及显示方法
CN202210042593.2 2022-01-14

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/610,676 Continuation US20240225587A1 (en) 2022-01-14 2024-03-20 Ultrasound automated detection and display method of cranial abnormal regions

Publications (1)

Publication Number Publication Date
WO2023133935A1 true WO2023133935A1 (zh) 2023-07-20

Family

ID=81231583

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/073430 WO2023133935A1 (zh) 2022-01-14 2022-01-24 超声颅脑异常区域自动检测及显示方法

Country Status (3)

Country Link
US (1) US20240225587A1 (zh)
CN (1) CN114399493B (zh)
WO (1) WO2023133935A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115861600B (zh) * 2022-12-20 2023-09-05 西北民族大学 一种spect图像的roi区域识别方法及系统
CN117912665B (zh) * 2024-03-18 2024-06-07 大连经典牙科科技有限公司 一种基于口腔扫描数据的远程管理系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101527047A (zh) * 2008-03-05 2009-09-09 深圳迈瑞生物医疗电子股份有限公司 使用超声图像检测组织边界的方法与装置
WO2016176863A1 (zh) * 2015-05-07 2016-11-10 深圳迈瑞生物医疗电子股份有限公司 三维超声成像方法和装置
US20170221215A1 (en) * 2014-10-21 2017-08-03 Wixi Hisky Medical Technologies Co., Ltd. Liver boundary identification method and system
CN111340780A (zh) * 2020-02-26 2020-06-26 汕头市超声仪器研究所有限公司 一种基于三维超声图像的病灶检测方法
CN113100827A (zh) * 2021-04-10 2021-07-13 汕头市超声仪器研究所股份有限公司 一种超声骨龄检测方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006325638A (ja) * 2005-05-23 2006-12-07 Konica Minolta Medical & Graphic Inc 異常陰影候補の検出方法及び医用画像処理システム
CA2845044C (en) * 2011-08-12 2023-03-28 Jointvue, Llc 3-d ultrasound imaging device and methods
WO2020087532A1 (zh) * 2018-11-02 2020-05-07 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、存储介质、处理器和计算机设备
CN110613483B (zh) * 2019-09-09 2022-05-20 南方医科大学 一种基于机器学习检测胎儿颅脑异常的系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101527047A (zh) * 2008-03-05 2009-09-09 深圳迈瑞生物医疗电子股份有限公司 使用超声图像检测组织边界的方法与装置
US20170221215A1 (en) * 2014-10-21 2017-08-03 Wixi Hisky Medical Technologies Co., Ltd. Liver boundary identification method and system
WO2016176863A1 (zh) * 2015-05-07 2016-11-10 深圳迈瑞生物医疗电子股份有限公司 三维超声成像方法和装置
CN111340780A (zh) * 2020-02-26 2020-06-26 汕头市超声仪器研究所有限公司 一种基于三维超声图像的病灶检测方法
CN113100827A (zh) * 2021-04-10 2021-07-13 汕头市超声仪器研究所股份有限公司 一种超声骨龄检测方法

Also Published As

Publication number Publication date
US20240225587A1 (en) 2024-07-11
CN114399493A (zh) 2022-04-26
CN114399493B (zh) 2024-06-11

Similar Documents

Publication Publication Date Title
EP2365356B1 (en) Three-dimensional (3D) ultrasound system for scanning object inside human body and method for operating 3D ultrasound system
WO2023133935A1 (zh) 超声颅脑异常区域自动检测及显示方法
JP2020506012A (ja) 脳卒中の診断及び予後予測方法並びにシステム
Giannini et al. A fully automatic algorithm for segmentation of the breasts in DCE-MR images
WO2012074039A1 (ja) 医用画像処理装置
US20140213901A1 (en) System & Method for Delineation and Quantification of Fluid Accumulation in EFAST Trauma Ultrasound Images
TW201603781A (zh) 偵測與量化腦梗塞區域的方法
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
CN111481233B (zh) 胎儿颈项透明层厚度测量方法
Hatanaka et al. Improvement of automatic hemorrhage detection methods using brightness correction on fundus images
Ho et al. Ultrasonography image analysis for detection and classification of chronic kidney disease
US20230225700A1 (en) Cranial ultrasonic standard plane imaging and automatic detection and display method for abnormal regions
Sahoo et al. Detection of diabetic retinopathy from retinal fundus image using wavelet based image segmentation
Somasundaram et al. Fetal head localization and fetal brain segmentation from MRI using the center of gravity
CN116645389A (zh) 一种个性化血管血栓三维结构建模方法及系统
Ashame et al. Abnormality Detection in Eye Fundus Retina
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
KR102349360B1 (ko) 영상 진단기기를 이용한 특발성 정상압 수두증의 진단 방법 및 시스템
Ni et al. Angle closure glaucoma detection using fractal dimension index on SS-OCT images
Chakkarwar et al. Automated analysis of gestational sac in medical image processing
Wang et al. Learning to diagnose cirrhosis via combined liver capsule and parenchyma ultrasound image features
Nirmala et al. Measurement of nuchal translucency thickness in first trimester ultrasound fetal images for detection of chromosomal abnormalities
Sumithra et al. Automatic Optic disc localization and optic cup segmentation from monocular color retinal images for glaucoma assessment
CN112070089B (zh) 一种基于超声图像的甲状腺弥漫性疾病智能诊断方法及系统

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: 22919581

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE