CN112465802A - Method, system, terminal and computer readable storage medium for processing tomographic image - Google Patents

Method, system, terminal and computer readable storage medium for processing tomographic image Download PDF

Info

Publication number
CN112465802A
CN112465802A CN202011454058.5A CN202011454058A CN112465802A CN 112465802 A CN112465802 A CN 112465802A CN 202011454058 A CN202011454058 A CN 202011454058A CN 112465802 A CN112465802 A CN 112465802A
Authority
CN
China
Prior art keywords
tomographic image
organ
preview window
dimensional
tomographic
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.)
Pending
Application number
CN202011454058.5A
Other languages
Chinese (zh)
Inventor
宋志杰
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.)
Shanghai United Imaging Healthcare Co Ltd
Original Assignee
Shanghai United Imaging Healthcare Co Ltd
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 Shanghai United Imaging Healthcare Co Ltd filed Critical Shanghai United Imaging Healthcare Co Ltd
Priority to CN202011454058.5A priority Critical patent/CN112465802A/en
Publication of CN112465802A publication Critical patent/CN112465802A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10112—Digital tomosynthesis [DTS]
    • 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
    • G06T2207/30068—Mammography; Breast

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Computer Graphics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention provides a processing method, a system, a terminal and a computer readable storage medium of a sectional image, wherein a sectional image sequence is placed in a three-dimensional coordinate system, then three-dimensional coordinates of edge points of an organ in the sectional image are extracted, a three-dimensional contour model of the organ is established according to an obtained coordinate set of the edge points, and a focus can be displayed in the three-dimensional contour model by marking and extracting the three-dimensional coordinates representing the focus, so that the specific position of the focus in a real three-dimensional space can be visually displayed, the position of the focus is accurately positioned, and a doctor is assisted in reading a film; in addition, in the process of establishing the three-dimensional contour model of the organ, only the edge points of the organ participate in calculation, so that the calculation amount is small, and the time consumption is low.

Description

Method, system, terminal and computer readable storage medium for processing tomographic image
Technical Field
The present invention relates to the field of medical imaging technologies, and in particular, to a method, a system, a terminal, and a computer-readable storage medium for processing a tomographic image.
Background
The Breast tomography technique can be considered as a Digital Breast Tomography (DBT) technique. DBT can overcome the problem of low mammary gland diagnosis accuracy rate caused by tissue overlapping in Full-digital mammography (FFDM) by using a three-dimensional tomography technology, and therefore has a good application prospect.
In the prior art, a breast tomography usually adopts a collective exposure (Combo) mode for scanning and shooting, a tomography image sequence of a breast can be obtained through one-time shooting, and then a doctor reads the breast, when the doctor finds a focus, the doctor can only mark in some tomography images and imagine the specific position of the focus in a real three-dimensional space, so that the requirements on the reading experience and the three-dimensional imagination capability of the doctor are extremely high, great inconvenience is brought to the doctor for reading the breast, and great uncertainty is brought to the positioning of the focus. At present, a three-dimensional image of a breast can be reconstructed according to a tomographic image sequence by adopting a 3D visualization reconstruction algorithm, but all coordinates in each tomographic image are required to participate in calculation, so that the calculation amount is extremely large, and the time consumption is extremely long.
Disclosure of Invention
The invention aims to provide a method, a system, a terminal and a computer readable storage medium for processing a tomogram, which can intuitively show the specific position of a focus in a real three-dimensional space and solve the problem of inaccurate positioning of the focus in the process of reading a tomogram.
In order to achieve the above object, the present invention provides a method of processing a tomographic image, comprising:
acquiring a tomographic image sequence of an organ, wherein the tomographic image sequence comprises a plurality of tomographic images which are sequentially stacked;
establishing a three-dimensional coordinate system according to the tomographic image sequence;
extracting three-dimensional coordinates of edge points of the organ from each tomographic image, and obtaining an edge point coordinate set representing the contour of the organ;
establishing a three-dimensional contour model of the organ according to the edge point coordinate set; and the number of the first and second groups,
the position of a lesion of the organ is marked in the tomographic image, and at least three-dimensional coordinates characterizing the position of the lesion are extracted to display the lesion in the three-dimensional contour model.
Optionally, the organ is a breast, brain stem, heart, liver, kidney or pancreas.
Optionally, the tomographic images are arranged along a first set direction, and the step of establishing a three-dimensional coordinate system according to the tomographic image sequence includes:
an XYZ three-dimensional coordinate system is established by taking any position in any tomographic image as a coordinate origin, the lateral direction and the longitudinal direction of the tomographic image as an X direction and a Y direction, respectively, and the arrangement direction of the tomographic image as a Z direction.
Optionally, the step of extracting three-dimensional coordinates of edge points of the organ in each of the tomographic images includes:
carrying out binarization on the tomogram to obtain a black-and-white image; and the number of the first and second groups,
and performing edge extraction on the black-and-white image to obtain the three-dimensional coordinates of the edge points of the organ.
Optionally, the organ is a breast, and the step of performing edge extraction on the black-and-white image to obtain three-dimensional coordinates of edge points of the organ includes:
and carrying out unidirectional scanning on a row of pixels of the black-and-white image at intervals of a preset interval along the transverse direction, taking the pixels with suddenly changed pixel values as the edge points during each scanning, and recording the three-dimensional coordinates of the edge points.
Optionally, the step of building a three-dimensional contour model of the organ according to the edge point coordinate set includes:
fitting the edge points extracted from each tomographic image into a corresponding contour line; and the number of the first and second groups,
and constructing a triangular network between the corresponding contour lines of every two adjacent tomograms so as to fit the three-dimensional contour model.
Optionally, the step of performing edge extraction on the black-and-white image to obtain three-dimensional coordinates of edge points of the organ includes:
dividing the black-and-white image into a first part and a second part by using a virtual dividing line, wherein in a direction perpendicular to the virtual dividing line, a row of pixels or a column of pixels of the first part and the second part have pixels with single pixel value abrupt change; and the number of the first and second groups,
and performing bidirectional scanning on a row of pixels or a column of pixels of the black-and-white image in a direction perpendicular to the virtual dividing line at intervals of a preset interval, taking the pixels with suddenly changed pixel values in the first part and the second part as the edge points during each scanning, and recording the three-dimensional coordinates of the edge points.
Optionally, the step of building a three-dimensional contour model of the organ according to the edge point coordinate set includes:
fitting the edge points extracted from the first part of each tomographic image into a first contour line, and fitting the edge points extracted from the second part of each tomographic image into a second contour line;
constructing a triangular network between first contour lines corresponding to two adjacent tomograms to fit a first contour model, and constructing a triangular network between second contour lines corresponding to two adjacent tomograms to fit a second contour model; and the number of the first and second groups,
and constructing a triangular network between a first contour line of the edge of the first contour model and a second contour line of the edge of the second contour model so as to fit the three-dimensional contour model.
Optionally, the step of marking a location of a lesion of the organ in the tomographic image comprises:
displaying the tomogram in a preview window;
manually marking the location of a lesion of the organ.
Optionally, the step of marking a position of a lesion of the organ in the tomographic image, and extracting at least three-dimensional coordinates representing the position of the lesion to display the lesion in the three-dimensional contour model includes:
drawing a marking point on the tomogram, wherein the marking point is positioned in the focus;
extracting the three-dimensional coordinates of the marking points as the three-dimensional coordinates representing the positions of the focuses; and the number of the first and second groups,
and displaying the mark points in the three-dimensional contour model according to the three-dimensional coordinates of the mark points.
Optionally, the step of marking a position of a lesion of the organ in the tomographic image, and extracting at least three-dimensional coordinates representing the position of the lesion to display the lesion in the three-dimensional contour model includes:
drawing a circle on the tomogram, the circle surrounding the lesion;
extracting a three-dimensional coordinate of the circle center of the circle as a three-dimensional coordinate representing the position of the focus;
calculating the radius of the circle; and the number of the first and second groups,
and drawing a sphere in the three-dimensional contour model according to the three-dimensional coordinate of the circle center of the circle and the radius of the circle.
Optionally, when the tomographic image is displayed in the preview window, the method further includes:
and judging whether the position of the organ in the tomographic image in the preview window meets a preset requirement or not, and when the position of the organ in the tomographic image in the preview window does not meet the preset requirement, translating and zooming the tomographic image.
Optionally, the organ in the tomographic image is displayed in a centered alignment manner, and the tomographic image in the preview window is displayed in a centered alignment manner.
Optionally, the step of determining whether the position of the organ in the tomographic image in the preview window meets a predetermined requirement includes:
drawing a minimum virtual rectangular frame capable of accommodating the organ on the sectional image; and the number of the first and second groups,
and judging whether the center of the minimum virtual rectangular frame is positioned at the center of the preview window, when the center of the minimum virtual rectangular frame is positioned at the center of the preview window, judging that the position of the organ in the tomographic image in the preview window meets a preset requirement, and when the center of the minimum virtual rectangular frame is not positioned at the center of the preview window, judging that the position of the organ in the tomographic image in the preview window does not meet the preset requirement.
Optionally, when the position of the organ in the tomographic image in the preview window does not meet a predetermined requirement, the tomographic image is translated until the center of the minimum virtual rectangular frame coincides with the center of the preview window, and the tomographic image is scaled.
Optionally, the lateral displacement of the tomographic image is Δ α, and a scaling γ for scaling the tomographic image satisfies a relationship:
γ＝(Δα+αj)；
wherein alpha isjAnd the abscissa of the center of the minimum virtual rectangular box in the preview window.
Optionally, the organ is a left breast, the left breast in the tomographic image is displayed in a left alignment manner, and the tomographic image in the preview window is displayed in a left alignment manner; and/or the organ is a right breast, the right breast in the tomographic image is displayed in a right alignment mode, and the tomographic image in the preview window is displayed in a right alignment mode.
Optionally, the chest wall of the breast in the tomographic image coincides with the corresponding edge of the tomographic image.
Optionally, the number of the preview windows is two, the two preview windows are arranged side by side and respectively display the tomographic images of the left breast and the right breast, and the chest wall of the left breast is overlapped with the chest wall of the right breast.
Optionally, the step of determining whether the position of the organ in the tomographic image in the preview window meets a predetermined requirement includes:
acquiring a position of a nipple of a breast in the tomographic image in a corresponding preview window; and the number of the first and second groups,
and judging whether the position of the nipple is positioned in the center of the corresponding preview window, judging that the position of the organ in the sectional image in the preview window meets a preset requirement when the position of the nipple is positioned in the center of the corresponding preview window, and judging that the position of the organ in the sectional image in the preview window does not meet the preset requirement when the position of the nipple is not positioned in the center of the corresponding preview window.
Optionally, when the position of the organ in the tomographic image in the preview window does not meet a predetermined requirement, the tomographic image is translated until the position of the nipple coincides with the center of the preview window, and the tomographic image is scaled.
Optionally, the lateral displacement of the tomographic image is Δ α, and a scaling γ for scaling the tomographic image satisfies a relationship:
γ＝(Δα+αj)；
wherein alpha isjThe abscissa of the nipple in the corresponding preview window.
The present invention also provides a system for processing a tomographic image, comprising:
the image acquisition module is used for acquiring a tomographic image sequence of an organ, wherein the tomographic image sequence comprises a plurality of tomographic images which are sequentially stacked;
the coordinate establishing module is used for establishing a three-dimensional coordinate system according to the tomographic image sequence;
the coordinate extraction module is used for extracting the three-dimensional coordinates of the edge points of the organ in each tomographic image and obtaining an edge point coordinate set representing the contour of the organ;
the model establishing module is used for establishing a three-dimensional contour model of the organ according to the edge point coordinate set;
a marking module that marks a position of a lesion of the organ in the tomogram and extracts at least three-dimensional coordinates representing the position of the lesion; and the number of the first and second groups,
a display module for displaying the lesion in the three-dimensional contour model.
The present invention also provides a terminal, including:
one or more processors; and the number of the first and second groups,
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the method of processing the tomographic image.
The present invention also provides a computer-readable storage medium on which a computer program is stored, characterized in that the program realizes the method of processing a tomographic image described above when executed by a processor.
In the method, the system, the terminal and the computer readable storage medium for processing the tomographic image, provided by the invention, the tomographic image sequence is placed in a three-dimensional coordinate system, then three-dimensional coordinates of edge points of an organ in the tomographic image are extracted, a three-dimensional contour model of the organ is established according to the obtained coordinate set of the edge points, and a lesion can be displayed in the three-dimensional contour model by marking and extracting the three-dimensional coordinates representing the lesion, so that the specific position of the lesion in a real three-dimensional space can be visually displayed, the position of the lesion can be accurately positioned, and a doctor is assisted in reading the image; in addition, in the process of establishing the three-dimensional contour model of the organ, only the edge points of the organ participate in calculation, so that the calculation amount is small, and the time consumption is low.
Drawings
FIG. 1 is a flowchart of a method for processing a tomographic image according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a tomographic image sequence of a breast provided in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a three-dimensional coordinate system established according to a sequence of tomographic images according to an embodiment of the present invention;
FIG. 4a is a schematic diagram of a first tomographic image in a tomographic image sequence provided by an embodiment of the present invention;
fig. 4b is a schematic diagram of a black-and-white image obtained by binarizing the first tomographic image according to the first embodiment of the present invention;
fig. 4c is a schematic diagram of edge points obtained by performing edge extraction on a black-and-white image according to a first embodiment of the present invention;
fig. 5a is a contour line corresponding to the ith tomographic image according to the first embodiment of the present invention;
FIG. 5b is a diagram illustrating contour lines corresponding to the i-m, i +1 and i +2 tomographic images according to the first embodiment of the present invention;
FIG. 5c is a schematic diagram of an embodiment of the present inventionFor in the contour fi、fi+1A schematic view of the triangular faces constructed to be connected with each other;
FIGS. 6a and 6b are three-dimensional contour models of a breast according to an embodiment of the present invention;
FIG. 7a is a schematic diagram of a doctor marking a lesion in a tomographic image according to an embodiment of the present invention;
FIGS. 7b and 7c are schematic diagrams illustrating a display mark point in a three-dimensional contour model according to an embodiment of the present invention;
FIG. 8a is another schematic diagram of a doctor marking a lesion in a tomographic image according to an embodiment of the present invention;
FIGS. 8b and 8c are schematic diagrams illustrating a circle displayed in a three-dimensional contour model according to an embodiment of the present invention;
fig. 9a and 9b are schematic diagrams of a case where the size of the breast in the tomographic image is too large and too small in the preview window, respectively, according to an embodiment of the present invention, where fig. 9a is the tomographic image of the left breast, and fig. 9b is the tomographic image of the right breast;
FIG. 9c is a schematic diagram of two preview windows displaying the tomographic images of the left and right breasts, respectively, according to an embodiment of the present invention;
FIG. 9d is a schematic diagram illustrating a comparison between the tomogram of FIG. 9c after being translated and zoomed and the tomogram of FIG. 9c according to a first embodiment of the present invention;
fig. 10a is a schematic diagram of edge points obtained by performing edge extraction on a black-and-white image according to a second embodiment of the present invention;
FIG. 10b is a schematic diagram of a first contour line and a second contour line corresponding to an ith tomographic image fault according to a second embodiment of the present invention;
FIG. 10c is a first contour line and a second contour line corresponding to the i-th, i + 1-th and i-1-th tomographic image slices respectively according to the second embodiment of the present invention;
FIG. 10d is a schematic view of triangular faces constructed to be connected to each other between the first contour lines and between the second contour lines according to the second embodiment of the present invention;
fig. 11a is a schematic diagram of displaying a tomographic image in a preview window according to a default display rule according to a third embodiment of the present invention;
FIG. 11b is a schematic diagram illustrating a comparison between the tomogram of FIG. 11a after being translated and zoomed and the tomogram of FIG. 11a according to a third embodiment of the present invention;
fig. 12 is a block diagram of a system for processing a tomographic image according to a fourth embodiment of the present invention.
Wherein the reference numerals are:
10-an image acquisition module 10; 20-coordinate establishing module; 30-a coordinate extraction module; 40-a model building module 40; 50-a labeling module; 60-a display module 60;
100-a sequence of tomographic images; 100 a-tomographic image; 101 a-a first tomographic image; 102 a-a second tomographic image; 100 b-black and white image; 200-a three-dimensional profile model; 300-preview window; 300 a-first preview window; 300 b-second preview window;
p-a predetermined pitch; q1-marker; q2-circle; q3-sphere; d-virtual dividing line.
Detailed Description
The following describes in more detail embodiments of the present invention with reference to the schematic drawings. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention.
Fig. 1 is a flowchart of a method for processing a tomographic image according to the present embodiment. As shown in fig. 1, the present embodiment provides a tomographic image processing method including steps S100 to S500.
Step S100 is performed to acquire a tomographic image sequence 100 of an organ, the tomographic image sequence 100 having a plurality of tomographic images 100a sequentially stacked.
Fig. 2 is a schematic diagram of a tomographic image sequence 100 of a breast provided by the present embodiment. As shown in fig. 2, a tomographic image scan is performed on a breast, a tomographic image sequence 100 of the breast is obtained, a plurality of tomographic images 100a in the tomographic image sequence 100 are sequentially stacked along a set direction, each tomographic image 100a is a two-dimensional image, and a doctor can observe whether the breast has a lesion and a two-dimensional feature of the lesion through the tomographic images 100 a.
It should be understood that the organ is not limited to the breast, but may also be an organ having a distinct edge and to which a tomography technique is applied, such as a heart, a brain stem, a liver, a kidney, and a pancreas, and the present embodiment is only described with the breast as an example, but should not be limited thereto.
Step S200 is executed to establish a three-dimensional coordinate system from the tomographic image sequence 100.
Fig. 3 is a schematic diagram of establishing a three-dimensional coordinate system according to a tomographic image sequence provided in this embodiment. As shown in fig. 3, an XYZ three-dimensional coordinate system is established with the top left corner of the first tomographic image 100a as the origin, the lateral direction and the longitudinal direction as the X direction and the Y direction, respectively, and the stacking direction of the tomographic images 100a as the Z direction. In this way, the tomographic image sequence 100 can be located in a three-dimensional coordinate system, and each pixel in each tomographic image 100a can be represented by a three-dimensional coordinate, where i represents a position (serial number) of the tomographic image 100a in the tomographic image sequence 100, and optionally, i is a natural number.
In this embodiment, in the tomographic image sequence 100, the size and the pixels of each tomographic image 100a are the same. Based on this, for example, a millimeter measurement unit is adopted in the three-dimensional coordinate system, and the actual physical dimensions pxiel spacing X and pixelsing y respectively corresponding to the width and height of one pixel of the tomographic image 100a and the layer thickness between the adjacent tomographic images 100a can be obtained from a digital Imaging and Communications in medicine file, so that the three-dimensional coordinate (X, v) of the pixel in the three-dimensional coordinate system can be obtained according to the following formula and the position (u, v) of any pixel in the i-th tomographic image 100a in the tomographic image 100ai(u,v)，Yi(u,v)，Zi(u,v))：
Xi(u,v)＝u*pixelSpacingX；
Yi(u,v)＝v*pixelSpacingY；
Zi(u,v)＝i*thickness。
It should be understood that, in the present invention, the selection of the origin, the X direction, the Y direction, and the Z direction of the XYZ three-dimensional coordinate system is not limited to this, the origin of the XYZ three-dimensional coordinate system may also be any point in the tomographic image sequence 100, and the X direction, the Y direction, and the Z direction may also be exchanged, and will not be described in detail herein.
Step S300 is executed: three-dimensional coordinates of edge points of the organ are extracted in each of the tomographic images 100a, and an edge point coordinate set representing the contour of the organ is obtained.
The present embodiment will explain a method of extracting three-dimensional coordinates of edge points of the organ in each of the tomographic images 100a by taking the first tomographic image 100a as an example.
Fig. 4a is a schematic diagram of a first tomographic image 100a in the tomographic image sequence 100 provided in the present embodiment. As shown in fig. 4a, the tomographic image 100a is preprocessed to perform background suppression, denoising, or contrast enhancement on the tomographic image 100a, so as to facilitate the subsequent image processing step.
Fig. 4b is a schematic diagram of a black-and-white image 100b obtained by binarizing the first tomographic image 100a according to the present embodiment. As shown in fig. 4b, the tomographic image 100a is binarized to obtain a black-and-white image 100b, where only black and white pixels in the black-and-white image 100b correspond to pixel values 0 and 255, respectively, and in fig. 4b, a black area is a background and a white area is a breast.
Fig. 4c is a schematic diagram of edge points obtained by performing edge extraction on the black-and-white image 100b according to this embodiment. As shown in fig. 4c, the pixels of the black-and-white image 100b are scanned in the X direction at every predetermined pitch P, the pixel value of each pixel of a row of pixels is sequentially acquired in the X direction at each scanning, and when a pixel having a sudden change in pixel value (a pixel having a pixel value that changes from 1 to 0) is scanned, the scanning is stopped, the pixel is determined as an edge point of the breast, and the three-dimensional coordinates of the edge point are extracted. In this way, after the black-and-white image 100b is scanned, all the edge points of the breast in the black-and-white image 100b can be extracted, and after all the edge points of the tomographic image 100a are extracted, all the edge points of the breast in the tomographic image sequence 100 can be obtained, so as to obtain an edge point coordinate set representing the contour of the breast.
Optionally, the predetermined pitch P may be 0 pixel, or 1 pixel, 2 pixels, or 3 pixels, that is, the pixels of the black-and-white image 100b may be scanned line by line to extract the edge points, or the pixels of the black-and-white image 100b may be scanned every few lines to extract the edge points. As can be understood, the edge points obtained by line-by-line scanning are more numerous, and the edge point coordinate set can more accurately represent the contour of the breast; the number of edge points obtained by scanning every few lines is correspondingly small, but the calculation amount and the calculation time can be reduced.
In this embodiment, each time the pixels of the black-and-white image 100b are scanned, unidirectional scanning is performed from left to right (with respect to fig. 4 c); as an alternative embodiment, each time the pixels of the black-and-white image 100b are scanned, unidirectional scanning may be performed from right to left, and in this case, the pixel with the abrupt change of the pixel value is the pixel with the pixel value changed from 0 to 1.
Step S400: and establishing a three-dimensional contour model of the organ according to the edge point coordinate set.
Firstly, the three-dimensional coordinates of all edge points in the edge point coordinate set are normalized (normalized to a range of-1 to 1) so as to facilitate 3D display and data storage. Specifically, assuming that the width of the tomographic image 100a is w, the height is h, and the number is n, the maximum size s of the 3D volume space formed by the entire tomographic image sequence 100 is:
Figure BDA0002827676250000101
after normalization, the three-dimensional coordinate of each edge point is (X)i(u,v)'，Yi(u,v)'，Zi(u,v)')：
Xi(u,v)'＝Xi(u,v)/s；
Yi(u,v)'＝Yi(u,v)/s；
Zi(u,v)'＝Zi(u,v)/s。
Next, all the edge points of each of the tomographic images 100a are curve-fitted to form a contour line corresponding to each of the tomographic images 100 a. FIG. 5a shows the contour f corresponding to the i-th tomographic image 100aiFIG. 5b shows the contour lines f corresponding to the i-m, i +1, and i +2 tomographic images 100ai-m、fi、fi+1And fi+2As shown in fig. 5a and 5b, each contour line of the tomographic image 100a includes all edge points extracted from the tomographic image 100a (of course, some edge points with large errors may be removed and are not on the contour line), each contour line is a part of the contour of the breast, and after all contour lines are arranged in sequence, the contour of the breast can be roughly seen; wherein m is a natural number smaller than i.
Further, mutually connected triangular faces are constructed on two adjacent contour lines, so that a continuous contour of the breast is fitted for 3D display. FIG. 5c is a schematic diagram of contour line f in the embodimenti、fi+1A schematic view of the triangular faces constructed to interconnect, as shown in FIG. 5c, to form a contour fi、fi+1For example, the contour line f is formed by connecting triangular surfacesi+1First edge point of (3) and contour line fiConnecting the first edge points of (c) to form the contour fiFirst edge point of (3) and contour line fi+1The second edge point of the first triangular surface is connected, so that a first triangular surface is formed; will outline the line fi+1Second edge point of (3) and contour line fiThe second edge point of the second triangular surface is connected, so that a second triangular surface is formed; will outline the line fiSecond edge point of (3) and contour line fi+1To form a third triangular face …; sequentially and alternately connecting contour lines fiAnd contour line fi+1At the edge point of (i), i.e. in the contour fiAnd contour line fi+1Form a triangle therebetweenShape network to fit the contour line fiAnd contour line fi+1A curved surface therebetween. After the construction of the triangular network between each two adjacent contour lines is completed, the three-dimensional contour model 200 of the breast shown in fig. 6a and 6b can be fit (fig. 6a and 6b are two different viewing angles of the three-dimensional contour model 200) for 3D display.
Further, when the three-dimensional contour model 200 is displayed in 3D, it is necessary to obtain a normal vector of a triangular surface, and in this embodiment, the normal vector of the triangular surface is calculated by a vector difference product method, but it should not be limited thereto.
After the normal vector of each triangular surface is obtained, 3D software such as OpenGL may be called to display the three-dimensional contour model 200, where the 3D software may directly display the three-dimensional contour model 200, or may store information corresponding to the three-dimensional contour model 200 in a standard file (e.g., STL file) form, and directly read the standard file for display when displaying.
Step S500 is performed to mark a location of a lesion of the organ in the tomographic image 100a and to extract at least three-dimensional coordinates representing the location of the lesion to display the lesion in the three-dimensional contour model 200.
Firstly, the tomographic image 100a is displayed in a preview window 300 for a doctor to read, and when the doctor looks up the tomographic image 100a, if a focus is observed, the position of the focus can be marked in the tomographic image 100a, and the position marked by the doctor is extracted and displayed in the three-dimensional contour model 200, so that the position of the focus in the breast can be visually observed in the three-dimensional contour model 200.
Fig. 7a is a schematic diagram of a doctor marking a lesion in a tomographic image 100 a. As shown in fig. 7a, the doctor may draw a marking point in the tomographic image 100a, where the marking point may be located in an area where the lesion is located and may reflect the position of the lesion. Fig. 7b and 7c are schematic diagrams illustrating the mark points displayed in the three-dimensional contour model 200. As shown in fig. 7b and 7c, the three-dimensional coordinates of the marking points are extracted, the positions of the lesions are represented by the three-dimensional coordinates of the marking points, and then the marking points are displayed in the three-dimensional contour model 200 according to the three-dimensional coordinates of the marking points. The marking method is simple and convenient, has small workload of doctors, and can be suitable for focus with smaller size.
Fig. 8a is another schematic diagram of a doctor marking a lesion in a tomographic image 100 a. As shown in fig. 8a, the doctor may draw a circle in the tomographic image 100a, the circle surrounding the lesion to circle the lesion, and the circle may reflect not only the position of the lesion but also the size of the lesion. Fig. 8b and 8c are schematic diagrams showing a circle in the three-dimensional contour model 200. As shown in fig. 8b and 8c, the three-dimensional coordinates of the center of the circle are extracted and the number r of pixels occupied by the radius of the circle is calculatedpThen, a sphere is drawn in the three-dimensional contour model 200 by using the three-dimensional coordinates of the center of the circle and the radius of the circle, and the sphere can represent the position and the size of the focus.
In this embodiment, the radius R of the circle may be calculated according to the following formula:
R＝(rp*pixelSpacingX)/s。
the marking method can visually display the position and the size of the focus, and can be suitable for the focus with larger size.
Of course, the marking modes of drawing the marking points and drawing the circles in the tomographic image 100a may be used simultaneously, and a doctor may select one or two modes according to the observed lesions.
Further, when the tomographic images 100a are captured and displayed in the preview window 300 for a doctor to read, each tomographic image 100a is displayed in the preview window 300 according to a default display rule, so that each tomographic image 100a can be displayed. However, due to different shooting angles or different breast sizes, the size, shape and/or position of the breast in the tomographic image 100a corresponding to different patients may be different, and the breast in the tomographic image 100a displayed in the preview window 300 is too large or too small, which may affect the reading experience of the doctor.
Fig. 9a and 9b are schematic diagrams illustrating a case where the size of a breast in a slice image is too large and too small in the preview window 300, respectively, where fig. 9a is a slice image of a left breast and fig. 9b is a slice image of a right breast. As can be seen from fig. 9a and 9b, when the breast size is too small, it is difficult for the doctor to observe whether a lesion exists in the tomographic image, and if a lesion exists, it is difficult to accurately mark the lesion.
With continued reference to fig. 9a and 9b, it should be understood that, for convenience of doctor's interpretation, in the tomographic image, the chest wall (the side away from the nipple) of the breast coincides with the corresponding edge of the tomographic image, for example, the tomographic images displayed in the preview window 300 in fig. 9a and 9b are the tomographic image of the left breast and the tomographic image of the right breast, respectively, and for convenience of distinction, the tomographic image of the left breast is hereinafter referred to as a first tomographic image 101a, and the tomographic image of the right breast is hereinafter referred to as a second tomographic image 102 a. Wherein the left breast in the first tomographic image 101a is displayed in left alignment, and the chest wall of the left breast coincides with the left side edge of the first tomographic image 101 a; the right breast in the second tomographic image 102a is displayed in right alignment in the second tomographic image 102a, and the chest wall of the right breast coincides with the right edge of the second tomographic image 102 a. When the first tomographic image 101a or the second tomographic image 102a is displayed in the preview window 300, an edge of the first tomographic image 101a or the second tomographic image 102a should also coincide with a corresponding edge of the preview window 300, wherein when the preview window 300 displays the first tomographic image 101a, the first tomographic image 101a is displayed in a left-aligned manner, and a left edge of the first tomographic image 101a coincides with a left edge of the preview window 300; when the second tomographic image 102a is displayed, the second tomographic image 102a is displayed in a right alignment manner, and a right edge of the second tomographic image 102a coincides with a right edge of the preview window 300.
Further, fig. 9c shows a schematic diagram when two preview windows 300 simultaneously display the tomographic images 100a of the left and right breasts. As shown in fig. 9c, the number of the preview windows 300 may be two, that is, a first preview window 300a and a second preview window 300b, and the first preview window 300a and the second preview window 300b are arranged side by side and are seamlessly butted, or it may be understood that the first preview window 300a and the second preview window 300b are actually two display regions of one display window. The first preview window 300a is located on the left side and is used for displaying the second tomographic image 102a, and the second preview window 300b is located on the right side and is used for displaying the first tomographic image 101 a.
As described above, the second tomographic image 102a is displayed in the first preview window 300a in a right-aligned manner, the first tomographic image 101a is displayed in the second preview window 300b in a left-aligned manner, a right edge of the second tomographic image 102a coincides with a left edge of the first tomographic image 101a, and a chest wall of the right breast in the second tomographic image 102a coincides with a chest wall of the left breast in the first tomographic image 101a, so that a doctor can visually check the left and right breasts of the patient for the doctor's contrast.
With continued reference to fig. 9c, when the first preview window 300a and the second preview window 300b display the second tomographic image 102a and the first tomographic image 101a according to the default display rule, the right breast in the second tomographic image 102a and the left breast in the first tomographic image 101a are not aligned in the longitudinal direction, which may affect the reading experience of the doctor.
Based on this, when the tomographic image 100a is displayed in the preview window 300, it may be determined whether the position of the breast in the tomographic image 100a in the preview window 300 satisfies a predetermined requirement, and when the position of the breast in the tomographic image 100a in the preview window 300 does not satisfy the predetermined requirement, the tomographic image 100a may be translated and scaled so that the tomographic image 100a is displayed in the preview window 300 in an appropriate position and size.
Fig. 9d is a schematic diagram illustrating the embodiment comparing the tomographic image 100a in fig. 9c after translating and scaling the tomographic image 100a in fig. 9 c. As shown in fig. 9d, the second tomographic image 102a and the first tomographic image 101a are displayed in the first preview window 300a and the second preview window 300b according to the default display rule, and the coordinates (α) of the nipple of the right breast in the first preview window 300a are first acquiredj1，βj1) And acquiring coordinates (α) of the nipple of the left breast in the second preview window 300bj2，βj2) And then judges whether or not the nipple of the right breast and the nipple of the left breast are respectively located at the center (α) of the first preview window 300a01，β01) And the center (alpha) of the second preview window 300b02，β02). When (alpha)j1，βj1) And (alpha)01，β01) Same, (alpha)j2，βj2) And (alpha)02，β02) When the same, the nipple of the right breast in the second tomographic image 102a is at the center of the first preview window 300a, and the nipple of the left breast in the first tomographic image 101a is at the center of the second preview window 300b, the second tomographic image 102a and the first tomographic image 101a are reasonably displayed in the first preview window 300a and the second preview window 300b, and the reading experience of the doctor is not affected; on the contrary, when (alpha)j1，βj1) And (alpha)01，β01) Is not identical or (alpha)j2，βj2) And (alpha)02，β02) When the difference is not the same, it indicates that the nipple of the right breast in the second tomographic image 102a is not located in the center of the first preview window 300a, or the nipple of the left breast in the first tomographic image 101a is not located in the center of the second preview window 300b, and the display of the second tomographic image 102a in the first preview window 300a or the display of the first tomographic image 101a in the second preview window 300b is not reasonable, which may affect the reading experience of the doctor.
Then, calculating the first preview windowCoordinates (α) of nipple of right breast in mouth 300aj1，βj1) And the center coordinate (alpha) of the first preview window 300a01，β01) Is offset by Δ α 1(Δ α 1 ═ α)j1-α01| and a longitudinal shift amount Δ β 1(Δ β 1 ═ β |)j1-β01|) calculating the center coordinates (α) of the nipple of the left breast in the second preview window 300b and the second preview window 300bj2，βj2) Is (a) is offset by a lateral offset amount Δ α 2(Δ α 2 ═ αj2-α02| and a longitudinal shift amount Δ β 2(Δ β 2 ═ β |)j2-β02|). The second tomographic image 102a is moved by- Δ α 1 in the lateral direction and- Δ β 1 in the longitudinal direction, the first tomographic image 101a is moved by- Δ α 2 in the lateral direction and- Δ β 2 in the longitudinal direction, and after the movement, the nipple of the right breast in the second tomographic image 102a is located at the center of the first preview window 300a, and the nipple of the left breast in the first tomographic image 101a is located at the center of the second preview window 300 b.
Next, the second tomographic image 102a and the first tomographic image 101a are scaled, the scaling of the second tomographic image 102a is γ 1, and the scaling of the first tomographic image 101a is γ 2, where the scaling γ 1 is (Δ α 1+ α)j1)/αj1，γ2＝(Δα2+αj2)/αj2. After the second tomographic image 102a and the first tomographic image 101a are zoomed, the breast in the second tomographic image 102a and the first tomographic image 101a can be displayed in the first preview window 300a and the second preview window 300b in an appropriate size, which is convenient for a doctor to read and mark a lesion.
Example two
The difference from the first embodiment is that in this embodiment, the edge extraction is performed on the black-and-white image 100b in another way to obtain the three-dimensional coordinates of the edge points of the organ.
Specifically, in the present embodiment, the organ is a heart, a brain stem, a liver, a kidney, a pancreas, or the like, and the present embodiment will be described by taking the organ as the heart as an example. The heart in the tomogram is usually located in the central region and is a closed figure with closed edge contours. As in the first embodiment, in this embodiment, each tomographic image is subjected to preprocessing and binarization in sequence to obtain a black-and-white image 100 b.
Fig. 10a is a schematic diagram of the black-and-white image 100b obtained by edge extraction to obtain edge points, and as shown in fig. 10a, the black-and-white image 100b is divided into a first part and a second part by a virtual dividing line d, in this embodiment, the virtual dividing line d extends along the Y direction, and the first part and the second part are respectively arranged on the left and right sides of the virtual dividing line d, that is, the virtual dividing line d divides the black-and-white image 100b into the left and right parts. In a direction perpendicular to the virtual dividing line (in the X-direction), each row of pixels of the first and second portions has only one pixel with an abrupt change in pixel value, i.e. each row of pixels of the first and second portions has one edge point.
The pixels of the black-and-white image 100b are scanned along the X direction at intervals of a predetermined pitch P, each time the scan is performed, the first portion sequentially acquires the pixel value of each pixel in one pixel row along the positive direction of the X direction, the second portion sequentially acquires the pixel value of each pixel in one pixel row along the negative direction of the X direction, when the pixel with a sudden change in pixel value is scanned (the pixel with the pixel value changed from 0 to 1), the scan is stopped, the pixels with sudden change in pixel value in the first portion and the second portion are respectively used as the edge points of the heart, and the three-dimensional coordinates of the edge points in the first portion and the second portion are respectively extracted. In this way, after the black-and-white image 100b is scanned, all edge points of the heart in the tomographic image 100a corresponding to the black-and-white image 100b can be extracted, and after all the edge points of the tomographic image 100a are extracted, all the edge points of the heart in the tomographic image sequence 100 can be obtained, so as to obtain an edge point coordinate set representing the outline of the heart.
In this embodiment, each time a row of pixels of the black-and-white image 100b is scanned, the first portion is scanned from left to right (with respect to fig. 10a), and the second portion is scanned from right to left (with respect to fig. 10a), that is, each time a row of pixels of the black-and-white image 100b is scanned, the bidirectional scanning is performed, so that all edge points of the first portion and the second portion can be obtained respectively.
As an alternative embodiment, the virtual dividing line d may extend along the X direction to divide the black-and-white image 100b into an upper portion and a lower portion, and the first portion and the second portion are respectively disposed on the upper and lower sides of the virtual dividing line d. In this case, when scanning the pixels of the monochrome image 100b, it is necessary to scan one row of the pixels of the monochrome image 100b along the Y direction, and each time one row of the pixels of the monochrome image 100b is scanned, the first portion is scanned from the top to the bottom (with respect to fig. 10a), and the second portion is scanned from the bottom to the top (with respect to fig. 10a), and the bidirectional scanning is also performed.
It should be understood that the virtual dividing line d in the present embodiment is not limited to one, and when the shape of the organ is irregular, the black-and-white image 100b may be divided by two parallel virtual dividing lines d, which will not be explained one by one here.
It should be understood that the manner of edge extraction for the black-and-white image 100b in the present embodiment is also applicable to the black-and-white image 100b of the breast, and in this case, the virtual dividing line d extends along the X direction.
Further, as in the first embodiment, after the edge point coordinate set is obtained, normalization processing (normalization to an interval of-1 to 1) may be performed on the three-dimensional coordinates of all edge points in the edge point coordinate set, so as to facilitate 3D display and data storage.
Next, all the edge points of the first portion of each of the tomographic images 100a are curve-fitted to form a first contour line corresponding to the first portion of each of the tomographic images 100a, and all the edge points of the second portion of each of the tomographic images 100a are curve-fitted to form a second contour line corresponding to the second portion of each of the tomographic images 100a, so that each of the tomographic images 100a has the corresponding first contour line and the corresponding second contour line. FIG. 10b showsFirst contour f corresponding to the i-th tomographic image 100ai1And a second contour fi2FIG. 10c shows first contour lines f corresponding to the i-th, i + 1-th and i-1-th tomograms 100ai1、fi1+1、fi1-1And a second contour fi2、fi2+1、fi2-1As shown in fig. 10b and 10c, the first contour line and the second contour line of each of the tomographic images 100a include all edge points extracted from the first portion and the second portion of the tomographic image 100a (of course, some edge points with large errors may be removed and thus are not on the first contour line or the second contour line), each contour line is a portion of the contour of the heart, and after all contour lines are sequentially arranged, the contour of the heart can be roughly seen.
Further, mutually connected triangular faces are constructed on the adjacent two first contour lines and the adjacent two second contour lines, so as to fit the continuous contour of the heart for 3D display. FIG. 10d is the first contour f provided in this embodimenti1、fi1-1In between and on the second contour fi2、fi2-1Between them, as shown in FIG. 10d, to form a first contour fi1、fi1-1For example, the first contour line fi1First edge point of (3) and first contour line fi1-1Connecting the first edge point of (c) to the first contour fi1-1First edge point of (3) and first contour line fi1The second edge point of the first triangular surface is connected, so that a first triangular surface is formed; the first contour line fi1Second edge point of (3) and first contour fi1-1The second edge point of the second triangular surface is connected, so that a second triangular surface is formed; the first contour line fi1-1Second edge point of (3) and first contour fi1To form a third triangular face …; sequentially and alternately connecting the first contour lines fi1And a first contour fi1-1At the edge point of (i), i.e. in the first contour fi1And a first contour fi1-1A triangular network is constructed between the two so as to fit a first contour line fi1And a first contour fi1-1A curved surface therebetween. Correspondingly, in the second contour fi2And a second contour fi2-1The method for constructing the triangular network is similar, and redundant description is omitted here.
After the surface fitting between every two adjacent first contour lines and every two adjacent second contour lines is completed, a first contour model and a second contour model can be respectively formed, wherein the first contour model and the second contour model correspond to the contours of the left part and the right part of the heart.
Next, a triangular network is constructed between the first contour line of the first contour model edge and the second contour line of the second contour model edge, thereby fitting the first contour model and the second contour model to the three-dimensional contour model 200 of the heart. It should be understood that in constructing the triangular network, the positions of the first contour line and the second contour line should correspond, i.e., the triangular network should be constructed between the first contour line and the second contour line corresponding to the positions, so as to prevent the three-dimensional contour model 200 of the heart from being distorted.
EXAMPLE III
Unlike the first embodiment, in the present embodiment, the organ is not a breast, but a heart, a brain stem, a liver, a kidney, a pancreas, and the like, and the present embodiment will be described by taking the organ as a heart as an example. When the tomographic image 100a is captured, the heart is usually located as much as possible in the central region of the tomographic image 100a, which is convenient for observation. When the tomographic image 100a is displayed in the preview window 300, it is also preferably displayed in a centered alignment manner, which is convenient for a doctor to read.
Fig. 11a is a schematic diagram of displaying the tomographic image 100a in the preview window 300 according to the default display rule provided in the present embodiment. As shown in fig. 11a, in order to determine whether the position of the breast in the tomographic image 100a in the preview window 300 meets a predetermined requirement, the tomographic image 100a may be displayed in the preview window 300 according to a default display rule, and as can be seen from fig. 11a, the tomographic image 100a displayed in the preview window 300 may be shifted in position or may be too large/too small in size.
Fig. 11b is a schematic diagram illustrating the embodiment comparing the tomographic image 100a in fig. 11a after translating and zooming the tomographic image 100a in fig. 11 a. As shown in fig. 11b, a minimum virtual rectangular frame capable of accommodating a center is first drawn in the preview window 300, and the coordinate (α) of the center of the minimum virtual rectangular frame is acquiredj3，βj3). Then, it is determined whether the center of the minimum virtual rectangular frame is located at the center of the preview window 300 when the coordinate (α) of the center of the minimum virtual rectangular frame isj3，βj3) Coordinates (alpha) with the center of the preview window 30003，β03) When the position of the heart in the tomographic image 100a in the preview window 300 meets a predetermined requirement, the tomographic image 100a is reasonably displayed in the preview window 300, and the reading experience of the doctor is not influenced; when the coordinate (alpha) of the center of the minimum virtual rectangular framej3，βj3) Coordinates (alpha) with the center of the preview window 30003，β03) If the positions of the heart in the tomographic image 100a in the preview window 300 are not the same, it is determined that the positions of the heart in the tomographic image 100a in the preview window 300 do not meet a predetermined requirement, and the display of the tomographic image 100a in the preview window 300 is not reasonable, which may affect the reading experience of the doctor.
Next, a lateral shift amount Δ α 3 between the center of the minimum virtual rectangular frame and the center of the preview window 300 is calculated (Δ α 3 ═ α)j3-α03| and a longitudinal offset Δ β 3(Δ β 3 ═ β |)j3-β03|). The tomographic image 100a in the preview window 300 is shifted by- Δ α 3 in the lateral direction and by- Δ β 3 in the longitudinal direction, and after the shift, the heart in the tomographic image 100a in the preview window 300 is located in the center region thereof.
Next, the tomographic image 100a in the preview window 300 is scaled, and the scaling of the tomographic image 100a in the preview window 300 is γ 3, where the scaling γ 3 is (Δ α 3+ α)j3)/αj3. After the tomographic image 100a is zoomed, the heart in the tomographic image 100a can be displayed in the preview window 300 in a suitable size, which is convenient for a doctor to read and mark a lesion.
Example four
Fig. 12 is a block diagram showing a configuration of a tomographic image processing system according to the present embodiment. As shown in fig. 12, the processing system of the tomographic image includes:
an image acquisition module 10 for acquiring a tomographic image sequence of an organ, the tomographic image sequence having a plurality of tomographic images sequentially stacked;
a coordinate establishing module 20, configured to establish a three-dimensional coordinate system according to the tomographic image sequence;
a coordinate extraction module 30, configured to extract three-dimensional coordinates of edge points of the organ in each of the tomographic images, and obtain an edge point coordinate set representing a contour of the organ;
the model establishing module 40 is used for establishing a three-dimensional contour model of the organ according to the edge point coordinate set;
a marking module 50 which marks a position of a lesion of the organ in the tomographic image and extracts at least three-dimensional coordinates representing the position of the lesion;
a display module 60 for displaying the lesion in the three-dimensional contour model.
Further, the present embodiment provides a terminal that can be used for processing of tomographic images. The terminal includes:
one or more processors;
a memory for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for processing a tomographic image as set forth in the above embodiments.
In this embodiment, the processor and the memory are both one, and the processor and the memory may be connected by a bus or in another manner.
The memory, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method of processing a tomographic image in an embodiment of the present invention. The processor executes various functional applications and data processing of the terminal, that is, implements the above-described tomographic image processing method, by executing the software programs, instructions, and modules stored in the memory.
The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the terminal, and the like. In addition, the tomographic image processing method memory may include a high-speed random access memory, and may further include a nonvolatile memory, such as at least one magnetic disk storage device, a flash memory device, or other nonvolatile solid-state storage devices. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The terminal proposed by the embodiment belongs to the same inventive concept as the method for processing the tomographic image proposed by the above embodiment, and the technical details which are not described in detail in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.
The present embodiment provides a storage medium on which a computer program is stored, which when executed by the processor, implements the method of processing a tomographic image as set forth in the above embodiments.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
In summary, in the method, the system, the terminal and the computer-readable storage medium for processing a tomographic image provided in this embodiment, a tomographic image sequence is placed in a three-dimensional coordinate system, then three-dimensional coordinates of edge points of an organ in the tomographic image are extracted, a three-dimensional contour model of the organ is established according to an acquired coordinate set of the edge points, and a lesion can be displayed in the three-dimensional contour model by marking and extracting three-dimensional coordinates representing the lesion, so that a specific position of the lesion in a real three-dimensional space can be visually displayed, a position of the lesion can be accurately positioned, and a doctor is assisted in reading a film; in addition, in the process of establishing the three-dimensional contour model of the organ, only the edge points of the organ participate in calculation, so that the calculation amount is small, and the time consumption is low.
The above description is only a preferred embodiment of the present invention, and does not limit the present invention in any way. It will be understood by those skilled in the art that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (15)

1. A method of processing a tomographic image, comprising:
acquiring a tomographic image sequence of an organ, wherein the tomographic image sequence comprises a plurality of tomographic images which are sequentially stacked;
establishing a three-dimensional coordinate system according to the tomographic image sequence;
extracting three-dimensional coordinates of edge points of the organ from each tomographic image, and obtaining an edge point coordinate set representing the contour of the organ;
establishing a three-dimensional contour model of the organ according to the edge point coordinate set; and the number of the first and second groups,
the position of a lesion of the organ is marked in the tomographic image, and at least three-dimensional coordinates characterizing the position of the lesion are extracted to display the lesion in the three-dimensional contour model.
2. The method of processing tomographic images as set forth in claim 1, wherein the step of extracting three-dimensional coordinates of edge points of the organ in each of the tomographic images includes:
carrying out binarization on the tomogram to obtain a black-and-white image; and the number of the first and second groups,
and performing edge extraction on the black-and-white image to obtain the three-dimensional coordinates of the edge points of the organ.
3. The tomographic image processing method according to claim 2, wherein the organ is a breast, and the step of performing edge extraction on the black-and-white image to obtain three-dimensional coordinates of edge points of the organ comprises:
and carrying out unidirectional scanning on a row of pixels of the black-and-white image at intervals of a preset interval along the transverse direction, taking the pixels with suddenly changed pixel values as the edge points during each scanning, and recording the three-dimensional coordinates of the edge points.
4. The tomographic image processing method as set forth in claim 3, wherein the step of building a three-dimensional contour model of the organ based on the set of edge point coordinates includes:
fitting the edge points extracted from each tomographic image into a corresponding contour line; and the number of the first and second groups,
and constructing a triangular network between the corresponding contour lines of every two adjacent tomograms so as to fit the three-dimensional contour model.
5. The method for processing a tomographic image according to claim 1, wherein the step of marking a position of a lesion of the organ in the tomographic image comprises:
displaying the tomogram in a preview window;
manually marking the location of a lesion of the organ.
6. The method of processing a tomographic image as set forth in claim 5, wherein the step of marking a position of a lesion of the organ in the tomographic image and extracting at least three-dimensional coordinates representing the position of the lesion to display the lesion in the three-dimensional contour model includes:
drawing a marking point on the tomogram, wherein the marking point is positioned in the focus;
extracting the three-dimensional coordinates of the marking points as the three-dimensional coordinates representing the positions of the focuses; and the number of the first and second groups,
and displaying the mark points in the three-dimensional contour model according to the three-dimensional coordinates of the mark points.
7. The method for processing a tomographic image according to claim 5, further comprising, when displaying the tomographic image in the preview window:
and judging whether the position of the organ in the tomographic image in the preview window meets a preset requirement or not, and when the position of the organ in the tomographic image in the preview window does not meet the preset requirement, translating and zooming the tomographic image.
8. The method of processing a tomographic image according to claim 7, wherein the organ in the tomographic image is displayed in a centered alignment, and the tomographic image in the preview window is displayed in a centered alignment.
9. The method of processing a tomographic image according to claim 7, wherein the organ is a left breast, the left breast in the tomographic image is displayed in left alignment, and the tomographic image in the preview window is displayed in left alignment; and/or the organ is a right breast, the right breast in the tomographic image is displayed in a right alignment mode, and the tomographic image in the preview window is displayed in a right alignment mode.
10. The method of processing a tomographic image as set forth in claim 9, wherein a chest wall of a breast in the tomographic image coincides with a corresponding edge of the tomographic image.
11. The method for processing a tomographic image according to claim 10, wherein there are two preview windows, the two preview windows are disposed side by side and display tomographic images of a left breast and a right breast, respectively, and a chest wall of the left breast coincides with a chest wall of the right breast.
12. The method for processing the tomographic image according to any of claims 9 to 11, wherein the step of determining whether a position of the organ in the tomographic image in the preview window satisfies a predetermined requirement includes:
acquiring a position of a nipple of a breast in the tomographic image in a corresponding preview window; and the number of the first and second groups,
and judging whether the position of the nipple is positioned in the center of the corresponding preview window, judging that the position of the organ in the sectional image in the preview window meets a preset requirement when the position of the nipple is positioned in the center of the corresponding preview window, and judging that the position of the organ in the sectional image in the preview window does not meet the preset requirement when the position of the nipple is not positioned in the center of the corresponding preview window.
13. A system for processing a tomographic image, comprising:
the image acquisition module is used for acquiring a tomographic image sequence of an organ, wherein the tomographic image sequence comprises a plurality of tomographic images which are sequentially stacked;
the coordinate establishing module is used for establishing a three-dimensional coordinate system according to the tomographic image sequence;
the coordinate extraction module is used for extracting the three-dimensional coordinates of the edge points of the organ in each tomographic image and obtaining an edge point coordinate set representing the contour of the organ;
the model establishing module is used for establishing a three-dimensional contour model of the organ according to the edge point coordinate set;
a marking module that marks a position of a lesion of the organ in the tomogram and extracts at least three-dimensional coordinates representing the position of the lesion; and the number of the first and second groups,
a display module for displaying the lesion in the three-dimensional contour model.
14. A terminal, characterized in that the terminal comprises:
one or more processors; and the number of the first and second groups,
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of processing a tomographic image as recited in any one of claims 1 to 12.
15. A computer-readable storage medium on which a computer program is stored, which program, when being executed by a processor, is characterized by carrying out the method of processing a tomographic image as recited in any one of claims 1 to 12.
CN202011454058.5A 2020-12-10 2020-12-10 Method, system, terminal and computer readable storage medium for processing tomographic image Pending CN112465802A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011454058.5A CN112465802A (en) 2020-12-10 2020-12-10 Method, system, terminal and computer readable storage medium for processing tomographic image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011454058.5A CN112465802A (en) 2020-12-10 2020-12-10 Method, system, terminal and computer readable storage medium for processing tomographic image

Publications (1)

Publication Number Publication Date
CN112465802A true CN112465802A (en) 2021-03-09

Family

ID=74800897

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011454058.5A Pending CN112465802A (en) 2020-12-10 2020-12-10 Method, system, terminal and computer readable storage medium for processing tomographic image

Country Status (1)

Country Link
CN (1) CN112465802A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102592283A (en) * 2012-02-21 2012-07-18 华南理工大学 Method for processing scalp positioning images of brain tumors
CN106373168A (en) * 2016-11-24 2017-02-01 北京三体高创科技有限公司 Medical image based segmentation and 3D reconstruction method and 3D printing system
CN110428887A (en) * 2019-08-05 2019-11-08 河南省三门峡市中心医院(三门峡市儿童医院、三门峡市妇幼保健院) A kind of brain tumor medical image three-dimensional reconstruction shows exchange method and system
CN110458950A (en) * 2019-08-14 2019-11-15 首都医科大学附属北京天坛医院 A kind of method for reconstructing three-dimensional model, mobile terminal, storage medium and electronic equipment
CN110738701A (en) * 2019-10-23 2020-01-31 左丙丽 tumor three-dimensional positioning system
CN111242877A (en) * 2019-12-31 2020-06-05 北京深睿博联科技有限责任公司 Mammary X-ray image registration method and device
CN111768878A (en) * 2020-06-30 2020-10-13 杭州依图医疗技术有限公司 Method for visually guiding focus and computer readable storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102592283A (en) * 2012-02-21 2012-07-18 华南理工大学 Method for processing scalp positioning images of brain tumors
CN106373168A (en) * 2016-11-24 2017-02-01 北京三体高创科技有限公司 Medical image based segmentation and 3D reconstruction method and 3D printing system
CN110428887A (en) * 2019-08-05 2019-11-08 河南省三门峡市中心医院(三门峡市儿童医院、三门峡市妇幼保健院) A kind of brain tumor medical image three-dimensional reconstruction shows exchange method and system
CN110458950A (en) * 2019-08-14 2019-11-15 首都医科大学附属北京天坛医院 A kind of method for reconstructing three-dimensional model, mobile terminal, storage medium and electronic equipment
CN110738701A (en) * 2019-10-23 2020-01-31 左丙丽 tumor three-dimensional positioning system
CN111242877A (en) * 2019-12-31 2020-06-05 北京深睿博联科技有限责任公司 Mammary X-ray image registration method and device
CN111768878A (en) * 2020-06-30 2020-10-13 杭州依图医疗技术有限公司 Method for visually guiding focus and computer readable storage medium

Similar Documents

Publication Publication Date Title
US8929635B2 (en) Method and system for tooth segmentation in dental images
CN106056537B (en) A kind of medical image joining method and device
US8761493B2 (en) Method and system for tooth segmentation in dental images
US8849016B2 (en) Panoramic image generation from CBCT dental images
US7492968B2 (en) System and method for segmenting a structure of interest using an interpolation of a separating surface in an area of attachment to a structure having similar properties
US8842904B2 (en) Method for tooth dissection in CBCT volume
JP4717585B2 (en) Medical image determination apparatus, medical image determination method and program thereof
CN111063424B (en) Intervertebral disc data processing method and device, electronic equipment and storage medium
CN107194909A (en) Medical image-processing apparatus and medical imaging processing routine
WO2020215734A1 (en) Three-dimensional reconstruction method and system for carotid artery ultrasound scanning
CN112001889A (en) Medical image processing method and device and medical image display method
JP3692050B2 (en) Image processing apparatus and method
CN109242947A (en) Three-dimensional ultrasound pattern display methods
CN107705350B (en) Medical image generation method, device and equipment
JP4964191B2 (en) Image processing apparatus and method, and program
CN111445575A (en) Image reconstruction method and device of Wirisi ring, electronic device and storage medium
CN110738633A (en) organism tissue three-dimensional image processing method and related equipment
CN108885797B (en) Imaging system and method
CN116051553B (en) Method and device for marking inside three-dimensional medical model
JP4887491B2 (en) MEDICAL IMAGE PROCESSING METHOD, DEVICE THEREOF, AND PROGRAM
CN115619790B (en) Hybrid perspective method, system and equipment based on binocular positioning
US9842398B2 (en) Dynamic local registration system and method
CN112465802A (en) Method, system, terminal and computer readable storage medium for processing tomographic image
CN111918611A (en) Abnormal display control method for chest X-ray image, abnormal display control program, abnormal display control device, and server device
EP2734147B1 (en) Method for segmentation of dental 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