CN113269798A - Medical image segmentation method and device, computer equipment and storage medium thereof - Google Patents
Medical image segmentation method and device, computer equipment and storage medium thereof Download PDFInfo
- Publication number
- CN113269798A CN113269798A CN202110528458.4A CN202110528458A CN113269798A CN 113269798 A CN113269798 A CN 113269798A CN 202110528458 A CN202110528458 A CN 202110528458A CN 113269798 A CN113269798 A CN 113269798A
- Authority
- CN
- China
- Prior art keywords
- bladder
- boundary
- image area
- pixel value
- image
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003709 image segmentation Methods 0.000 title claims abstract description 38
- 238000001914 filtration Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 15
- 230000002708 enhancing effect Effects 0.000 claims abstract description 11
- 230000001131 transforming effect Effects 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 14
- 238000002604 ultrasonography Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 10
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000004422 calculation algorithm Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000005457 optimization Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 210000002700 urine Anatomy 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 206010046555 Urinary retention Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003387 muscular Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002485 urinary effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a medical image segmentation method, a medical image segmentation device, computer equipment and a storage medium thereof. The method comprises the steps of acquiring a bladder image area and a non-bladder image area in a bladder ultrasonic image; selecting a coordinate origin in the bladder image area, and connecting the coordinate origin with the edge of the image area at intervals of a preset angle to form a plurality of pixel value connecting lines; filtering each pixel value connecting line to obtain a filtering result, confirming a boundary signal of the bladder image area according to the filtering result, and enhancing the boundary signal to obtain an initial boundary of the bladder image area; carrying out constraint processing on the initial boundary, and iteratively calculating an optimal target boundary; and transforming the target boundary to a rectangular coordinate system to obtain the optimal contour of the bladder image region. The invention adopts a searching and optimizing method with lower calculation amount to quickly confirm the optimal contour of the bladder image region so as to segment the target region, and has the advantages of high segmentation accuracy, low algorithm cost and low hardware requirement.
Description
Technical Field
The present invention relates to the field of medical image processing, and in particular, to a medical image segmentation method, apparatus, computer device, and storage medium thereof.
Background
The image segmentation has an important role in the imaging diagnosis, and the automatic segmentation can help a doctor to quickly determine the size and the position of an organ or a lesion, so that the heavy workload brought by manual labeling of the doctor can be reduced.
The bladder is a muscular saccular organ for storing urine in a human body, the volume of the bladder reflects the amount of urine stored in the human body, and the bladder is also an important parameter for clinical application of urology; in the diagnosis and treatment of the urinary system, the measurement results of the residual urine volume of the human bladder and the full urine volume of the bladder are important reference bases for doctors to diagnose cases; the method of non-invasive measurement of bladder volume using ultrasound devices has been widely used clinically; measuring bladder volume requires first an effective segmentation of the bladder image.
In the prior art, a plurality of bladder ultrasound image segmentation methods including a segmentation method based on deep learning appear, and although the segmentation accuracy is high, the segmentation method based on deep learning has high computational complexity, high requirements on running hardware and high overall cost.
Disclosure of Invention
The invention aims to provide a medical image segmentation method, a medical image segmentation device, computer equipment and a storage medium thereof, and aims to solve the problems of high computational complexity and high requirement on running hardware of the conventional segmentation method based on deep learning.
In order to solve the technical problems, the invention aims to realize the following technical scheme: there is provided a medical image segmentation method comprising:
acquiring a bladder ultrasonic image, wherein the bladder ultrasonic image comprises an image area and a background area, and the image area comprises a bladder image area and a non-bladder image area;
selecting a coordinate origin in the bladder image area, and connecting the coordinate origin with the edge of the image area at intervals of a preset angle to form a plurality of pixel value connecting lines;
filtering each pixel value connecting line to obtain a filtering result of the pixel value connecting line, and confirming a boundary signal of the bladder image area according to the filtering result;
enhancing the boundary signal of the bladder image area to obtain the initial boundary of the bladder image area;
carrying out constraint processing on the initial boundary, and iteratively calculating an optimal target boundary;
and transforming the target boundary to a rectangular coordinate system to obtain the optimal contour of the bladder image area.
In addition, an object of the present invention is to provide a medical image segmentation apparatus, including:
an acquisition unit, configured to acquire a bladder ultrasound image, where the bladder ultrasound image includes an image region and a background region, and the image region includes a bladder image region and a non-bladder image region;
the connecting unit is used for selecting a coordinate origin in the bladder image area, and connecting the coordinate origin with the edge of the image area at intervals of preset angles to form a plurality of pixel value connecting lines;
the confirming unit is used for carrying out filtering processing on each pixel value connecting line to obtain a filtering result of the pixel value connecting line and confirming a boundary signal of the bladder image area according to the filtering result;
the enhancing unit is used for enhancing the boundary signal of the bladder image area to obtain the initial boundary of the bladder image area;
the computing unit is used for carrying out constraint processing on the initial boundary and iteratively computing an optimal target boundary;
and the transformation unit is used for transforming the target boundary to a rectangular coordinate system to obtain the optimal contour of the bladder image region.
In addition, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the medical image segmentation method according to the first aspect when executing the computer program.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, causes the processor to execute the medical image segmentation method according to the first aspect.
The embodiment of the invention discloses a medical image segmentation method, a medical image segmentation device, computer equipment and a storage medium thereof. The method comprises the steps of acquiring a bladder image area and a non-bladder image area in a bladder ultrasonic image; selecting a coordinate origin in the bladder image area, and connecting the coordinate origin with the edge of the image area at intervals of a preset angle to form a plurality of pixel value connecting lines; filtering each pixel value connecting line to obtain a filtering result, confirming a boundary signal of the bladder image area according to the filtering result, and enhancing the boundary signal to obtain an initial boundary of the bladder image area; carrying out constraint processing on the initial boundary, and iteratively calculating an optimal target boundary; and transforming the target boundary to a rectangular coordinate system to obtain the optimal contour of the bladder image region. The embodiment of the invention adopts a searching and optimizing method with lower calculation amount to quickly confirm the optimal contour of the bladder image region so as to segment the target region, and has the advantages of high segmentation accuracy, low algorithm cost and low hardware requirement.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a medical image segmentation method according to an embodiment of the present invention;
FIG. 2 is a sub-flow diagram of a medical image segmentation method according to an embodiment of the present invention;
FIG. 3 is a sub-flow diagram of a medical image segmentation method according to an embodiment of the present invention;
FIG. 4 is an exemplary illustration of an ultrasound image of the bladder provided by an embodiment of the present invention;
FIG. 5 is a schematic diagram of a connection line for forming pixel values in an image area of a bladder according to an embodiment of the present invention;
FIG. 6 is a comparison of a bladder image region before and after boundary enhancement provided by an embodiment of the present invention;
FIG. 7 is a graph comparing signals at an angle before and after bladder boundary enhancement provided by an embodiment of the present invention;
FIG. 8 is a comparison of bladder profiles before and after optimization provided by an embodiment of the present invention;
fig. 9 is a schematic block diagram of a medical image segmentation apparatus provided by an embodiment of the present invention;
FIG. 10 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1, fig. 1 is a schematic flow chart of a medical image segmentation method according to an embodiment of the present invention;
as shown in fig. 1, the method includes steps S101 to S106.
S101, obtaining a bladder ultrasonic image, wherein the bladder ultrasonic image comprises an image area and a background area, and the image area comprises a bladder image area and a non-bladder image area.
In this embodiment, the bladder ultrasound image is a bladder ultrasound image of a human body, taking a convex probe as an example, the bladder ultrasound image acquired from an ultrasound device includes an image region and a background region, where the image region includes a bladder image region and a non-bladder image region, as shown in fig. 4, a sector region is an image region, a region outside the image region is a background region, and the bladder image region is a target region to be detected and segmented by the present invention, that is, a bladder region inside a closed curve in fig. 4.
Under the influence of an imaging principle and a human organ structure, a lot of noise is mixed in the bladder ultrasonic image, and the bladder is internally liquid-like, so that the bladder image area is a low-echo area in the bladder ultrasonic image; however, due to multiple reflections of the ultrasonic signals on the upper and lower walls of the bladder, some high-echo interference signals are often contained in the bladder cavity; therefore, the original bladder ultrasonic image needs to be subjected to noise reduction treatment; the noise reduction method can be to filter the bladder ultrasonic image through a two-dimensional filter operator or filter the bladder ultrasonic image through an anisotropic filtering method; in the bladder ultrasonic image after the filtering process, the echo intensity is relatively low in the bladder image area, and the bladder wall has relatively high echo intensity, which is also an important characteristic for distinguishing the bladder boundary.
S102, selecting a coordinate origin in the bladder image area, and connecting the coordinate origin with the edge of the image area at intervals of a preset angle to form a plurality of pixel value connecting lines.
In this embodiment, any point in the bladder image region is selected as the origin of coordinates, which may be selected manually or automatically by an algorithm according to a preset rule; the coordinates of the selected coordinate origin are [ Xs, Ys ]. Establishing a polar coordinate system by taking Xs and Ys as origins, connecting the coordinate origin with the edge of the image area at preset angles in the polar coordinate system to form a connecting line radiating from the coordinate origin to the periphery, taking image pixel values of the position of each point on the connecting line to form a pixel value connecting line, and marking as I (I, rho), as shown in FIG. 5, wherein I represents the ith angle, rho represents the rho-th point from the coordinate origin at the ith angle, I (I, rho) represents the pixel value of the rho-th point at the ith angle, and the pixel value connecting line end point position is marked as (Xe, Ye).
The preset angle may be 2 ° or another angle, and taking 2 ° as an example, there is a line connecting pixel values every 2 °, that is, 180 lines connecting pixel values in a 360 ° range with the origin of coordinates as the center of a circle.
S103, filtering each pixel value connecting line to obtain a filtering result of the pixel value connecting line, and confirming a boundary signal of the bladder image area according to the filtering result.
In this embodiment, the boundary signal of the bladder image area may be enhanced by performing filtering processing on the pixel value connection line, so as to remove most of the signals that are not the bladder boundary, and only highlight the boundary signal of the bladder image area, thereby facilitating to recognize the boundary signal of the bladder image area.
In one embodiment, as shown in fig. 2, the step S103 includes:
s201, filtering each pixel value connecting line through a step filter to obtain a filtering value of each pixel point on the pixel value connecting line;
s202, reserving pixel points with filtering values larger than 0 on each pixel value connecting line, and taking the filtering values of the reserved pixel points as boundary signals of the bladder image area.
In this embodiment, in the process of filtering the pixel value connection line, a filter with a variation trend may be adopted, for example, each pixel value connection line is filtered by using a 6-step filter [ -1, -1, -1, 1, 1, 1], so as to obtain a filter value of each pixel point on the pixel value connection line.
As described in step S101, in the bladder image region, the echo intensity is relatively low, and the bladder wall has relatively high echo intensity, so that the boundary of the bladder image region has a jump change from low echo to high echo, but the step filter is adopted in the present invention, so that the filter value is certainly greater than 0 at the boundary of the bladder image region, so that the filter value 0 is used as a defining parameter for distinguishing the boundary from the non-boundary, and parameters close to the filter value 0, such as 0.1, 0.2, etc., can be selected, and this embodiment is described with the filter value 0, so that in other echo uniform regions or regions transitioning from high echo to low echo, the filter value is less than or equal to 0; thus, the boundary signal of the bladder image area can be highlighted; and reserving pixel points with the filtering values larger than 0 on each pixel value connecting line, and taking the filtering values of the reserved pixel points as boundary signals of the bladder image area, so that the following search of the boundary of the bladder image area is easier and more accurate.
S104, enhancing the boundary signal of the bladder image area to obtain the initial boundary of the bladder image area.
Specifically, as shown in fig. 3, the step S104 includes:
s301, multiplying the boundary signal of the bladder image area by the pixel value of the corresponding pixel point position to enhance the pixel value of the boundary position of the bladder image area;
s302, taking the enhanced pixel points with the highest pixel values on the pixel value connecting lines, taking the pixel points with the highest pixel values on each pixel value connecting line as initial boundary points of the bladder image area, and sequentially connecting all the initial boundary points to construct an initial boundary of the bladder image area.
In this embodiment, since the image at the boundary of the bladder image area is relatively bright, the pixel value is relatively large, and the pixel value is relatively small due to the relatively dark inside the bladder image area; therefore, the contrast of the boundary of the bladder image region can be enhanced by multiplying the boundary signal of the bladder image region by the pixel value of the corresponding pixel point position, i.e. the pixel value of the boundary position of the bladder image region is further enhanced, as shown in fig. 6, fig. 6 is a contrast diagram before and after the boundary of the bladder image region is enhanced, it is obvious that only part of the boundary of the bladder image region is basically reserved in the enhanced bladder ultrasound image, and other regions, such as the inside of the bladder image region and the non-bladder image region, are darkened due to being suppressed.
Taking a pixel connecting line under the i-th angle in the images before and after the boundary enhancement of the bladder image area, as shown in fig. 7, an abscissa rho in the image represents a rho-th point from a coordinate origin on the current pixel value connecting line, an ordinate represents a pixel value after the boundary enhancement, a dotted line in the image represents a signal before the boundary enhancement, and a solid line represents a signal after the boundary enhancement, so that it can be obviously seen that the signal after the boundary enhancement is cleaner, and the boundary between the boundary and the non-boundary is more obvious. Observing the signal before the boundary enhancement, wherein the fluctuation of the signal amplitude along with the change of rho is large, so that the boundary position is difficult to accurately find out; and observing the signals after the boundary enhancement, the maximum value can be accurately extracted, the position corresponding to the maximum value is also the pixel point with the highest pixel value, the pixel point with the highest pixel value on each pixel value connecting line is used as the initial boundary point of the bladder image area, and then all the initial boundary points are connected in sequence, so that the initial boundary of the bladder image area can be constructed.
And S105, carrying out constraint processing on the initial boundary, and iteratively calculating an optimal target boundary.
Specifically, the constraining process performed on the initial boundary includes:
optimizing the initial boundary according to the following constraint formula:
wherein i is the ith angle, i is 1,2,3.. 180; p (i) is the distance from the coordinate origin of the pixel value connecting line of the ith angle to the initial boundary point; f (p (I)) is a constraint value of the distance from the coordinate origin on the pixel value connecting line of the ith angle to the corresponding initial boundary point, I [ (I, p (I) ] is the pixel value of the position of the initial boundary point under the ith angle, and k1 and k2 are weights respectively.
In this example, the first part [ p (i +1) -p (i)]2The change rate of the distance from the coordinate origin to the initial boundary point at the ith angle and the distance from the coordinate origin to the initial boundary point at the (i +1) th angle is the slope and the first derivative of the initial boundary position p at the ith angle; since the bladder boundary changes continuously and smoothly in the human body, the bladder boundaries at two adjacent angles i and i +1 should be closely located, i.e., [ p (i +1) -p (i)]2The smaller the value of this term, the better.
Second part I [ (I, p (I))]Normalized to [0, 1] pixel values]In between, because the bladder boundary is generally brighter and the gray value is very large, (1-I [ I, p (I))])2Smaller means that the position is more likely to be the target boundary, i.e. the value of this term should also be smaller as well.
Based on the above, the values of k1 and k2 can be adjusted to highlight the specific gravity of a certain part, so as to optimize the initial boundary; in addition to this, other amount of constraint can be added, such as adding the second derivative constraint term of p based on the first derivative of the bladder position p: [ p (i +2) -2. sup. p (i +1) + p (i)]2This may result in a smoother bladder profile.
Further, the iteratively calculating an optimal target boundary includes:
and (3) searching an optimal target boundary by taking the negative gradient direction of p (i) as a searching direction according to the following searching formula:
p(i)k+1＝p(i)k-λ*g(f(p(i)))；
wherein k is the kth iteration, k +1 is the kth iteration, λ is the search step length, and g (f (p (i))) is the gradient of f (p (i));
and when a preset iteration termination condition is reached, obtaining an optimal p (i), calculating corresponding target boundary points according to the optimal p (i), and sequentially connecting all the target boundary points to construct a target boundary.
In this embodiment, it can be seen from the above constraint formula for optimizing the initial boundary that when f (p (i)) takes the minimum value, it is the optimal target boundary to be calculated in the present invention, i.e. the process of solving the optimal solution under the given constraint, and the minimum value can be approximated by a gradual iterative calculation.
Specifically, during iteration, the initial value of p (i) is the distance from the coordinate origin of the pixel value connecting line of the ith angle to the initial boundary point, the negative gradient direction of p (i) is taken as the search direction, (because the direction is the fastest descending direction of the current position, the direction can approach the minimum value more quickly), the values of k, λ and g (f (p (i))) are respectively substituted into the search formula to carry out iteration search until the absolute value of the difference value of f (p (i)) between two adjacent iterations is smaller than the preset value or the iteration times k reach the preset times, the iteration termination condition is reached, and the distance value of p (i) at the moment is taken as the optimal value, so that the optimal target boundary can be obtained. And sequentially connecting the corresponding target boundaries under each angle to obtain the bladder contour. As shown in fig. 8, which is the bladder profile before and after optimization, wherein the dotted line represents the bladder profile before optimization and the solid line represents the bladder profile after optimization, it can be seen that the bladder profile after optimization is smoother and more in line with the real bladder profile.
And S106, transforming the target boundary to a rectangular coordinate system to obtain the optimal contour of the bladder image region.
Specifically, the step S106 includes:
calculating and obtaining an optimal profile according to the following formula:
x(i)＝Xs+p(i)*cos[angle(i)]；
y(i)＝Ys-p(i)*sin[angle(i)]；
where x (i) and y (i) are the optimal contour coordinate points at the i-th angle, Xs and Ys are the coordinate origins, and angle (i) is the optimal p (i) and the corresponding angle.
In this embodiment, values Xs, Ys, optimal p (i), and angle (i) are respectively substituted into the above formula to calculate and obtain an optimal contour coordinate point at a corresponding angle; and connecting the corresponding optimal contour coordinate points under all angles to obtain the optimal contour of the bladder image region, and accurately segmenting the bladder image region in the bladder ultrasonic image based on the optimal contour.
Embodiments of the present invention further provide a medical image segmentation apparatus for performing any one of the embodiments of the medical image segmentation method described above. Specifically, referring to fig. 10, fig. 10 is a schematic block diagram of a medical image segmentation apparatus according to an embodiment of the present invention.
As shown in fig. 9, the medical image segmentation apparatus 900 includes: an acquisition unit 901, a connection unit 902, a confirmation unit 903, an enhancement unit 904, a calculation unit 905, and a transformation unit 906.
An acquiring unit 901, configured to acquire a bladder ultrasound image, where the bladder ultrasound image includes an image region and a background region, and the image region includes a bladder image region and a non-bladder image region;
a connecting unit 902, configured to select a coordinate origin in the bladder image region, connect the coordinate origin with an edge of the image region at intervals of a preset angle, and form a plurality of pixel value connecting lines;
a confirming unit 903, configured to perform filtering processing on each pixel value connection line to obtain a filtering result of the pixel value connection line, and confirm a boundary signal of the bladder image area according to the filtering result;
an enhancing unit 904, configured to enhance a boundary signal of the bladder image region to obtain an initial boundary of the bladder image region;
a calculating unit 905, configured to perform constraint processing on the initial boundary, and iteratively calculate an optimal target boundary;
a transforming unit 906, configured to transform the target boundary to a rectangular coordinate system to obtain an optimal contour of the bladder image region.
The device adopts a searching and optimizing method with low calculation amount to quickly confirm the optimal contour of the bladder image region so as to segment the target region, and has the advantages of high segmentation accuracy, low algorithm cost and low hardware requirement; the method aims at solving the problem that the segmentation is not accurate easily when the signal-to-noise ratio is low, and has strong anti-interference performance.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The medical image segmentation apparatus described above may be implemented in the form of a computer program which may be run on a computer device as shown in fig. 10.
Referring to fig. 10, fig. 10 is a schematic block diagram of a computer device according to an embodiment of the present invention. The computer device 1000 is a server, and the server may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 10, the computer device 1000 includes a processor 1002, a memory, which may include a non-volatile storage medium 1003 and an internal memory 1004, and a network interface 1005 connected by a system bus 1001.
The nonvolatile storage medium 1003 can store an operating system 10031 and a computer program 10032. The computer program 10032, when executed, may cause the processor 1002 to perform a method of medical image segmentation.
The processor 1002 is used to provide computing and control capabilities, supporting the operation of the overall computer device 1000.
The internal memory 1004 provides an environment for running the computer program 10032 in the non-volatile storage medium 1003, which computer program 10032, when executed by the processor 1002, may cause the processor 1002 to perform the medical image segmentation method.
The network interface 1005 is used for network communication, such as providing transmission of data information. Those skilled in the art will appreciate that the configuration shown in fig. 10 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing device 1000 to which aspects of the present invention may be applied, and that a particular computing device 1000 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Those skilled in the art will appreciate that the embodiment of a computer device illustrated in fig. 10 does not constitute a limitation on the specific construction of the computer device, and that in other embodiments a computer device may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components. For example, in some embodiments, the computer device may only include a memory and a processor, and in such embodiments, the structures and functions of the memory and the processor are consistent with those of the embodiment shown in fig. 10, and are not described herein again.
It should be understood that, in the embodiment of the present invention, the Processor 1002 may be a Central Processing Unit (CPU), and the Processor 1002 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In another embodiment of the invention, a computer-readable storage medium is provided. The computer readable storage medium may be a non-volatile computer readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the medical image segmentation method of an embodiment of the invention.
The storage medium is an entity and non-transitory storage medium, and may be various entity storage media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses, devices and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A medical image segmentation method, comprising:
acquiring a bladder ultrasonic image, wherein the bladder ultrasonic image comprises an image area and a background area, and the image area comprises a bladder image area and a non-bladder image area;
selecting a coordinate origin in the bladder image area, and connecting the coordinate origin with the edge of the image area at intervals of a preset angle to form a plurality of pixel value connecting lines;
filtering each pixel value connecting line to obtain a filtering result of the pixel value connecting line, and confirming a boundary signal of the bladder image area according to the filtering result;
enhancing the boundary signal of the bladder image area to obtain the initial boundary of the bladder image area;
carrying out constraint processing on the initial boundary, and iteratively calculating an optimal target boundary;
and transforming the target boundary to a rectangular coordinate system to obtain the optimal contour of the bladder image area.
2. The medical image segmentation method according to claim 1, wherein the filtering processing on each of the pixel value lines to obtain a filtering result of the pixel value lines, and determining the boundary signal of the bladder image region according to the filtering result comprises:
filtering each pixel value connecting line through a step filter to obtain a filtering value of each pixel point on the pixel value connecting line;
and reserving pixel points with the filtering values larger than 0 on each pixel value connecting line, and taking the filtering values of the reserved pixel points as boundary signals of the bladder image area.
3. The medical image segmentation method according to claim 1, wherein the enhancing the boundary signal of the bladder image region to obtain an initial boundary of the bladder image region comprises:
multiplying the boundary signal of the bladder image area by the pixel value of the corresponding pixel point position to enhance the pixel value of the boundary position of the bladder image area;
and taking the enhanced pixel points with the highest pixel value on the pixel value connecting line, taking the pixel points with the highest pixel value on each pixel value connecting line as initial boundary points of the bladder image area, and sequentially connecting all the initial boundary points to construct an initial boundary of the bladder image area.
4. The medical image segmentation method according to claim 1, wherein the constraining the initial boundary includes:
optimizing the initial boundary according to the following constraint formula:
wherein I is the ith angle, I is 1,2,3.. 180, p (I) is the distance from the coordinate origin of the pixel value connecting line of the ith angle to the initial boundary point, f (p (I)) is the constraint value of the distance from the coordinate origin on the pixel value connecting line of the ith angle to the corresponding initial boundary point, I [ (I, p (I) ] is the pixel value of the position of the initial boundary point under the ith angle, and k1 and k2 are weights respectively.
5. The medical image segmentation method according to claim 4, wherein the iteratively calculating an optimal object boundary comprises:
and (3) searching an optimal target boundary by taking the negative gradient direction of p (i) as a searching direction according to the following searching formula:
p(i)k+1＝p(i)k-λ*g(f(p(i)))；
wherein k is the kth iteration, k +1 is the kth iteration, λ is the search step length, and g (f (p (i))) is the gradient of f (p (i));
and when a preset iteration termination condition is reached, obtaining an optimal p (i), calculating corresponding target boundary points according to the optimal p (i), and sequentially connecting all the target boundary points to construct a target boundary.
6. The medical image segmentation method according to claim 5, wherein the iteration termination condition is:
the absolute value of the difference value of f (p (i)) between two adjacent iterations is smaller than a preset value or the iteration number k reaches a preset number.
7. The medical image segmentation method according to claim 4, wherein transforming the target boundary to a rectangular coordinate system to obtain an optimal contour of the bladder image region comprises:
calculating and obtaining an optimal contour coordinate point according to the following formula:
x(i)＝Xs+p(i)*cos[angle(i)]；
y(i)＝Ys-p(i)*sin[angle(i)]；
where x (i) and y (i) are the coordinates of the optimal contour point at the i-th angle, Xs and Ys are the origin of coordinates, and angle (i) is the optimal p (i) and its corresponding angle.
8. A medical image segmentation apparatus, characterized by comprising:
an acquisition unit, configured to acquire a bladder ultrasound image, where the bladder ultrasound image includes an image region and a background region, and the image region includes a bladder image region and a non-bladder image region;
the connecting unit is used for selecting a coordinate origin in the bladder image area, and connecting the coordinate origin with the edge of the image area at intervals of preset angles to form a plurality of pixel value connecting lines;
the confirming unit is used for carrying out filtering processing on each pixel value connecting line to obtain a filtering result of the pixel value connecting line and confirming a boundary signal of the bladder image area according to the filtering result;
the enhancing unit is used for enhancing the boundary signal of the bladder image area to obtain the initial boundary of the bladder image area;
the computing unit is used for carrying out constraint processing on the initial boundary and iteratively computing an optimal target boundary;
and the transformation unit is used for transforming the target boundary to a rectangular coordinate system to obtain the optimal contour of the bladder image region.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of medical image segmentation of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the method of medical image segmentation of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110528458.4A CN113269798A (en) | 2021-05-14 | 2021-05-14 | Medical image segmentation method and device, computer equipment and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110528458.4A CN113269798A (en) | 2021-05-14 | 2021-05-14 | Medical image segmentation method and device, computer equipment and storage medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113269798A true CN113269798A (en) | 2021-08-17 |
Family
ID=77231015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110528458.4A Pending CN113269798A (en) | 2021-05-14 | 2021-05-14 | Medical image segmentation method and device, computer equipment and storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113269798A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152274A (en) * | 2023-04-23 | 2023-05-23 | 之江实验室 | Image segmentation method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705576A (en) * | 2019-09-29 | 2020-01-17 | 慧影医疗科技（北京）有限公司 | Region contour determining method and device and image display equipment |
| CN111091567A (en) * | 2020-03-23 | 2020-05-01 | 南京景三医疗科技有限公司 | Medical image registration method, medical device and storage medium |
| CN111429451A (en) * | 2020-04-15 | 2020-07-17 | 深圳市嘉骏实业有限公司 | Medical ultrasonic image segmentation method and device |
-
2021
- 2021-05-14 CN CN202110528458.4A patent/CN113269798A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705576A (en) * | 2019-09-29 | 2020-01-17 | 慧影医疗科技（北京）有限公司 | Region contour determining method and device and image display equipment |
| CN111091567A (en) * | 2020-03-23 | 2020-05-01 | 南京景三医疗科技有限公司 | Medical image registration method, medical device and storage medium |
| CN111429451A (en) * | 2020-04-15 | 2020-07-17 | 深圳市嘉骏实业有限公司 | Medical ultrasonic image segmentation method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152274A (en) * | 2023-04-23 | 2023-05-23 | 之江实验室 | Image segmentation method, device, equipment and storage medium |
| CN116152274B (en) * | 2023-04-23 | 2023-08-04 | 之江实验室 | Image segmentation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9119559B2 (en) | Method and system of generating a 3D visualization from 2D images | |
| US7856130B2 (en) | Object recognition system for medical imaging | |
| RU2653274C2 (en) | Coupled segmentation in conventional and contrast ultrasound 3d images | |
| CN111429451B (en) | Medical ultrasonic image segmentation method and device | |
| EP2357609B1 (en) | Adaptative hit-or-miss region growing for vessel segmentation in medical imaging | |
| CN107103605B (en) | Breast tissue segmentation method | |
| US20100322495A1 (en) | Medical imaging system | |
| Padmapriya et al. | Edge based image segmentation technique for detection and estimation of the bladder wall thickness | |
| US11455720B2 (en) | Apparatus for ultrasound diagnosis of liver steatosis using feature points of ultrasound image and remote medical-diagnosis method using the same | |
| CN106530236B (en) | Medical image processing method and system | |
| CN115843373A (en) | Multi-scale local level set ultrasonic image segmentation method fusing Gabor wavelets | |
| JP2008194239A (en) | Image processing apparatus and method for the same | |
| CN104361554B (en) | A kind of externa automatic testing method based on ivus image | |
| WO2008097630A2 (en) | 3d segmentation of the colon in mr colonography | |
| CN113269798A (en) | Medical image segmentation method and device, computer equipment and storage medium thereof | |
| CN107169978B (en) | Ultrasonic image edge detection method and system | |
| CN111539926B (en) | Image detection method and device | |
| CN112651984A (en) | Blood vessel lumen intimal contour extraction method and device, ultrasonic equipment and storage medium | |
| CN115861132B (en) | Blood vessel image correction method, device, medium and equipment | |
| CN110349203B (en) | Ultrasonic equipment and method for measuring blood vessel diameter in ultrasonic image thereof | |
| Georgieva et al. | Ultrasound image processing for improving diagnose of renal diseases | |
| CN107928707B (en) | Area rapid measurement method and system suitable for portable ultrasonic equipment | |
| CN110930394B (en) | Method and terminal equipment for measuring slope and pinnate angle of muscle fiber bundle line | |
| CN114170258A (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN115775217A (en) | Method for acquiring blood vessel digital structure, electronic device and storage medium |
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 |