[go: up one dir, main page]

CN103456001A - Method and device for positioning key section in brain CT image - Google Patents

Method and device for positioning key section in brain CT image Download PDF

Info

Publication number
CN103456001A
CN103456001A CN2012105106643A CN201210510664A CN103456001A CN 103456001 A CN103456001 A CN 103456001A CN 2012105106643 A CN2012105106643 A CN 2012105106643A CN 201210510664 A CN201210510664 A CN 201210510664A CN 103456001 A CN103456001 A CN 103456001A
Authority
CN
China
Prior art keywords
brain
image
column
length
calculate
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
CN2012105106643A
Other languages
Chinese (zh)
Other versions
CN103456001B (en
Inventor
李永红
谢晓勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Information Technology
Original Assignee
Shenzhen Institute of Information Technology
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 Shenzhen Institute of Information Technology filed Critical Shenzhen Institute of Information Technology
Priority to CN201210510664.3A priority Critical patent/CN103456001B/en
Publication of CN103456001A publication Critical patent/CN103456001A/en
Application granted granted Critical
Publication of CN103456001B publication Critical patent/CN103456001B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Apparatus For Radiation Diagnosis (AREA)

Abstract

本发明适用于数据处理领域，提供了在脑CT图像中定位关键切片的方法和装置，该方法包括下述步骤：确定脑CT图像的后半部分；通过像素计算所述脑CT图像的后半部分出现断裂的列，并统计所述出现断裂的列的个数；将所述出现断裂的列的个数与预先设定的出现断裂的列的个数阀值进行比较。本发明实施例，首先确定脑CT图像切片的后半部分，然后通过像素计算每张切片中出现断裂的列的个数，并根据所述出现断裂的列的个数判断是否为岩骨所在的切片，提供了一种通过直接计算获取岩骨CT图像切片的方法，提高了获取图像切片的速度。

Figure 201210510664

The present invention is applicable to the field of data processing, and provides a method and device for locating a key slice in a brain CT image. The method includes the following steps: determining the second half of the brain CT image; calculating the second half of the brain CT image by pixels Partially broken columns, and count the number of broken columns; compare the number of broken columns with a preset threshold value of the number of broken columns. In the embodiment of the present invention, firstly determine the second half of the brain CT image slice, then calculate the number of fractured columns in each slice by pixels, and judge whether it is the petrous bone according to the number of fractured columns. Slicing provides a method for obtaining petrous bone CT image slices through direct calculation, which improves the speed of obtaining image slices.

Figure 201210510664

Description

The method and apparatus of locator key section in brain CT image
Technical field
The invention belongs to data processing field, relate in particular to the method and apparatus of locator key section in brain CT image.
Background technology
Along with constantly issuing licence of computer-aided diagnosis technology, the demand of carrying out intelligentized graphical analysis and feature identification in computed tomography (Computed Tomography CT) technology is more and more.In intelligent analysis application specific to brain CT image, how to determine rapidly and accurately the key section in brain CT, for automatically determining suspicious critical area, it is the problem that must solve that intelligent genius morbi extracts.
Prior art is determined brain CT image slices by the method for image registration, by brain map and the actual CT data of a standard, carries out image registration, by the collection of illustrative plates after registration, finds corresponding section.Classic method atlas registration chronic, and the result of registration also is subject to the impact of artificial subjective factor.
Summary of the invention
The purpose of the embodiment of the present invention is to be provided at the method and apparatus of locator key section in brain CT image, is intended to solution long in the existing locator key section time, the problem be affected by human factors.
The embodiment of the present invention is achieved in that a kind of method of locator key section in brain CT image, and described method comprises the steps:
Determine the latter half of brain CT image;
The row of fracture appear in the latter half that calculates described brain CT image by pixel, and add up the number of the row of described appearance fracture;
The number threshold values of the row of the number of the row of described appearance fracture and predefined appearance fracture is compared, if the number of the row of described appearance fracture is greater than the number threshold values of the row of predefined appearance fracture, will occur that the brain CT image of described number is defined as the petrous bone section.
Another purpose of the embodiment of the present invention is a kind of method that is provided at locator key section in brain CT image, said method comprising the steps of:
Determine center section in brain CT image;
Calculate the average gray g of described center section s;
From top to bottom, according to formula (g s-g s-1)/g scalculate the graded value of more last section gray scale, and the brain CT image of described graded value maximum is defined as to brain side room CT image.
Another purpose of the embodiment of the present invention is to provide a kind of device of locator key section in brain CT image, and described device comprises:
The latter half determining unit, for determining the latter half of brain CT image;
Fracture column count unit, the row that rupture occur for the latter half that calculates the definite brain CT image of described latter half determining unit by pixel;
Fracture row statistic unit, the number of the row that rupture for the appearance of adding up the calculating of described fracture column count unit;
The threshold values comparing unit, be used for the number threshold values of the row of the number of described fracture row statistic unit statistics and predefined appearance fracture is compared, if the number of the row of described appearance fracture is greater than the number threshold values of the row of predefined appearance fracture, will occur that the brain CT image of described number is defined as the petrous bone section.
Another purpose of the embodiment of the present invention is to provide a kind of device of locator key section in brain CT image, and described device comprises:
The center section determining unit, for determining center section at brain CT image;
The average gray computing unit, for calculating the average gray g of the definite center section of described center section determining unit s;
Grey scale change value computing unit, for from top to bottom, according to formula (g s-g s-1)/g scalculate the graded value of more last the section of average gray of described average gray computing unit calculating.
The embodiment of the present invention, at first determine the latter half of brain CT image slices, then calculate by pixel the number that occurs the row of fracture in every section, and the number of the row that rupture according to described appearance determines whether the section of petrous bone, a kind of method of obtaining petrous bone CT image slices by direct calculating is provided, has improved the speed of obtaining image slices.
The accompanying drawing explanation
Fig. 1 is the process flow diagram of locator key dicing method in brain CT image that one embodiment of the invention provides;
Fig. 2 is the design sketch of the brain CT image latter half that provides of the embodiment of the present invention;
Fig. 3 is the design sketch of the brain CT image latter half fracture row that provide of the embodiment of the present invention;
Fig. 4 is the process flow diagram of locator key dicing method in brain CT image that further embodiment of this invention provides;
Fig. 5 is the design sketch that the brain CT image brain rectangle that provides of the embodiment of the present invention surrounds frame;
Fig. 6 is the design sketch of the little rectangle of brain CT image that provides of the embodiment of the present invention;
Fig. 7 is the structural drawing of locator key slicing device in brain CT image that one embodiment of the invention provides;
Fig. 8 is the structural drawing of locator key slicing device in brain CT image that further embodiment of this invention provides.
Embodiment
In order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
The embodiment of the present invention, at first determine the latter half of brain CT image slices, then calculate by pixel the number that occurs the row of fracture in every section, and the number of the row that rupture according to described appearance determines whether the section of petrous bone, a kind of method of obtaining petrous bone CT image slices by direct calculating is provided, has improved the speed of obtaining image slices.
For technical solutions according to the invention are described, below by specific embodiment, describe.
Embodiment mono-:
The realization flow of locator key dicing method in brain CT image that Fig. 1 shows that one embodiment of the invention provides said method comprising the steps of:
In step S101, determine the latter half of brain CT image.
In embodiments of the present invention, because petrous bone is positioned at the latter half of brain, therefore according to this characteristic of petrous bone, the latter half image that only needs brain CT section, search and can save a lot of calculating at described latter half, as shown in Figure 2, wherein white portion is the latter half of brain CT image to its effect.Its concrete definite method is as follows:
(1), obtain the Y-axis coordinate fP on summit on described brain CT image and the Y-axis coordinate bP on lower summit;
(2) Y-axis of, according to formula yM=fP+ (bP-fP)/3, calculating lower summit is the Y-axis coordinate yM at 1/3 place up.YM is the latter half of the brain CT image needed to the coordinate range of bP.
In step S102, the row of fracture appear in the latter half that calculates described brain CT image by pixel, and add up the number of the row of described appearance fracture.
In embodiments of the present invention, after the latter half of determining brain CT image, calculate the number of often listing existing fracture of the latter half that obtains described brain CT image, as shown in Figure 3, wherein dotted line represents the row that fracture occurs to its display effect.The method of the row of fracture appears in the described latter half that calculates described brain CT image by pixel, comprising:
Latter half to described brain CT image carries out the pixel classification: brain is divided into a class pixel, and background is a class pixel.
The pixel of can brain in concrete implementation process dividing is set to grey, and the pixel of background parts is set to black.
By the latter half of the described brain CT of column scan image, and calculate in permutation and belong to length that brain divides and the length of permutation by pixel, the length of wherein said permutation is the most front length to the brain rearmost point of brain from current scan line.
In concrete implementation process, can be made as L by belonging to the length in pixels that brain divides in column of pixels, the difference Dy of the Y coordinate by calculating first pixel in column of pixels and the Y coordinate of last pixel calculates the length of column of pixels.
The relation that belongs to the length of length that brain divides and permutation in more described permutation, belong to if the length of described permutation is greater than in described permutation the length that length that brain divides adds two unit picture elements, thinks the described row that fracture occurs of classifying as.
In step S103, the number threshold values of the row of the number of the row of described appearance fracture and predefined appearance fracture is compared, if the number of the row of described appearance fracture is greater than the number threshold values of the row of predefined appearance fracture, will occur that the brain CT image of described number is defined as the petrous bone section.
The embodiment of the present invention, at first determine the latter half of brain CT image slices, then calculate by pixel the number that occurs the row of fracture in every section, and the number of the row that rupture according to described appearance determines whether the section of petrous bone, a kind of method of obtaining petrous bone CT image slices by direct calculating is provided, has improved the speed of obtaining image slices.
As an optional embodiment of the present invention, before described step S101, described method is further comprising the steps of:
From the brain CT image of brain area maximum, start down to be scanned.
Therefore in embodiments of the present invention, petrous bone is positioned at the part on the lower of brain, and the brain CT image of brain area maximum is the center section of section, starts down to scan from the brain CT image of brain area maximum and can save a lot of time.
As another alternative embodiment of the invention, before described step S103, described method is further comprising the steps of:
Set the number threshold values of the row that fracture occurs.
Embodiment bis-:
The process flow diagram of locator key dicing method in brain CT image that is illustrated in figure 4 that further embodiment of this invention provides said method comprising the steps of:
In step S401, determine center section in brain CT image.
In embodiments of the present invention, the position of telocoele is near the zone of calvarium, and mainly is positioned at the center section of head, therefore need at first determine the center section of head, and the step of described definite head center section is specially:
(1) rectangle that, calculates brain CT image deutocerebrum surrounds frame.
In concrete implementation process, set up rectangle according to the summit of brain CT image surrounding and surround frame, so both brain can be included in to described rectangle and surround in frame, its design sketch is as shown in Figure 5.
(2) new little rectangle is calculated in the zone of, selecting described rectangle to surround each limit of frame 1/4-3/4.
In embodiments of the present invention, the zone that described rectangle surrounds each limit of frame 1/4-3/4 is the center section that described rectangle surrounds frame, by described zone, forms the center section that little rectangle is head, and its display effect as shown in Figure 6.
In step S402, calculate the average gray g of described center section s.
In embodiments of the present invention, calculate the average gray of center section definite in brain CT image, calculate the method for described average gray and use prior art, therefore not to repeat here.
In step S403, from top to bottom, according to formula (g s-g s-1)/g scalculate the graded value of more last section gray scale, and the brain CT image of described graded value maximum is defined as to brain side room CT image.
In embodiments of the present invention, because the brain side room presents low-density characteristic, for low-density characteristic characteristic of correspondence in the CT image, be exactly that gray scale is more and more shallow, therefore can determine brain side room image according to the graded value of gray scale, the brain CT image of described graded value maximum is defined as brain side room CT image.
The embodiment of the present invention, the center section of at first definite brain CT image, then calculate the average gray of described center section, and determine brain side room CT image according to the changing value of described average gray.A kind of method of obtaining brain side room CT image slices by direct calculating is provided, has improved the speed of obtaining image slices.
Embodiment tri-:
The structural drawing of locator key slicing device in brain CT image that is illustrated in figure 7 that one embodiment of the invention provides for convenience of explanation, only illustrates part related to the present invention:
Latter half determining unit 701, for determining the latter half of brain CT image.
In embodiments of the present invention, because petrous bone is positioned at the latter half of brain, therefore according to this characteristic of petrous bone, only need the latter half image of brain CT section, at described latter half, search and can save a lot of calculating.Described latter half determining unit 701 specifically comprises:
Summit Y-axis coordinate obtains subelement 7011, for the Y-axis coordinate fP that obtains summit on described brain CT image and the Y-axis coordinate bP on lower summit.
Latter half computation subunit 7012, for according to described summit Y-axis coordinate, obtaining the apex coordinate that subelement 7011 obtains, the Y-axis of calculating lower summit according to formula yM=fP+ (bP-fP)/3 is the Y-axis coordinate yM at 1/3 place up.YM is the latter half of the brain CT image that we need to the coordinate range of bP.
Fracture column count unit 702, the row that rupture occur for the latter half that calculates the definite brain CT image of described latter half determining unit 701 by pixel.
Fracture row statistic unit 703, the number of the row that rupture for the appearance of adding up 702 calculating of described fracture column count unit.
In embodiments of the present invention, after the latter half of determining brain CT image, calculate the number of often listing existing fracture of the latter half that obtains described brain CT image.Described fracture column count unit 702 specifically comprises:
Pixel classification subelement 7021, the latter half of described brain CT image is carried out to the pixel classification: brain is divided into a class pixel, and background is a class pixel.
The pixel of can brain in concrete implementation process dividing is set to grey, and the pixel of background parts is set to black.
Column scan subelement 7022, for the latter half by the described brain CT of column scan image, and calculate in permutation and belong to length that brain divides and the length of permutation by pixel, the length of wherein said permutation is the most front length to the brain rearmost point of brain from current scan line.
In concrete implementation process, can be made as L by belonging to the length in pixels that brain divides in column of pixels, the difference Dy of the Y coordinate by calculating first pixel in column of pixels and the Y coordinate of last pixel calculates the length of column of pixels.
Compare subelement 7023, the relation that belongs to the length of length that brain divides and permutation for 7022 permutations of more described column scan subunit computes, belong to if the length of described permutation is greater than in described permutation the length that length that brain divides adds two unit picture elements, think the described row that fracture occurs of classifying as.
Threshold values comparing unit 704, be used for the number threshold values of the row of the number of described fracture row statistic unit 703 statistics and predefined appearance fracture is compared, if the number of the row of described appearance fracture is greater than the number threshold values of the row of predefined appearance fracture, will occur that the brain CT image of described number is defined as the petrous bone section.
The embodiment of the present invention, at first determine the latter half of brain CT image slices, then calculate by pixel the number that occurs the row of fracture in every section, and the number of the row that rupture according to described appearance determines whether the section of petrous bone, a kind of method of obtaining petrous bone CT image slices by direct calculating is provided, has improved the speed of obtaining image slices.
As an optional embodiment of the present invention, before described latter half determining unit 701 is determined the latter half of brain CT image, described device also comprises:
The maximum scan unit, start down to be scanned for the brain CT image from brain area maximum.
Therefore in embodiments of the present invention, petrous bone is positioned at the part on the lower of brain, and the brain CT image of brain area maximum is the center section of section, starts down to scan from the brain CT image of brain area maximum and can save a lot of time.
As another alternative embodiment of the invention, described threshold values comparing unit 704 carry out threshold values relatively before, described device also comprises:
The threshold value setting unit, for setting the number threshold values of the row that fracture occurs.
Embodiment tetra-:
The structural drawing of locator key slicing device in brain CT image that is illustrated in figure 8 that further embodiment of this invention provides, for convenience of explanation, only illustrate the part relevant to the embodiment of the present invention, comprising:
Center section determining unit 801, for determining center section at brain CT image.
In embodiments of the present invention, the position of telocoele is near the zone of calvarium, and mainly is positioned at the center section of head, therefore need at first determine the center section of head.Described center section determining unit 801 specifically comprises:
Rectangle surrounds frame computation subunit 8011, for the rectangle that calculates brain CT image deutocerebrum, surrounds frame.
In concrete implementation process, set up rectangle according to the summit of brain CT image surrounding and surround frame, so both brain can be included in to described rectangle and surround in frame.
Little rectangle computation subunit 8012, surround the zone of each limit of frame 1/4-3/4 and calculate new little rectangle for the rectangle of selecting described rectangle to surround 8011 calculating of frame computation subunit.
In embodiments of the present invention, the zone that described rectangle surrounds each limit of frame 1/4-3/4 is the center section that described rectangle surrounds frame, by described zone, forms the center section that little rectangle is head.
Average gray computing unit 802, for calculating the average gray g of the definite center section of described center section determining unit 801 s.
In embodiments of the present invention, calculate the average gray of center section definite in brain CT image, calculate the method for described average gray and use prior art, therefore not to repeat here.
Grey scale change value computing unit 803, for from top to bottom, according to formula (g s-g s-1)/g scalculate the graded value of more last the section of average gray of described average gray computing unit 802 calculating.
In embodiments of the present invention, because the brain side room presents low-density characteristic, for low-density characteristic characteristic of correspondence in the CT image, be exactly that gray scale is more and more shallow, therefore can determine brain side room image according to the graded value of gray scale, the brain CT image of described graded value maximum is defined as brain side room CT image.
The embodiment of the present invention, the center section of at first definite brain CT image, then calculate the average gray of described center section, and determine brain side room CT image according to the changing value of described average gray.A kind of method of obtaining brain side room CT image slices by direct calculating is provided, has improved the speed of obtaining image slices.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.

Claims (14)

1.一种在脑CT图像中定位关键切片的方法，其特征在于，所述方法包括以下步骤：1. A method for locating key slices in a brain CT image, characterized in that the method comprises the following steps: 确定脑CT图像的后半部分；Determine the second half of the brain CT image; 通过像素计算所述脑CT图像的后半部分出现断裂的列，并统计所述出现断裂的列的个数；Calculate the columns with fractures in the second half of the brain CT image by pixels, and count the number of columns with fractures; 将所述出现断裂的列的个数与预先设定的出现断裂的列的个数阀值进行比较，如果所述出现断裂的列的个数大于预先设定的出现断裂的列的个数阀值，则将出现所述个数的脑CT图像确定为岩骨切片。Comparing the number of broken columns with a preset number threshold of broken columns, if the number of broken columns is greater than the preset number threshold of broken columns value, the brain CT images with the number appearing will be determined as petrous bone slices. 2.如权利要求1所述的方法，其特征在于，所述确定脑CT图像的后半部分的步骤，具体为：2. The method according to claim 1, wherein the step of determining the second half of the brain CT image is specifically: 获取所述脑CT图像上顶点的Y轴坐标fP和下顶点的Y轴坐标bP；Obtain the Y-axis coordinate fP of the upper vertex and the Y-axis coordinate bP of the lower vertex of the brain CT image; 根据公式yM=fP+(bP-fP)/3计算下顶点的Y轴往上1/3处的Y轴坐标yM。则yM到bP的坐标范围即为需要的脑CT图像的后半部分。According to the formula yM=fP+(bP-fP)/3, calculate the Y-axis coordinate yM of the upper 1/3 of the Y-axis of the lower vertex. Then the coordinate range from yM to bP is the second half of the required brain CT image. 3.如权利要求1所述的方法，其特征在于，所述通过像素计算所述脑CT图像的后半部分出现断裂的列的步骤，具体为：3. The method according to claim 1, characterized in that, the step of calculating the row of broken columns in the second half of the brain CT image by pixels is specifically: 对所述脑CT图像的后半部分进行像素分类：脑部分为一类像素，背景为一类像素；Perform pixel classification on the second half of the brain CT image: the brain is divided into one type of pixels, and the background is one type of pixels; 按列扫描所述脑CT图像的后半部分，并通过像素计算整列中属于脑部分的长度和整列的长度，其中所述整列的长度为从当前扫描线上脑最前点到脑最后点的长度；Scan the second half of the brain CT image by column, and calculate the length of the brain part in the entire column and the length of the entire column by pixels, wherein the length of the entire column is the length from the frontmost point of the brain to the last point of the brain on the current scanning line. ; 比较所述整列中属于脑部分的长度和整列的长度的关系，如果所述整列的长度大于所述整列中属于脑部分的长度加上两个单位像素的长度，则认为所述列为出现断裂的列。Comparing the relationship between the length of the brain part in the whole column and the length of the whole column, if the length of the whole column is greater than the length of the brain part in the whole column plus the length of two unit pixels, it is considered that the column is broken column. 4.如权利要求1所述的方法，其特征在于，在所述确定脑CT图像的后半部分的步骤之前，所述方法还包括以下步骤：4. The method according to claim 1, wherein, before the step of determining the second half of the brain CT image, the method further comprises the following steps: 从脑面积最大的脑CT图像开始往下进行扫描。Scanning starts from the CT image of the brain with the largest brain area. 5.如权利要求1所述的方法，其特征在于，在所述将所述出现断裂的列的个数与预先设定的出现断裂的列的个数阀值进行比较的步骤之前，所述方法还包括以下步骤：5. The method according to claim 1, characterized in that, before the step of comparing the number of broken columns with a preset number threshold of broken columns, the The method also includes the steps of: 设定出现断裂的列的个数阀值。Set the threshold for the number of broken columns. 6.一种在脑CT图像中定位关键切片的方法，其特征在于，所述方法包括以下步骤：6. A method for locating key slices in brain CT images, characterized in that said method comprises the following steps: 在脑CT图像中确定中间部分；Identify the middle part in the brain CT image; 计算所述中间部分的平均灰度gs；calculating the average gray level g s of said middle portion; 由上至下，根据公式（gs-gs-1）/gs计算较前一张切片灰度的梯度变化值，并将所述梯度变化值最大的脑CT图像确定为脑侧室CT图像。From top to bottom, according to the formula (g s -g s-1 )/g s , calculate the gradient change value of the gray value of the previous slice, and determine the brain CT image with the largest gradient change value as the lateral ventricle CT image . 7.如权利要求6所述的方法，其特征在于，所述在脑CT图像中确定中间部分的步骤，包括：7. The method according to claim 6, wherein the step of determining the middle part in the brain CT image comprises: 计算脑CT图像中大脑的矩形包围框；Calculate the rectangular bounding box of the brain in the brain CT image; 选择所述矩形包围框各边1/4-3/4的区域计算新的小矩形。Select the area of 1/4-3/4 of each side of the rectangular bounding box to calculate a new small rectangle. 8.一种在脑CT图像中定位关键切片的装置，其特征在于，所述装置包括：8. A device for positioning key slices in brain CT images, characterized in that the device comprises: 后半部分确定单元，用于确定脑CT图像的后半部分；a second half determining unit, configured to determine the second half of the brain CT image; 断裂列计算单元，用于通过像素计算所述后半部分确定单元确定的脑CT图像的后半部分出现断裂的列；A fracture column calculation unit, configured to calculate, by pixel, the column in which a fracture occurs in the second half of the brain CT image determined by the second half determination unit; 断裂列统计单元，用于统计所述断裂列计算单元计算的出现断裂的列的个数；A fracture column statistics unit, configured to count the number of fractured columns calculated by the fracture column calculation unit; 阀值比较单元，用于将所述断裂列统计单元统计的个数与预先设定的出现断裂的列的个数阀值进行比较，如果所述出现断裂的列的个数大于预先设定的出现断裂的列的个数阀值，则将出现所述个数的脑CT图像确定为岩骨切片。Threshold value comparison unit, used to compare the number counted by the broken column statistics unit with the preset threshold value of the number of broken columns, if the number of broken columns is greater than the preset If there is a threshold value for the number of broken columns, then the brain CT images with the number of broken columns are determined as petrous bone slices. 9.如权利要求8所述的装置，其特征在于，所述后半部分确定单元具体包括：9. The device according to claim 8, wherein the second half determining unit specifically comprises: 顶点Y轴坐标获取子单元，用于获取所述脑CT图像上顶点的Y轴坐标fP和下顶点的Y轴坐标bP；The vertex Y-axis coordinate acquisition subunit is used to acquire the Y-axis coordinate fP of the upper vertex and the Y-axis coordinate bP of the lower vertex of the brain CT image; 后半部分计算子单元，用于根据所述顶点Y轴坐标获取子单元获取的顶点坐标，根据公式yM=fP+(bP-fP)/3计算下顶点的Y轴往上1/3处的Y轴坐标yM。则yM到bP的坐标范围即为需要的脑CT图像的后半部分。The second half of the calculation sub-unit is used to obtain the vertex coordinates obtained by the sub-unit according to the Y-axis coordinates of the vertex, and calculate the Y at the upper 1/3 of the Y-axis of the lower vertex according to the formula yM=fP+(bP-fP)/3 Axis coordinates yM. Then the coordinate range from yM to bP is the second half of the required brain CT image. 10.如权利要求8所述的装置，其特征在于，所述断裂列计算单元具体包括：10. The device according to claim 8, wherein the fracture column calculation unit specifically comprises: 像素分类子单元，对所述脑CT图像的后半部分进行像素分类：脑部分为一类像素，背景为一类像素；The pixel classification subunit is used to perform pixel classification on the second half of the brain CT image: the brain part is divided into one type of pixels, and the background is divided into one type of pixels; 列扫描子单元，用于按列扫描所述脑CT图像的后半部分，并通过像素计算整列中属于脑部分的长度和整列的长度，其中所述整列的长度为从当前扫描线上脑最前点到脑最后点的长度；The column scanning subunit is used to scan the second half of the brain CT image by column, and calculate the length of the brain part in the entire column and the length of the entire column by pixels, wherein the length of the entire column is from the front of the brain on the current scanning line. The length from the point to the last point of the brain; 比较子单元，用于比较所述列扫描子单元计算的整列中属于脑部分的长度和整列的长度的关系，如果所述整列的长度大于所述整列中属于脑部分的长度加上两个单位像素的长度，则认为所述列为出现断裂的列。The comparison subunit is used to compare the relationship between the length of the brain part in the whole column calculated by the column scanning subunit and the length of the whole column, if the length of the whole column is greater than the length of the brain part in the whole column plus two units pixel length, the column is considered to be the column where the break occurred. 11.如权利要求8所述的装置，其特征在于，在所述后半部分确定单元确定脑CT图像的后半部分之前，所述装置还包括：11. The device according to claim 8, wherein, before the second half determining unit determines the second half of the brain CT image, the device further comprises: 最大扫描单元，用于从脑面积最大的脑CT图像开始往下进行扫描。The largest scanning unit is used to scan downward from the brain CT image with the largest brain area. 12.如权利要求8所述的装置，其特征在于，在所述阀值比较单元进行阀值比较之前，所述装置还包括：12. The device according to claim 8, wherein, before the threshold comparison unit performs threshold comparison, the device further comprises: 阀值设定单元，用于设定出现断裂的列的个数阀值。The threshold value setting unit is used to set the threshold value of the number of broken columns. 13.一种在脑CT图像中定位关键切片的装置，其特征在于，所述装置包括：13. A device for locating key slices in a brain CT image, characterized in that the device comprises: 中间部分确定单元，用于在脑CT图像中确定中间部分；an intermediate portion determining unit, configured to determine the intermediate portion in the brain CT image; 平均灰度计算单元，用于计算所述中间部分确定单元确定的中间部分的平均灰度gs；an average grayscale calculation unit, configured to calculate the average grayscale g s of the middle portion determined by the middle portion determination unit; 灰度变化值计算单元，用于由上至下，根据公式（gs-gs-1）/gs计算所述平均灰度计算单元计算的平均灰度较前一张切片的梯度变化值。The grayscale change value calculation unit is used to calculate the gradient change value of the average grayscale calculated by the average grayscale calculation unit compared with the previous slice according to the formula (g s -g s-1 )/g s from top to bottom . 14.如权利要求13所述的装置，其特征在于，所述中间部分确定单元具体包括：14. The device according to claim 13, wherein the middle part determination unit specifically comprises: 矩形包围框计算子单元，用于计算脑CT图像中大脑的矩形包围框；The rectangular bounding box calculation subunit is used to calculate the rectangular bounding box of the brain in the brain CT image; 小矩形计算子单元，用于选择所述矩形包围框计算子单元计算的矩形包围框各边1/4-3/4的区域计算新的小矩形。The small rectangle calculation subunit is used to select the area of 1/4-3/4 of each side of the rectangular bounding box calculated by the rectangular bounding box calculation subunit to calculate a new small rectangle.
CN201210510664.3A 2012-12-04 2012-12-04 Method and apparatus for locating key slices in brain CT images Expired - Fee Related CN103456001B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210510664.3A CN103456001B (en) 2012-12-04 2012-12-04 Method and apparatus for locating key slices in brain CT images

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210510664.3A CN103456001B (en) 2012-12-04 2012-12-04 Method and apparatus for locating key slices in brain CT images

Publications (2)

Publication Number Publication Date
CN103456001A true CN103456001A (en) 2013-12-18
CN103456001B CN103456001B (en) 2016-11-02

Family

ID=49738331

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210510664.3A Expired - Fee Related CN103456001B (en) 2012-12-04 2012-12-04 Method and apparatus for locating key slices in brain CT images

Country Status (1)

Country Link
CN (1) CN103456001B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040031065A1 (en) * 2002-04-26 2004-02-12 Barth Alison L. Neuronal activation in a transgenic model
CN101916443A (en) * 2010-08-19 2010-12-15 中国科学院深圳先进技术研究院 Processing method and system of CT image

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040031065A1 (en) * 2002-04-26 2004-02-12 Barth Alison L. Neuronal activation in a transgenic model
CN101916443A (en) * 2010-08-19 2010-12-15 中国科学院深圳先进技术研究院 Processing method and system of CT image

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MINGWU LOU等: "Correspondence of CT perfusion imaging to pathological manifestations in rabbit models of hyperacute cerebral infarction", 《NEURAL REGENERATION RESEARCH》 *
税午阳等: "基于医学体数据场的大脑皮层重构", 《计算机工程》 *

Also Published As

Publication number Publication date
CN103456001B (en) 2016-11-02

Similar Documents

Publication Publication Date Title
US20210225003A1 (en) Image processing method and apparatus, server, and storage medium
CN104200210B (en) A kind of registration number character dividing method based on component
CN103093181B (en) A kind of method and apparatus of license plate image location
CN113828948B (en) Plate edge searching method, calibration system and edge searching system of laser cutting machine
CN104616275A (en) Defect detecting method and defect detecting device
CN104408398B (en) A method and system for identifying liver boundaries
CN105608455B (en) A kind of license plate tilt correction method and device
CN110781839A (en) Sliding window-based small and medium target identification method in large-size image
CN106725593B (en) Ultrasonic three-dimensional fetal face contour image processing method and system
US20140161312A1 (en) Setting apparatus, image processing apparatus, control method of setting apparatus, and storage medium
CN105517677A (en) Depth/disparity map post-processing method and apparatus
CN104182987A (en) People counting device and people trajectory analysis device
CN105117725B (en) A kind of car plate self-correction recognition methods based on car plate confidence level
CN110199317A (en) Automatic detection, counting and measurement of wooden boards using a handheld device
CN116703911B (en) LED lamp production quality detecting system
CN117670886B (en) Display screen defect detection method, device, equipment and storage medium
WO2024125217A1 (en) Light spot tracking method and apparatus, and electronic device and storage medium
CN105893963B (en) A Method for Screening the Best Recognizable Frames for Single Pedestrian Objects in Videos
CN105701438B (en) Medical image processing apparatus and method and medical imaging device
CN103528515A (en) Dynamic detection method for crack of bridge bottom surface
CN110969135B (en) Vehicle logo recognition method in natural scene
JP6316154B2 (en) Vehicle detection device, adjustment support device, vehicle detection method, and adjustment method
US9111346B2 (en) Image processing apparatus, image processing method, and recording medium
CN102283675B (en) Rotation judgment and error correction method in medical ultrasonic panoramic imaging
CN103065313B (en) A kind of crystal position chart method for building up

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20161102

Termination date: 20191204