+

CN109191523B - Method and device for identifying heart position in chest X-ray plain film - Google Patents

Method and device for identifying heart position in chest X-ray plain film Download PDF

Info

Publication number
CN109191523B
CN109191523B CN201810965502.6A CN201810965502A CN109191523B CN 109191523 B CN109191523 B CN 109191523B CN 201810965502 A CN201810965502 A CN 201810965502A CN 109191523 B CN109191523 B CN 109191523B
Authority
CN
China
Prior art keywords
chest
lung tissue
ray
heart
plain film
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.)
Expired - Fee Related
Application number
CN201810965502.6A
Other languages
Chinese (zh)
Other versions
CN109191523A (en
Inventor
马乐
苏瑾
邹丹凤
蔡裕兴
陈卫国
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.)
Nanfang Hospital of Southern Medical University
Original Assignee
Nanfang Hospital of Southern Medical University
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 Nanfang Hospital of Southern Medical University filed Critical Nanfang Hospital of Southern Medical University
Priority to CN201810965502.6A priority Critical patent/CN109191523B/en
Publication of CN109191523A publication Critical patent/CN109191523A/en
Application granted granted Critical
Publication of CN109191523B publication Critical patent/CN109191523B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52Devices using data or image processing specially adapted for radiation diagnosis
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52Devices using data or image processing specially adapted for radiation diagnosis
    • A61B6/5211Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10116X-ray image
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30048Heart; Cardiac

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Pathology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Optics & Photonics (AREA)
  • General Physics & Mathematics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Processing (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

本发明公开了一种用于识别胸部X线平片中心脏方位的方法和装置,所述方法包括从胸部X线平片中提取肺组织轮廓,计算肺组织轮廓各点的斜率和根据所计算出的斜率确定心尖位置等步骤,所述装置包括存储器和处理器。本发明能够通过计算机等自动化设备自动识别胸部X线平片图像中的心尖所在位置,从而进一步识别心脏方位,避免需要人工逐张观察胸部X线平片来进行判断和识别,提高识别效率,降低了出错率。进一步地,在识别出心脏方位之后还可以自动按照识别结果给出相应的警告消息,以对医务人员进行提醒,从而提高诊疗效果。本发明广泛应用于图像识别领域。

Figure 201810965502

The invention discloses a method and a device for recognizing the orientation of the heart in the chest X-ray plain film. The method includes extracting the outline of lung tissue from the chest X-ray plain film, calculating the slope of each point of the lung tissue outline and calculating The obtained slope determines the apex position and other steps, and the device includes a memory and a processor. The invention can automatically identify the position of the apex of the heart in the chest X-ray plain film image through automatic equipment such as a computer, so as to further identify the position of the heart, avoid the need to manually observe the chest X-ray plain film one by one for judgment and identification, improve the identification efficiency, reduce error rate. Further, after the orientation of the heart is recognized, a corresponding warning message can be automatically given according to the recognition result to remind medical personnel, thereby improving the effect of diagnosis and treatment. The invention is widely used in the field of image recognition.

Figure 201810965502

Description

Method and device for identifying heart position in chest X-ray plain film
Technical Field
The invention relates to the field of image recognition, in particular to a method and a device for recognizing the position of a heart in a chest X-ray plain film.
Background
X-ray plain film shooting is a widely applied medical diagnosis and treatment means, and various diseases can be effectively diagnosed and treated through the X-ray plain film. The chest X-ray plain film is an X-ray plain film that is taken of the chest of a subject, and the images of the lung tissue, heart, soft tissue and other human tissues of the subject can be clearly observed through the chest X-ray plain film, and the rest of the chest X-ray plain film is a background except for the images of the human tissues.
Because human tissues and focus have asymmetry, it is significant to distinguish the left and right positions of chest X-ray plain film. Taking the chest X-ray plain film shot by using the DR flat panel detector as an example, when in actual shooting, medical staff can place a lead mark in the shape of a letter R on the right side of the DR flat panel detector, so that an R-shaped mark appears in an image shot under the action of the lead mark, and the mark is used by the medical staff to judge the left side and the right side of the body of a shot person in the chest X-ray plain film. Under normal conditions, namely the shooting position of the shot person and the condition that the imaging device is correctly installed, the side of the chest X-ray flat film where the R-shaped mark is located is the right side of the body of the shot person.
However, special cases are liable to occur in practice. For example, medical staff flip the imaging apparatus side to side due to carelessness when installing the imaging apparatus; the individual subject is difficult to stand or the child is not crying and is not matched with the subject to finish shooting in a lying mode, namely shooting by using the front and back positions. The special case will cause the side of the R-shaped mark on the chest X-ray flat film not to be the right side of the body of the person to be photographed. In this particular case, the chest X-ray plain film of the subject with a normal heart orientation looks the same as the chest X-ray plain film of the right heart. Therefore, after the special condition occurs, the photographed person is easily misdiagnosed as right heart, and even further serious medical consequences are caused.
In the prior art, medical staff needs to identify chest X-ray plain films one by one through naked eyes, judge the heart position in the chest X-ray plain films and then further confirm whether the right position heart appears. The specific operation mode is to observe the side of the heart apex relative to the human body midline of the shot. However, the method completely relying on manual identification has the disadvantages of low efficiency, high error rate and the like. Therefore, there is a need for a technique capable of further determining the position of the heart by automatically recognizing the apex of the heart.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a method and a device for identifying the heart position in a chest X-ray plain.
The first technical scheme adopted by the invention is as follows:
a method for identifying the position of the heart in a chest X-ray surview, comprising the steps of:
extracting a lung tissue outline from a chest X-ray plain film;
calculating the slope of each point of the lung tissue outline;
the apex location is determined from the calculated slope.
Further, the chest X-ray flat sheet is provided with a mark for indicating the body orientation of the shot, and after the position of the apex of the heart is determined, the method further comprises the following steps:
comparing the apex location with the marker, thereby obtaining a comparison result; the comparison result comprises that the apex position and the mark are both positioned on the same side relative to the midline of the human body, and the apex position and the mark are respectively positioned on different sides relative to the midline of the human body;
and sending out corresponding information according to the comparison result.
Further, the mark is used for marking the right side of the body of the photographed person, and the step of sending out a corresponding message according to the comparison result specifically includes:
if the apex position and the mark are on the same side with respect to the human body, a warning message for warning of an error in the photographing process or a physical abnormality of the subject is issued.
Further, the step of extracting the lung tissue contour from the chest X-ray plain film specifically comprises:
dividing the chest X-ray plain film into parts respectively corresponding to lung tissues, soft tissues and a background according to the gray level of each point on the chest X-ray plain film;
and extracting the boundary between the part corresponding to the lung tissue and the part corresponding to the soft tissue on the chest X-ray flat sheet so as to obtain the lung tissue outline.
Further, after the boundary between the portion corresponding to the lung tissue and the portion corresponding to the soft tissue on the chest X-ray plain film is acquired, the boundary is further subjected to filtering processing.
Further, the method further comprises the steps of:
the lung tissue contour is divided into a left part and a right part with reference to the midline of the human body.
Further, the step of determining the apex location according to the calculated slope specifically includes:
calculating the difference between the maximum value and the minimum value of the slope of each point on the left side part, thereby obtaining a first difference value;
calculating the difference between the maximum value and the minimum value of the slope of each point on the right side part, thereby obtaining a second difference value;
and taking the position of the lung tissue contour corresponding to the larger of the first difference and the second difference as the apex position.
Further, the human body midline is obtained by the following steps:
finding the longitudinal highest point and the longitudinal lowest point of the left part of the lung tissue outline;
finding the longitudinal highest point and the longitudinal lowest point of the right part of the lung tissue outline;
finding a midpoint of a first connection line formed by a longitudinal highest point of the left part of the lung tissue outline and a longitudinal highest point of the right part of the lung tissue outline;
finding a midpoint of a second line formed by the longitudinal nadir of the left portion of the lung tissue profile and the longitudinal nadir of the right portion of the lung tissue profile;
and taking the straight line where the middle point of the first connecting line and the middle point of the second connecting line are positioned as the middle line of the human body.
Further, the human body midline is obtained by the following steps:
acquiring the central line of the chest X-ray flat sheet in the vertical direction;
the midline of the chest X-ray flat piece in the vertical direction is taken as the midline of the human body.
The second technical scheme adopted by the invention is as follows:
an apparatus for identifying a dirty position in a chest X-ray surview, comprising a memory for storing at least one program and a processor for loading the at least one program to perform the method of the first aspect.
The invention has the beneficial effects that: the heart apex position in the chest X-ray plain film image can be automatically identified through automation equipment such as a computer, the heart position is further identified, the condition that the chest X-ray plain film is observed manually one by one to judge and identify is avoided, the identification efficiency is improved, and the error rate is reduced.
Furthermore, after the heart position is identified, a corresponding warning message can be automatically given according to the identification result so as to remind medical staff, thereby improving the diagnosis and treatment effect.
Drawings
FIG. 1 is a flow chart of the method of example 1;
FIG. 2 is a chest X-ray surview of the heart location to be identified;
FIG. 3 is an enlarged view of a portion of FIG. 2;
fig. 4 is a chest X-ray plain image of the midline of the human body to be identified.
Detailed Description
Example 1
A method for identifying the position of the heart in a chest X-ray surview, with reference to fig. 1, comprising the following steps:
extracting a lung tissue outline from a chest X-ray plain film;
calculating the slope of each point of the lung tissue outline;
the apex location is determined from the calculated slope.
A typical chest X-ray plain image is shown in fig. 2. The gray levels of the lung tissue a, the soft tissue B and the background C in the chest X-ray plain are significantly different, so the chest X-ray plain image can be divided into three parts of background, soft tissue and lung tissue by gray level comparison, wherein the lung tissue comprises a left part and a right part. The boundary of the lung tissue a and the soft tissue B is further determined as the lung tissue contour by gray scale contrast. In the process of extracting the lung tissue contour, in order to improve the accuracy, the region corresponding to the lung tissue a and the soft tissue B may be binarized first. After the lung tissue contour is obtained through extraction, the lung tissue contour can be further subjected to filtering processing, so that burrs and sharp components are removed, and the lung tissue contour is smoother.
The portion denoted by D in fig. 2 is the apex of the heart, and identifying the position of the apex of the heart is key to identifying the position of the heart. As can be seen from fig. 2, except for the locations of the apex of the lung and the angle of the ribcage, other portions of the lung tissue contour are relatively flat, while the portion of the lung tissue contour corresponding to the apex of the heart has a higher degree of curvature, i.e., the degree of change of the slope of the portion of the lung tissue contour corresponding to the apex of the heart is greater, so that the location of the apex of the heart can be identified by the slope.
In the calculation of the slope, the calculation is preferably performed only for the inner side of the lung tissue contour. The inner side of the lung tissue contour refers to the portion of the lung tissue contour closest to the midline of the human body. Fig. 3 is an enlarged view of a portion of fig. 2, the portion of the lung tissue contour shown in fig. 3 being the inner side of the entire lung tissue contour. The inside of the lung tissue contour is also divided into a left side portion and a right side portion, corresponding to the division of the lung tissue contour into a left side portion and a right side portion as a whole.
As can be seen from fig. 3, the more curved portion of the inner side of the contour of the lung tissue (i.e. the right portion in the figure) corresponds to the location of the apex of the heart. The slope can be calculated mathematically by coordinating the points of the lung tissue contour, and then the portion of the slope that changes most is identified as the location of the apex.
Further preferably, the step of determining the position of the apex of the heart according to the calculated slope specifically includes:
calculating the difference between the maximum value and the minimum value of the slope of each point on the left side part, thereby obtaining a first difference value;
calculating the difference between the maximum value and the minimum value of the slope of each point on the right side part, thereby obtaining a second difference value;
and taking the position of the lung tissue contour corresponding to the larger of the first difference and the second difference as the apex position.
Considering fig. 2 partially, as shown in fig. 3, the inner side of the lung tissue contour is divided into a left side portion and a right side portion, and the slope is preferably calculated only for each point inside the lung tissue contour. And respectively calculating a first difference value and a second difference value, wherein the first difference value is the difference between the maximum value and the minimum value of the slope of each point in the left part, and the second difference value is the difference between the maximum value and the minimum value of the slope of each point in the right part. As shown in fig. 3, the calculation result will be that the second difference is large, that is, the right portion of the inner side of the lung tissue contour has a large degree of curvature, and thus it can be determined that the apex is located on the right side as shown in fig. 3.
After the position of the apex is obtained, the position of the apex can be further compared with the R-shaped mark. On the chest X-ray flat sheet, the R-shaped mark has a gray level which is obviously different from the surrounding, so that the R-shaped mark can be identified through gray level comparison or other image identification methods, and the position of the R-shaped mark is obtained.
According to the relation between the central point position of the X-ray plain film and the position of the R-shaped mark, whether an abnormal state exists or not can be automatically judged. The specific judgment rule is as follows:
the apex of the heart and the R-shaped mark are positioned on different sides of the chest X-ray plain film, which generally belongs to the normal medical condition, and in this case, a warning message does not need to be sent out;
the apex of the heart and the R-shaped mark are positioned on the same side of the chest X-ray plain film, which generally belongs to an abnormal situation in medicine, and the reason for causing the phenomenon can be that the photographed person belongs to the right position, or the medical staff turns the related equipment left and right due to carelessness, and in any case, the subsequent diagnosis and treatment work can be influenced and attention must be paid, so that a warning message can be sent when the situation occurs, and the medical staff can be reminded that the photographed person is possibly abnormal in body (right position) or the photographing process is wrong (the related equipment is turned left and right).
It is worth explaining that under the condition that the photographed person is in the right position and the medical staff is careless and the related equipment is installed in a left-right overturning mode simultaneously, the phenomenon that the apex of the heart and the R-shaped mark are located on different sides also occurs in the chest X-ray plain film photographed, so that the method has the possibility of misjudgment theoretically, but medical statistical data shows that the incidence rate of the right position is only 0.013% -0.05%, the probability of errors in the chest X-ray plain film photographing process caused by careless work of the medical staff is quite low, and after comprehensive consideration, the possibility of the misjudgment is extremely low and can be ignored.
In this embodiment, the descriptions of the left side, the right side, the same side, the different sides, and the like of the chest X-ray flat sheet are all referred to the human midline on the chest X-ray flat sheet, i.e. the straight line on which the trachea or the spine of the chest X-ray flat sheet is located. The embodiment also discloses a method for automatically identifying the human body midline on the chest X-ray plain film.
Because the position relation between the body position of the shot person and the relevant equipment has certain fixity in the chest X-ray plain film shooting process, the human body central line on the shot chest X-ray plain film is basically superposed with the central axis of the chest X-ray plain film image, and the central axis of the chest X-ray plain film image can be directly obtained to be used as the human body central line. Namely, the first method for automatically identifying the human body midline on the chest X-ray plain film comprises the following steps:
acquiring the central line of the chest X-ray flat sheet in the vertical direction;
the midline of the chest X-ray flat piece in the vertical direction is taken as the midline of the human body.
The second method for automatically identifying the human body midline on the chest X-ray plain film comprises the following steps:
finding the longitudinal highest point and the longitudinal lowest point of the left part of the lung tissue outline;
finding the longitudinal highest point and the longitudinal lowest point of the right part of the lung tissue outline;
finding a midpoint of a first connection line formed by a longitudinal highest point of the left part of the lung tissue outline and a longitudinal highest point of the right part of the lung tissue outline;
finding a midpoint of a second line formed by the longitudinal nadir of the left portion of the lung tissue profile and the longitudinal nadir of the right portion of the lung tissue profile;
and taking the straight line where the middle point of the first connecting line and the middle point of the second connecting line are positioned as the middle line of the human body.
Referring to fig. 4, after each point of the chest X-ray plain image is coordinated, it can be extracted from the ordinate of each point of the lung tissue contour. Extracting a longitudinal highest point (a point corresponding to a maximum value of an ordinate) E1 and a longitudinal lowest point (a point corresponding to a minimum value of the ordinate) F1 at the left part of the lung tissue profile, and a longitudinal highest point (a point corresponding to a maximum value of an ordinate) E2 and a longitudinal lowest point (a point corresponding to a minimum value of an ordinate) F2 at the right part of the lung tissue profile, wherein E1 and E2 are respectively the lung tips of the left lung and the right lung in medical significance, and F1 and F2 are respectively the costal diaphragm angles of the left lung and the right lung in medical significance. The straight line formed by the middle point of the connecting line E1-E2 and the middle point of the connecting line F1-F2 can be regarded as the midline of the human body medically.
Example 2
Let the pixel intensity of a chest X-ray flat be f (X, y) function, where (X, y) is the pixel coordinate. The criterion for dividing the regions according to the gray scale may be: the combination of 20< f (x, y) <100 to classify the point as lung tissue, 110< f (x, y) <200 to classify it as soft tissue, and f (x, y) <10 to classify it as background, divides the gray pixels possessed by lung tissue, soft tissue, and background into three groups.
The method of extracting the boundary of the lung tissue and the soft tissue may be: when the gray value of the adjacent pixel changes sharply, the pixel point is determined as the boundary of the lung tissue and the soft tissue, namely two adjacent points (x) in the horizontal directionn,yn) And (x)n-1,yn-1) Satisfies | f (x)n,yn)-f(xn-1,yn-1)|>When 10, it can be considered that (x)n,yn) And (x)n-1,yn-1) Between are the boundaries of lung tissue and soft tissue, and will be (x)n,yn) And (x)n-1,yn-1) As a point on the contour of the lung tissue.
The boundary points are connected in turn to form two lung tissue contours. A 4 th order 50Hz low pass filter may be used to filter out frightened low frequency signals in the outer contour, resulting in a smooth lung tissue contour, and to extract the inner portion of the outer contour near the centerline of the human body.
Calculating the point (x) on the contour of the lung tissuen,yn) Can obtain the sum point (x) on the lung tissue contourn,yn) Adjacent point (x)n-1,yn-1) Then by the formula
Figure BDA0001774854770000061
Calculating to obtain a slope kn
Calculating the slope of each point on the left side of the lung tissue contour shown in FIG. 3 to obtain a set of slopes
Figure BDA0001774854770000062
Calculating the slope of each point on the right part of the image to obtain a group of slopes
Figure BDA0001774854770000063
Calculating the difference between the maximum and minimum of each of the two sets of slopes, i.e.
Figure BDA0001774854770000064
Figure BDA0001774854770000065
In actual calculation, a threshold value may be set, such as 30, when dlOr drIf the value is larger than the threshold, the heart apex is judged to be positioned at the position dlOr drThe corresponding lung tissue contour is on one side. Or directly to dlAnd drThe size of the heart point is judged, and the side of the lung tissue contour corresponding to the larger lung tissue contour is the position of the heart point.
Example 3
The embodiment is an apparatus for identifying a visceral position in a chest X-ray plain, comprising a memory for storing at least one program and a processor for loading the at least one program to perform the method of embodiment 1 or embodiment 2.
The apparatus of this embodiment may also be connected to a DR flat panel detector or film scanner to acquire an electronic image of the chest X-ray flat film for processing by a processor.
In conclusion, the beneficial effects of the invention are as follows:
the heart apex position in the chest X-ray plain film image can be automatically identified through automatic equipment such as a computer, so that the heart position is further identified, the judgment and identification by manually observing the chest X-ray plain films one by one are avoided, the identification efficiency is improved, and the error rate is reduced;
after the heart position is identified, corresponding warning messages can be automatically given according to the identification result so as to remind medical staff, and therefore diagnosis and treatment effects are improved.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (8)

1.一种用于识别胸部X线平片中心脏方位的方法,其特征在于,包括以下步骤:1. a method for identifying the position of the heart in the chest X-ray plain film, is characterized in that, comprises the following steps: 从胸部X线平片中提取肺组织轮廓;Extract lung tissue contours from plain chest X-rays; 计算肺组织轮廓各点的斜率;Calculate the slope of each point of the lung tissue contour; 根据所计算出的斜率确定心尖位置;Determine the apex position according to the calculated slope; 以人体中线为参考,将所述肺组织轮廓区分为左侧部分和右侧部分;Taking the midline of the human body as a reference, the outline of the lung tissue is divided into a left part and a right part; 所述根据所计算出的斜率确定心尖位置这一步骤具体包括:The step of determining the apex position according to the calculated slope specifically includes: 计算所述左侧部分各点斜率的最大值与最小值之差,从而获得第一差值;Calculate the difference between the maximum value and the minimum value of the slope of each point on the left side, so as to obtain the first difference value; 计算所述右侧部分各点斜率的最大值与最小值之差,从而获得第二差值;Calculate the difference between the maximum value and the minimum value of the slope of each point on the right side, so as to obtain a second difference value; 根据第一差值和第二差值中较大者所对应的肺组织轮廓所处位置作为心尖位置。The position of the lung tissue contour corresponding to the larger of the first difference value and the second difference value is used as the position of the heart apex. 2.根据权利要求1所述的一种用于识别胸部X线平片中心脏方位的方法,所述胸部X线平片上带有用于表示被拍摄者身体方位的标记,其特征在于,在确定心尖位置之后,还包括以下步骤:2. A method for recognizing the position of the heart in the chest X-ray plain film according to claim 1, wherein the chest X-ray plain film is provided with a mark for representing the body position of the photographed person, and it is characterized in that, after determining After the apex position, the following steps are also included: 将心尖位置与所述标记进行对比,从而获得对比结果;所述对比结果包括心尖位置与标记均位于相对于人体中线的同一侧,以及心尖位置与标记分别位于相对于人体中线的不同侧;Comparing the apex position with the marker to obtain a comparison result; the comparison result includes that both the apex position and the marker are located on the same side relative to the midline of the human body, and the apex position and the marker are located on different sides relative to the midline of the human body; 根据对比结果发出相应的消息。Send corresponding messages according to the comparison results. 3.根据权利要求2所述的一种用于识别胸部X线平片中心脏方位的方法,所述标记用于标示被拍摄者的身体右侧,其特征在于,所述根据对比结果发出相应的消息这一步骤具体包括:3. A method for identifying the position of the heart in the chest X-ray plain film according to claim 2, the mark is used to mark the right side of the body of the subject, and it is characterized in that, according to the comparison result, the corresponding This step specifically includes: 如果心尖位置与标记位于相对于人体的同一侧,则发出用于提示拍摄过程出错或者被拍摄者身体异常的警告消息。If the position of the apex of the heart and the marker are located on the same side relative to the human body, a warning message for prompting an error in the photographing process or an abnormality in the body of the photographed person is issued. 4.根据权利要求1所述的一种用于识别胸部X线平片中心脏方位的方法,其特征在于,所述从胸部X线平片中提取肺组织轮廓这一步骤具体包括:4. a kind of method for recognizing the position of the heart in the chest X-ray plain film according to claim 1, is characterized in that, the described step of extracting the outline of lung tissue from the chest X-ray plain film specifically comprises: 根据胸部X线平片上各点的灰度,将胸部X线平片分为分别与肺组织、软组织和背景对应的各部分;According to the gray level of each point on the chest X-ray, the chest X-ray is divided into parts corresponding to lung tissue, soft tissue and background; 提取胸部X线平片上肺组织对应的部分与软组织对应的部分之间的交界,从而得到肺组织轮廓。The boundary between the part corresponding to the lung tissue and the part corresponding to the soft tissue on the chest X-ray is extracted to obtain the outline of the lung tissue. 5.根据权利要求4所述的一种用于识别胸部X线平片中心脏方位的方法,其特征在于,在获取到胸部X线平片上肺组织对应的部分与软组织对应的部分之间的交界之后,还对所述交界进行滤波处理。5. A method for recognizing the position of the heart in the chest X-ray plain film according to claim 4, characterized in that, between the part corresponding to the lung tissue and the part corresponding to the soft tissue obtained on the chest X-ray plain film. After the boundary, the boundary is also filtered. 6.根据权利要求1所述的一种用于识别胸部X线平片中心脏方位的方法,其特征在于,通过以下步骤获取所述人体中线:6. a kind of method for recognizing heart position in chest X-ray plain film according to claim 1, is characterized in that, obtain described human body midline by following steps: 查找肺组织轮廓的左侧部分的纵向最高点和纵向最低点;Find the longitudinal maxima and longitudinal nadir of the left part of the lung tissue contour; 查找肺组织轮廓的右侧部分的纵向最高点和纵向最低点;Find the longitudinal maxima and longitudinal nadir of the right part of the lung tissue contour; 查找肺组织轮廓的左侧部分的纵向最高点和肺组织轮廓的右侧部分的纵向最高点所形成的第一连线的中点;Find the midpoint of the first connecting line formed by the longitudinal highest point of the left part of the lung tissue contour and the longitudinal highest point of the right part of the lung tissue contour; 查找肺组织轮廓的左侧部分的纵向最低点和肺组织轮廓的右侧部分的纵向最低点所形成的第二连线的中点;Find the midpoint of the second connecting line formed by the longitudinal nadir of the left part of the lung tissue contour and the longitudinal nadir of the right part of the lung tissue contour; 以第一连线的中点和第二连线的中点所在直线作为人体中线。Take the line where the midpoint of the first connection line and the midpoint of the second connection line lie as the midline of the human body. 7.根据权利要求2所述的一种用于识别胸部X线平片中心脏方位的方法,其特征在于,通过以下步骤获取所述人体中线:7. a kind of method for recognizing heart position in chest X-ray plain film according to claim 2, is characterized in that, obtain described human body midline by following steps: 获取胸部X线平片在垂直方向的中线;Obtain a plain chest X-ray in the vertical midline; 将胸部X线平片在垂直方向的中线作为人体中线。The vertical midline of the chest X-ray was taken as the midline of the body. 8.一种用于识别胸部X线平片中心脏方位的装置,其特征在于,包括存储器和处理器,所述存储器用于存储至少一个程序,所述处理器用于加载所述至少一个程序以执行权利要求1-7任一项所述方法。8. A device for recognizing the orientation of the heart in a plain chest X-ray, comprising a memory and a processor, the memory for storing at least one program, the processor for loading the at least one program to The method of any one of claims 1-7 is performed.
CN201810965502.6A 2018-08-23 2018-08-23 Method and device for identifying heart position in chest X-ray plain film Expired - Fee Related CN109191523B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810965502.6A CN109191523B (en) 2018-08-23 2018-08-23 Method and device for identifying heart position in chest X-ray plain film

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810965502.6A CN109191523B (en) 2018-08-23 2018-08-23 Method and device for identifying heart position in chest X-ray plain film

Publications (2)

Publication Number Publication Date
CN109191523A CN109191523A (en) 2019-01-11
CN109191523B true CN109191523B (en) 2021-11-09

Family

ID=64919667

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810965502.6A Expired - Fee Related CN109191523B (en) 2018-08-23 2018-08-23 Method and device for identifying heart position in chest X-ray plain film

Country Status (1)

Country Link
CN (1) CN109191523B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473180A (en) * 2019-07-31 2019-11-19 南方医科大学南方医院 Recognition methods, system and the storage medium of respiratory chest motion

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5072384A (en) * 1988-11-23 1991-12-10 Arch Development Corp. Method and system for automated computerized analysis of sizes of hearts and lungs in digital chest radiographs
US6335980B1 (en) * 1997-07-25 2002-01-01 Arch Development Corporation Method and system for the segmentation of lung regions in lateral chest radiographs
CN1442118A (en) * 2002-03-05 2003-09-17 株式会社东芝 Image treatment equipment and ultrasonic diagnosis equipment
EP1460584A3 (en) * 2002-12-10 2005-02-16 Eastman Kodak Company Method for automatic construction of 2D statistical shape model for the lung regions
CN101152096A (en) * 2006-09-27 2008-04-02 株式会社东芝 Ultrasonic diagnostic device and medical image processing device
CN103400398A (en) * 2013-07-31 2013-11-20 东北大学 Automatic heart locating method based on chest locating film
CN103927160A (en) * 2013-12-25 2014-07-16 宁波市科技园区明天医网科技有限公司 Method and system for intelligent auxiliary generation of electrocardio standardized report
CN107563998A (en) * 2017-08-30 2018-01-09 上海联影医疗科技有限公司 Medical image cardiac image processing method
CN108205941A (en) * 2018-01-04 2018-06-26 苏州尚领医疗科技有限公司 A kind of real-time detection method of thoracic cavity coefficient of elasticity and external chest compression reponse system

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6174279B1 (en) * 1999-09-21 2001-01-16 Acorn Cardiovascular, Inc. Cardiac constraint with tension indicator
US7616818B2 (en) * 2003-02-19 2009-11-10 Agfa Healthcare Method of determining the orientation of an image
US8463361B2 (en) * 2007-05-24 2013-06-11 Lifewave, Inc. System and method for non-invasive instantaneous and continuous measurement of cardiac chamber volume
JP5591545B2 (en) * 2010-01-20 2014-09-17 株式会社東芝 Magnetic resonance imaging system
CN104732520A (en) * 2015-01-31 2015-06-24 西安华海盈泰医疗信息技术有限公司 Cardio-thoracic ratio measuring algorithm and system for chest digital image
CN106991697B (en) * 2017-04-17 2019-08-06 心医国际数字医疗系统(大连)有限公司 Measuring Method of Cardiothoracic Ratio in Chest Digital Image

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5072384A (en) * 1988-11-23 1991-12-10 Arch Development Corp. Method and system for automated computerized analysis of sizes of hearts and lungs in digital chest radiographs
US6335980B1 (en) * 1997-07-25 2002-01-01 Arch Development Corporation Method and system for the segmentation of lung regions in lateral chest radiographs
CN1442118A (en) * 2002-03-05 2003-09-17 株式会社东芝 Image treatment equipment and ultrasonic diagnosis equipment
EP1460584A3 (en) * 2002-12-10 2005-02-16 Eastman Kodak Company Method for automatic construction of 2D statistical shape model for the lung regions
CN101152096A (en) * 2006-09-27 2008-04-02 株式会社东芝 Ultrasonic diagnostic device and medical image processing device
CN103400398A (en) * 2013-07-31 2013-11-20 东北大学 Automatic heart locating method based on chest locating film
CN103927160A (en) * 2013-12-25 2014-07-16 宁波市科技园区明天医网科技有限公司 Method and system for intelligent auxiliary generation of electrocardio standardized report
CN107563998A (en) * 2017-08-30 2018-01-09 上海联影医疗科技有限公司 Medical image cardiac image processing method
CN108205941A (en) * 2018-01-04 2018-06-26 苏州尚领医疗科技有限公司 A kind of real-time detection method of thoracic cavity coefficient of elasticity and external chest compression reponse system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张戈军."胸部X线平片在心血管疾病诊断中的价值".《 临床荟萃》.2009,第24卷(第5期),1663-1666. *

Also Published As

Publication number Publication date
CN109191523A (en) 2019-01-11

Similar Documents

Publication Publication Date Title
Chawla et al. A method for automatic detection and classification of stroke from brain CT images
JP4702971B2 (en) Computer-aided diagnosis system
CN101238987A (en) A Processing Method for CT Cerebral Hemorrhage Images
US8437520B2 (en) Medical image processor and medical image processing method
KR101472558B1 (en) The system and method for automatic segmentation of lung, bronchus, pulmonary vessels images from thorax ct images
KR101530015B1 (en) Method for analysis of densitometry in computed tomography
US7881508B2 (en) Method, apparatus, and program for judging medical images
JP2004032684A (en) Automated method and apparatus for computerized detection of masses and parenchymal tissue deformations in medical images
CN115345893B (en) Ovarian tissue canceration region segmentation method based on image processing
CN104619257A (en) System and method for automated detection of lung nodules in medical images
CN114529502B (en) Deep learning-based methods and systems for automated subject anatomy and orientation recognition
WO2012106580A2 (en) Methods and apparatus for computer-aided radiological detection and imaging
US11967079B1 (en) System and method for automatically detecting large vessel occlusion on a computational tomography angiogram
JP2014128648A (en) Image processor and image processing method
CN109191523B (en) Method and device for identifying heart position in chest X-ray plain film
CN119600017B (en) Neurosurgery medical image analysis method and system based on image processing
CN109615656A (en) A Spine Localization Method Based on Model Search
JP2017167965A (en) Image processing apparatus and medical information management system
TWI439253B (en) Method and system for disease detection using human infrared thermal map
US10062164B2 (en) Method for the analysis of image data representing a three-dimensional volume of biological tissue
EP4309121A1 (en) Detecting abnormalities in an x-ray image
CN118735912A (en) A spinal deformity identification method for auxiliary diagnosis of abdominal aortic aneurysm
Motoki et al. Automatic teeth recognition method from dental panoramic images using faster R-CNN and prior knowledge model
CN116030042B (en) Diagnostic device, method, equipment and storage medium for doctor&#39;s diagnosis
Zhou et al. Automated estimation of the upper surface of the diaphragm in 3-D CT images

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
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: 20211109

点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载