CN113724264B - Image segmentation method, system and readable storage medium - Google Patents
Image segmentation method, system and readable storage medium Download PDFInfo
- Publication number
- CN113724264B CN113724264B CN202010457666.5A CN202010457666A CN113724264B CN 113724264 B CN113724264 B CN 113724264B CN 202010457666 A CN202010457666 A CN 202010457666A CN 113724264 B CN113724264 B CN 113724264B
- Authority
- CN
- China
- Prior art keywords
- image
- segmented
- segmentation
- tissue organ
- region
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 97
- 238000003709 image segmentation Methods 0.000 title claims abstract description 53
- 210000000056 organ Anatomy 0.000 claims abstract description 137
- 230000011218 segmentation Effects 0.000 claims abstract description 86
- 239000011159 matrix material Substances 0.000 claims abstract description 30
- 230000000877 morphologic effect Effects 0.000 claims description 32
- 210000004204 blood vessel Anatomy 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 5
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 4
- 239000010931 gold Substances 0.000 claims description 4
- 229910052737 gold Inorganic materials 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000009792 diffusion process Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 11
- 238000003745 diagnosis Methods 0.000 abstract description 6
- 230000003993 interaction Effects 0.000 abstract description 5
- 210000001519 tissue Anatomy 0.000 description 117
- 210000004072 lung Anatomy 0.000 description 29
- 230000008569 process Effects 0.000 description 9
- 210000001147 pulmonary artery Anatomy 0.000 description 9
- 238000002591 computed tomography Methods 0.000 description 8
- 230000002685 pulmonary effect Effects 0.000 description 8
- 230000009471 action Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 6
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010968 computed tomography angiography Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000002600 positron emission tomography Methods 0.000 description 1
- 210000004879 pulmonary tissue Anatomy 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 210000002345 respiratory system Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30061—Lung
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention provides an image segmentation method, an image segmentation system and a readable storage medium, wherein a multiscale hessian matrix is adopted to carry out enhancement treatment on an image to be segmented to enhance a second tissue organ, binarization treatment is carried out to obtain a first segmented image of the second tissue organ, meanwhile, the region of the first tissue organ in the image to be segmented is segmented to obtain a region segmented image of the first tissue organ, and finally, the first segmented image is segmented again according to the region segmented image to obtain a second segmented image of the second tissue organ image. The invention enhances the second tissue and organ through the multiscale hessian matrix, improves the efficiency and the precision of the segmentation algorithm, and reduces the complicated operation of man-machine interaction. In addition, the segmentation accuracy of the second tissue organ image is further improved by automatically segmenting the first tissue organ region. In addition, the image segmentation algorithm has strong universality, realizes an end-to-end algorithm flow, and can better assist doctors in improving diagnosis accuracy.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an image segmentation method, system, and readable storage medium.
Background
The pulmonary vessel imaging in the field of medical image segmentation has the characteristics of low vessel contrast, complex fine vessel structure and multiple pulmonary tissue structures, which brings great difficulty to the doctor for analyzing the pulmonary structure of the medical image of the patient. Therefore, it is particularly important to accurately segment the lung medical image, and the accurate segmentation can provide high-quality lung structure information for doctors, thereby being beneficial to the rapid diagnosis of the doctors.
Angiographic techniques include Computed Tomography Angiography (CTA), nuclear Magnetic Resonance Angiography (MRA), and the like. The blood vessel imaging obtains a three-dimensional image, not only blood vessel tissues but also other tissues (bones, fat, muscles, lung tissues and the like) around the blood vessel, and cannot bring accurate diagnosis to doctors. Therefore, the whole blood vessel region is extracted from the three-dimensional image, and the morphology of the blood vessel is displayed by the three-dimensional display technology, so that the diagnosis accuracy of doctors can be improved.
Although there are many techniques for vessel segmentation available, the vessel segmentation problem remains a very challenging task. At present, the pulmonary vessel segmentation method mainly adopts manual and semiautomatic modes, and the existing semiautomatic vessel segmentation method can be roughly divided into two types: top-down and bottom-up.
However, the existing method for segmenting the pulmonary blood vessels has the following disadvantages:
(1) The manual blood vessel segmentation method requires a lot of time and effort;
(2) The top-down semi-automatic segmentation method requires the artificial input of seed points as starting conditions, then iteratively merging adjacent areas based on target errors, and finally generating images;
(3) The semi-automatic segmentation method from bottom to top utilizes a tubular detection filter to segment the blood vessel, and does not need to manually input initialization information, but the method has high calculation cost, is greatly influenced by noise and can not obtain a complete blood vessel structure in a region with low contrast.
Disclosure of Invention
The invention aims to provide an image segmentation method, an image segmentation system and a readable storage medium, which can not only improve the overall image segmentation precision, but also effectively reduce the complicated operation of man-machine interaction.
In order to achieve the above object, the present invention provides an image segmentation method, comprising:
acquiring an image to be segmented;
performing enhancement processing on the image to be segmented by utilizing a multiscale hessian matrix to obtain an enhanced image after the second tissue organ is enhanced;
performing binarization processing on the enhanced image to obtain a first segmentation image of the second tissue organ;
performing segmentation processing on the region where the first tissue organ is located in the image to be segmented to obtain a region segmentation image of the first tissue organ;
and segmenting the first segmented image according to the region segmentation image to obtain a second segmented image of the second tissue organ image.
Optionally, in the image segmentation method, before the enhancement processing is performed on the image to be segmented by using the multiscale hessian matrix, the method further includes:
preprocessing the image to be segmented to filter noise in the blood vessel image to be segmented;
the enhancement processing is carried out on the image to be segmented by utilizing a multiscale hessian matrix, specifically:
and carrying out enhancement processing on the preprocessed image to be segmented by utilizing the multiscale hessian matrix.
Optionally, in the image segmentation method, the enhancing the image to be segmented by using a multiscale hessian matrix includes:
and on the basis of the hessian matrix, carrying out enhancement processing on the image to be segmented according to a preset scale range and the preset scale iteration times.
Optionally, in the image segmentation method, the scale range is 0.5-5, and the iteration number range is 5-15.
Optionally, in the image segmentation method, the segmenting the region where the first tissue organ in the image to be segmented is located includes:
performing binarization processing on the image to be segmented to obtain a region preliminary segmentation image of the first tissue organ;
and setting a seed point in a boundary area of the area preliminary segmentation image, and distinguishing the first tissue organ by a morphological method by taking the seed point as an initial point to obtain the area segmentation image of the first tissue organ.
Optionally, in the above image segmentation method, the differentiating the first tissue organ by a morphological method includes:
and taking the first seed point as an initial point, and distinguishing the first tissue organ by a morphological water-diffusion gold mountain method.
Optionally, in the above image segmentation method, after distinguishing the first tissue organ, the method further includes:
and performing hole filling and/or boundary repairing treatment on the region of the first tissue organ by adopting morphological closing operation based on a preset first morphological parameter.
Optionally, in the above image segmentation method, the segmenting the first segmented image according to the region segmented image to obtain a second segmented image of the second tissue organ image includes:
and performing logical AND operation on the region segmentation image and the first segmentation image to obtain a second segmentation image of the second tissue organ image.
Optionally, in the above image segmentation method, before performing a logical and operation on the region segmentation image and the first segmentation image, the method further includes:
removing a small target area in the area segmentation image by adopting a maximum connected domain method so as to obtain the processed area segmentation image;
the performing a logical AND operation on the region segmentation image and the first segmentation image specifically includes: and performing logical AND operation on the processed region segmentation image and the first segmentation image.
Optionally, in the above image segmentation method, after the second segmented image of the second tissue organ image is obtained, the method further includes:
and carrying out edge smoothing on the second segmented image by adopting morphological closing operation based on a preset second morphological parameter.
In order to achieve the above object, the present invention further provides an image segmentation system, including a processor and a memory, the memory storing instructions thereon, which when executed by the processor, implement the image segmentation method described above.
To achieve the above object, the present invention also provides a readable storage medium having stored therein a computer program which, when executed by a processor, implements the above-described image segmentation method.
Compared with the prior art, the image segmentation method, the system and the storage medium provided by the invention have the following advantages: after an image to be segmented is obtained, firstly, a multiscale hessian matrix is adopted to carry out enhancement treatment on the image to be segmented so as to enhance the second tissue organ, then binarization treatment is carried out to obtain a first segmented image of the second tissue organ, meanwhile, the region where the first tissue organ is located in the image to be segmented is segmented to obtain a region segmented image of the first tissue organ, and finally, the first segmented image is segmented again according to the region segmented image to obtain a second segmented image of the second tissue organ image. The invention enhances the second tissue and organ through the multiscale hessian matrix, improves the efficiency and the precision of the segmentation algorithm, and reduces the complicated operation of man-machine interaction. In addition, the segmentation accuracy of the second tissue organ image can be further improved by automatically segmenting the first tissue organ region and further segmenting the second tissue organ image according to the first tissue organ region. In addition, the image segmentation algorithm has strong universality, realizes an end-to-end algorithm flow, and can better assist doctors in improving diagnosis accuracy.
Drawings
FIG. 1 is a flowchart of an image segmentation method according to an embodiment of the present invention;
FIG. 2 is a specific example of an image to be segmented;
FIG. 3 is a pulmonary vessel enhancement image obtained by enhancement processing of the image to be segmented shown in FIG. 2;
FIG. 4 is a first segmented image of the pulmonary blood vessel obtained by binarizing the enhanced image of the pulmonary blood vessel shown in FIG. 3;
FIG. 5 is a segmented image of the lung region obtained by segmenting the image to be segmented shown in FIG. 2;
FIG. 6 is a second segmented image of the pulmonary vessel from the segmented first segmented image of FIG. 4 based on the segmented region image of FIG. 5;
FIG. 7 is a three-dimensional model image of the final segmented pulmonary vessel shown in FIG. 6;
fig. 8 is a schematic diagram of an image segmentation system according to an embodiment of the present invention.
Detailed Description
The image segmentation method, system and storage medium according to the present invention are described in further detail below with reference to the accompanying drawings and detailed description. The advantages and features of the present invention will become more apparent from the following description. It should be noted that the drawings are in a very simplified form and are all to a non-precise scale, merely for the purpose of facilitating and clearly aiding in the description of embodiments of the invention. For a better understanding of the invention with objects, features and advantages, refer to the drawings. It should be understood that the structures, proportions, sizes, etc. shown in the drawings are for illustration purposes only and should not be construed as limiting the invention to the extent that any modifications, changes in the proportions, or adjustments of the sizes of structures, proportions, or otherwise, used in the practice of the invention, are included in the spirit and scope of the invention which is otherwise, without departing from the spirit or essential characteristics thereof.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The core idea of the invention is to provide an image segmentation method, an image segmentation system and a storage medium, which can not only improve the accuracy of the whole segmentation algorithm, but also effectively reduce the complicated operation of man-machine interaction.
In the embodiment of the present invention, the image segmentation method provided by the present invention is described by taking an organ image, such as a lung image, for example, and the method is not limited to segmentation of an organ image, but may be applied to segmentation of other images. The image segmentation method according to the embodiment of the present invention is applicable to the image segmentation system according to the embodiment of the present invention, and the image segmentation system may be a personal computer, a mobile terminal, or the like, and the mobile terminal may be a hardware device having various operating systems, such as a mobile phone, a tablet computer, or the like.
To achieve the above-described idea, the present invention provides an image segmentation method for segmenting a second tissue organ of a first tissue organ from an image. For example, the image is a lung image, the first tissue organ is a lung, the second tissue organ is a blood vessel, and the image segmentation algorithm provided by the invention is used for segmenting the lung blood vessel from the image. Referring to fig. 1, the method specifically includes the following steps:
step S100: and acquiring an image to be segmented.
In the present invention, the image to be segmented may be an image of a lung, or may be an image of other tissues or organs (for example, respiratory tract, etc.) or other non-organ images, which the present invention is not limited to. The image to be segmented can be acquired by scanning acquisition by various imaging systems, and can also be acquired by transmission by an internal or external storage system such as a storage system image archiving and communication system. The imaging system includes, but is not limited to, a combination of one or more of Magnetic Resonance Imaging (MRI), computed Tomography (CT), positron Emission Tomography (PET), and the like. It should be noted that the size of the image to be segmented may be set according to the specific situation, and the present invention is not limited thereto, for example, the size of the image to be segmented may be 512×512×130 pixels. Referring to fig. 2, a specific example of an image to be segmented according to the present invention is schematically shown, the image to be segmented is a CT volume data image of a lung, a first tissue organ 10 is identified as the lung, and a second tissue organ 20 is identified as a blood vessel.
Step S200: and performing enhancement processing on the image to be segmented by utilizing a multiscale hessian matrix to obtain an enhanced image after the second tissue organ is enhanced.
The hessian matrix is the second derivative of the image, and in the actual calculation process of the hessian matrix, the second derivative of the gaussian filter can be equivalently used for carrying out convolution calculation with the image to obtain the hessian matrix. Since the radius of the second tissue organ (such as blood vessel) in the first tissue organ (such as lung) is different, the area of the second tissue organ with different size scale on the image to be segmented can be enhanced by the multiscale hessian matrix, so that the segmentation and extraction of the second tissue organ are facilitated.
Specifically, the image to be segmented may be enhanced based on a hessian matrix according to a preset scale range and a preset scale iteration number.
The image to be segmented is represented by I (x, y), and the hessian matrix H (x, y; δ) at the scale δ is defined as follows:
wherein I is xx (x, y; delta) represents a secondary transverse image at a scale delta,* Is a convolution operation; i xy (x, y; delta) represents the quadratic cross image at the scale delta,/and->* Is a convolution operation; i yy (x, y; delta) represents a second longitudinal image at scale delta,/and>* Is a convolution operation; />Is high at the scale deltaThe gaussian filter kernel parameters, +.are product operations.
Wherein x and y represent position coordinates of pixel points in the image, the scale delta is closely related to the size of a second tissue organ (such as a blood vessel), when the radius of the second tissue organ (such as the blood vessel) is matched with the scale, the hessian matrix result has a large data value, so that the second tissue organ with the radius is enhanced, and when a plurality of scales are set according to the radius of the second tissue organ, the second tissue organ with each radius can be enhanced, so that an enhanced image of the enhanced second tissue organ is obtained. Taking the second tissue organ as a pulmonary vessel as an example, since the sizes of the pulmonary vessels are different, the scale delta, that is, the kernel parameter of the gaussian filter, is set to a range value, for example, 0.5-5, and the iteration number can be selected from 5-15, for example, when the iteration number is 10, 10 kernel parameters are obtained at equal intervals in the kernel parameter range of 0.5-5 to calculate the multiscale hessian matrix result.
The input of the hessian matrix is the image to be segmented, the scale delta range and the iteration times, and the output result is the enhanced image of the second tissue organ with different size radiuses. The above enhancement processing is performed on the image to be segmented shown in fig. 2, so that an enhanced image of the pulmonary blood vessel shown in fig. 3 can be obtained, and it can be seen from the figure that blood vessels with different sizes and radii are highlighted.
Preferably, before executing step S200, the image to be segmented may be preprocessed, so as to filter noise in the image to be segmented. Therefore, noise information in the image to be segmented can be effectively filtered through preprocessing the image to be segmented, and accordingly image quality of the image to be segmented can be effectively improved. Correspondingly, in step S200, the preprocessed image to be segmented is enhanced by using the multiscale hessian matrix, so that the enhancement effect of the second tissue organ can be improved. Specifically, due to the equipment molding parameters and the like, the generated noise has relatively high randomness, and the noise is generally approximately normally distributed, so that a Gaussian filter can be adopted to filter noise information in the image to be segmented. In addition, other commonly used filters can be used for preprocessing the image to be segmented, which is not limited by the present invention.
Step S300: and carrying out binarization processing on the enhanced image to obtain a first segmentation image of the second tissue organ.
In the step, binarization processing is carried out on the enhanced image enhanced by the hessian matrix to obtain a binary image of the second tissue organ, thereby realizing preliminary segmentation of the enhanced image. As shown in fig. 4, the first segmented image of the pulmonary blood vessel is obtained by binarizing the enhanced image shown in fig. 3. Specifically, the enhanced image may be binarized using a fixed threshold (e.g., a pixel value of 40-60, preferably 50), although other binarization methods may be used, which is not limited in the present invention.
Step S400: and carrying out segmentation processing on the region where the first tissue organ is located in the image to be segmented to obtain a region segmentation image of the first tissue organ.
Since the first segmented image obtained after the processing in steps S200 and S300 includes not only the second tissue organ (pulmonary vessel) but also the non-second tissue organ (non-pulmonary vessel) in the first tissue organ (for example, the lung), in order to obtain an accurate segmented image of the second tissue organ, the region of the first tissue organ may be segmented, and then the second tissue organ region in the first segmented image may be segmented according to the first tissue organ region, so as to exclude the non-second tissue organ region in the first segmented image. It should be noted that, in other embodiments, the step S400 may be performed before the step S200, and the execution sequence of the steps S400 and S200 is not limited in the present invention.
Specifically, one embodiment of obtaining the region-segmented image of the first tissue organ is as follows: firstly, binarizing the image to be segmented to obtain a region preliminary segmentation image of the first tissue organ; and setting a seed point in a boundary area of the area preliminary segmentation image, and distinguishing the first tissue organ by a morphological method by taking the seed point as an initial point to obtain the area segmentation image of the first tissue organ.
Firstly, a fixed threshold value can be adopted to carry out binarization processing on the image to be segmented. In particular, the threshold value is selected from pixel values of the first tissue organ in the CT image, i.e. the threshold value may be selected depending on the target segmented tissue. CT images use a DICOM (digital imaging and communications in medicine) format of data format, which is widely used in the medical field. The standard DICOM-format image consists of a header file and a data set, wherein the header file contains Tag information of data, including patient information, equipment parameters, imaging parameters, hospital information, doctor information and the like, and the data set is different from a common image format and is 12-bit or 16-bit data, the CT value of the data set is between-1024 and 3071, the corresponding gray value from black to white is between 0 and 4095, and richer information can be expressed. Typically CT images are calibrated to represent different regions/tissues, e.g. water at pixel values of 0 and lung tissue at pixel values-600 to-400. The optional pixel value is-500 as a threshold when the target segmented tissue is the lung and-900 as a threshold when the target segmented tissue is the airway tube. In addition, other methods may be used to perform binarization processing on the image to be segmented, which is not limited in the present invention.
Then, a seed point is set at a boundary region of the region preliminary divided image. In the region preliminary segmentation image, the region of the first tissue organ (lung) is usually located at the central part, and at this time, seed points are set in the boundary region of the region preliminary segmentation image, so that the seed points can be ensured to be located outside the lung region, and the first tissue organ (lung) can be further distinguished by a morphological method, thereby obtaining the region segmentation image of the first tissue organ. It will be appreciated that the seed points may be selected as locations of particular pixels in the preliminary segmentation image of the region, such seed points representing regions other than the first tissue organ (lung) as input parameters for subsequent resolution of the first tissue organ (lung). The seed points in the step do not need to be selected manually, but are preset from the image boundary area to be seed points, so that the method can save a large amount of time and cost and reduce the workload of doctors.
Wherein the step of distinguishing the first tissue organ by a morphological method specifically comprises the following steps: and distinguishing the first tissue organ by using the seed point as an initial point through a morphological water-diffusion gold mountain method (FloodFill). Starting from seed points of the boundary of the preliminary segmentation image of the region, obtaining an image with the region of the first tissue organ displayed in black and the other regions displayed in white through a morphological water diffuse golden mountain method, and performing inversion operation (for example, performing black-white image inversion operation to display the region of the first tissue organ in white and the other regions displayed in black) on the obtained image so as to segment the region of the first tissue organ. The water diffuse gold mountain method can be understood as that whether the seed point is the same as the adjacent pixels or not is judged, if so, the seed point is considered as the same area, otherwise, the seed point is different from the adjacent area or not, and then whether the area where the seed point is located and the adjacent area have the same attribute (for example, the same pixel value) is continuously judged, and if not, the area where the seed point is located is set to be the adjacent area attribute so as to distinguish the first tissue organ area from other areas. In addition, other morphological methods may be used to distinguish the first tissue organ, and the invention is not limited in this regard.
Preferably, after the first tissue organ is distinguished, hole filling and/or boundary repairing treatment may be further performed on the region of the first tissue organ. For example, the first tissue organ is a lung, and typically there is a hole in the lung tissue region, and there may be a defect at the edge, and for better extraction of the lung region, hole filling and/or border repair of the lung region is required. Specifically, based on a preset first morphological parameter, a morphological closing operation is adopted to perform hole filling and/or boundary repairing treatment on the region of the first tissue organ, so that the holes in the first tissue organ are filled and the boundary is also kept intact. Referring to fig. 5, fig. 5 is a segmented image of a lung region obtained by performing the above processing on the image to be segmented shown in fig. 2, and as shown in fig. 5, after a morphological closing operation is performed, the lung region has no holes and smooth boundaries without burrs. The first morphological parameter may be set to 5, and the morphological closing operation may be performed by a morphological closing operation method of expanding and then corroding, that is, expanding the segmented image of the region by 5 pixels, and corroding the expanded image by 5 pixels.
And step S500, segmenting the first segmented image according to the region segmentation image to obtain a second segmented image of the second tissue organ image.
As described above, the first segmented image may have a non-second tissue organ region, so that the first segmented image needs to be segmented again according to the region segmented image of the first tissue organ, so as to remove the non-second tissue organ region in the first segmented image, thereby obtaining an accurate second segmented image of the second tissue organ.
Specifically, the region segmentation image and the first segmentation image may be logically and-ed to obtain a second segmentation image of the second tissue organ image. The logical AND operation of the images is to perform logical AND operation on corresponding pixels of two binary images so as to obtain the intersection areas of the two images with the same size. By logically AND the region segmentation image and the first segmentation image, a non-second tissue organ region beyond the first tissue organ region in the first segmentation image can be eliminated, and a second tissue organ region in the first tissue organ region is reserved, so that a second segmentation image of the second tissue organ image is obtained.
Preferably, before performing the logical and operation on the region-divided image and the first-divided image, the method further includes: and removing a small target area in the area segmentation image by adopting a maximum connected domain method so as to obtain the processed area segmentation image. Correspondingly, performing logical AND operation on the processed region segmentation image and the first segmentation image to obtain a second segmentation image of the second tissue organ image. The small target region in the region segmentation image is a non-first tissue organ region (non-lung region), so that the non-first tissue organ region (non-lung region) can be further removed through the processing, and the segmentation accuracy of the second tissue organ is improved.
Specifically, maximum connected domain analysis is performed on the basis of the region segmentation image, the number of pixels of each connected domain is counted, one connected domain represents a set with the same pixels, and the largest number of pixels is the largest connected domain. In the invention, when the small target area on the area segmentation image is removed by adopting a maximum connected domain method, the volume of each connected domain can be obtained by counting the number of pixel points of each connected domain, and the connected domains with larger volume difference with the maximum connected domain are removed as the small target area. For example, those connected domains having a volume smaller than 1% of the volume of the largest connected domain may be removed as small target regions.
Preferably, in order to make the boundary of the second tissue organ smoother, after the second segmented image of the second tissue organ image is obtained, a morphological closing operation may be further adopted to perform edge smoothing on the second segmented image based on a preset second morphological parameter. The second morphological parameter may be set to 1, and the morphological closing operation may be performed by using a morphological closing operation method of expanding and then corroding, that is, expanding the segmented image of the region by 1 pixel, and corroding the expanded image by 1 pixel.
Referring to fig. 6, a second segmentation image of a pulmonary blood vessel obtained by segmenting the first segmentation image shown in fig. 4 according to the region segmentation image shown in fig. 5 is schematically shown, and as shown in fig. 6, the present invention can segment a second tissue organ (for example, a pulmonary blood vessel) from the image of the first tissue organ, so that a doctor can observe the image conveniently. Three intersecting straight lines in fig. 7 represent X, Y, Z axes in the spatial coordinate system.
The above examples are given by taking a lung vessel image from a CT image, but are not limited to this application in practice. The invention can also be applied to image segmentation in any other tissue organ, for example, segmentation of heart vessels from the heart or segmentation of airway vessels.
In summary, the present invention employs a combination of thresholding, morphological operations and multi-scale hessian matrix enhanced image processing techniques to segment and extract a second tissue organ from a first tissue organ image. The invention enhances the second tissue and organ through the multiscale hessian matrix, improves the efficiency and the precision of the segmentation algorithm, and reduces the complicated operation of man-machine interaction. In addition, the first tissue organ region is automatically segmented through the threshold value, and the second tissue organ image is further segmented according to the first tissue organ region, so that the segmentation accuracy of the second tissue organ image can be further improved. In addition, morphological operation is adopted to process the image segmentation result, so that the segmentation precision is further improved. In addition, the image segmentation algorithm has strong universality, realizes an end-to-end algorithm flow, and can better assist doctors in improving diagnosis accuracy.
Based on the above inventive concept, the present invention also provides an image segmentation system, as shown in fig. 8, the image segmentation system 200 may include a processor 210 and a memory 220, the memory 220 having instructions stored thereon, which when executed by the processor 210, may implement the steps in the image segmentation method as described above.
Wherein the processor 210 may perform various actions and processes in accordance with instructions stored in the memory 220. In particular, the processor 210 may be an integrated circuit chip having signal processing capabilities. The processor may be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. Various methods, steps, and logic blocks disclosed in embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and may be an X86 architecture or an ARM architecture or the like.
The memory 220 stores executable instructions that, when executed by the processor 210, perform the image segmentation method described above. The memory 220 may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be Random Access Memory (RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (ddr SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous Link Dynamic Random Access Memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
Based on the same inventive concept, the present invention also provides a computer readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, can implement the steps in the image segmentation method described above.
Similarly, the computer readable storage medium in embodiments of the present invention may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. It should be noted that the computer-readable storage media described herein are intended to comprise, without being limited to, these and any other suitable types of memory.
It is noted that the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In general, the various example embodiments of the invention may be implemented in hardware or special purpose circuits, software, firmware, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While aspects of the embodiments of the invention are illustrated or described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.
It should be noted that, in the present specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment is mainly described in a different point from other embodiments. In particular, for a system, a computer readable storage medium, since it is substantially similar to the method embodiments, the description is relatively simple, and references to parts of the description of the method embodiments are only required.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only illustrative of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention, and any alterations and modifications made by those skilled in the art based on the above disclosure shall fall within the scope of the appended claims.
Claims (10)
1. An image segmentation method for segmenting a second tissue organ from a first tissue organ from an image, comprising:
acquiring an image to be segmented;
performing enhancement processing on the image to be segmented by utilizing a multiscale hessian matrix to obtain an enhanced image of the second tissue organ;
performing binarization processing on the enhanced image to obtain a first segmentation image of the second tissue organ;
performing segmentation processing on the region where the first tissue organ is located in the image to be segmented to obtain a region segmentation image of the first tissue organ;
dividing the first divided image according to the region division image to obtain a second divided image of the second tissue organ image;
the enhancement processing of the image to be segmented by using the multiscale hessian matrix comprises the following steps:
based on the hessian matrix, carrying out enhancement processing on the image to be segmented according to a preset scale range and a preset scale iteration number;
the segmenting the first segmented image according to the region segmented image to obtain a second segmented image of the second tissue organ image, including:
and performing logical AND operation on the region segmentation image and the first segmentation image to obtain a second segmentation image of the second tissue organ image.
2. The image segmentation method according to claim 1, characterized in that before the enhancement processing of the image to be segmented using a multiscale hessian matrix, further comprising:
preprocessing the image to be segmented to filter noise in the blood vessel image to be segmented;
the enhancement processing is carried out on the image to be segmented by utilizing a multiscale hessian matrix, specifically:
and carrying out enhancement processing on the preprocessed image to be segmented by utilizing the multiscale hessian matrix.
3. The image segmentation method as set forth in claim 1, wherein the scale range is 0.5-5 and the iteration number is 5-15.
4. The image segmentation method according to claim 1, wherein the segmenting the region of the image to be segmented in which the first tissue organ is located includes:
performing binarization processing on the image to be segmented to obtain a region preliminary segmentation image of the first tissue organ;
and setting a seed point in a boundary area of the area preliminary segmentation image, and distinguishing the first tissue organ by a morphological method by taking the seed point as an initial point to obtain the area segmentation image of the first tissue organ.
5. The image segmentation method as set forth in claim 4, wherein the morphologically distinguishing the first tissue organ comprises:
and taking the seed point as an initial point, and distinguishing the first tissue organ by a morphological water-diffusion gold mountain method.
6. The image segmentation method as set forth in claim 5, further comprising, after differentiating the first tissue organ:
and performing hole filling and/or boundary repairing treatment on the region of the first tissue organ by adopting morphological closing operation based on a preset first morphological parameter.
7. The image segmentation method as set forth in claim 1, further comprising, prior to logically anding the region segmented image with the first segmented image:
removing a small target area in the area segmentation image by adopting a maximum connected domain method so as to obtain the processed area segmentation image;
the performing a logical AND operation on the region segmentation image and the first segmentation image specifically includes: and performing logical AND operation on the processed region segmentation image and the first segmentation image.
8. The image segmentation method as set forth in claim 1, further comprising, after obtaining the second segmented image of the second tissue organ image:
and carrying out edge smoothing on the second segmented image by adopting morphological closing operation based on a preset second morphological parameter.
9. An image segmentation system comprising a processor and a memory having instructions stored thereon that, when executed by the processor, implement the method of any of claims 1-8.
10. A readable storage medium, characterized in that the readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010457666.5A CN113724264B (en) | 2020-05-26 | 2020-05-26 | Image segmentation method, system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010457666.5A CN113724264B (en) | 2020-05-26 | 2020-05-26 | Image segmentation method, system and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113724264A CN113724264A (en) | 2021-11-30 |
| CN113724264B true CN113724264B (en) | 2023-08-11 |
Family
ID=78672117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010457666.5A Active CN113724264B (en) | 2020-05-26 | 2020-05-26 | Image segmentation method, system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724264B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296660A (en) * | 2016-07-28 | 2017-01-04 | 北京师范大学 | A kind of full-automatic coronary artery dividing method |
| CN110648338A (en) * | 2019-09-25 | 2020-01-03 | 上海微创医疗器械（集团）有限公司 | Image segmentation method, readable storage medium, and image processing apparatus |
| CN111028241A (en) * | 2019-11-13 | 2020-04-17 | 东北大学 | Multi-scale blood vessel enhanced level set segmentation system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3409187B1 (en) * | 2017-05-30 | 2023-08-16 | Siemens Healthcare GmbH | Method and device for determining a flow situation in an organ |
-
2020
- 2020-05-26 CN CN202010457666.5A patent/CN113724264B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296660A (en) * | 2016-07-28 | 2017-01-04 | 北京师范大学 | A kind of full-automatic coronary artery dividing method |
| CN110648338A (en) * | 2019-09-25 | 2020-01-03 | 上海微创医疗器械（集团）有限公司 | Image segmentation method, readable storage medium, and image processing apparatus |
| CN111028241A (en) * | 2019-11-13 | 2020-04-17 | 东北大学 | Multi-scale blood vessel enhanced level set segmentation system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113724264A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11062449B2 (en) | Method and system for extracting vasculature | |
| CN110706246B (en) | Blood vessel image segmentation method and device, electronic equipment and storage medium | |
| US8761475B2 (en) | System and method for automatic recognition and labeling of anatomical structures and vessels in medical imaging scans | |
| CN111008984B (en) | Automatic contour line drawing method for normal organ in medical image | |
| JP6329697B2 (en) | Method for automatic segmentation and quantification of body tissue | |
| CN110648338B (en) | Image segmentation method, readable storage medium, and image processing apparatus | |
| US9098912B2 (en) | Method, system and computer readable medium for automatic segmentation of a medical image | |
| Deshpande et al. | Automatic segmentation, feature extraction and comparison of healthy and stroke cerebral vasculature | |
| US7593762B2 (en) | System and method for automatically segmenting bones in computed tomography angiography data | |
| CN116503607B (en) | CT image segmentation method and system based on deep learning | |
| CN115100067A (en) | Image reconstruction method and device | |
| Ng et al. | Medical image segmentation using watershed segmentation with texture-based region merging | |
| CN115439533A (en) | Method, computer device, readable storage medium and program product for obtaining the location of an intracranial aneurysm at a vessel segment | |
| Cercos-Pita et al. | NASAL-Geom, a free upper respiratory tract 3D model reconstruction software | |
| CN112116623B (en) | Image segmentation method and device | |
| CN112562058A (en) | Rapid establishing method of intracranial vascular simulation three-dimensional model based on transfer learning | |
| CN113724264B (en) | Image segmentation method, system and readable storage medium | |
| Mueller et al. | Robust semi-automated path extraction for visualising stenosis of the coronary arteries | |
| Myint et al. | Effective kidney segmentation using gradient based approach in abdominal CT images | |
| CN112862785B (en) | CTA image data identification method, device and storage medium | |
| CN117078711A (en) | Medical image segmentation method, system, electronic device and storage medium | |
| CN112862786B (en) | CTA image data processing method, device and storage medium | |
| CN112509080A (en) | Method for establishing intracranial vascular simulation three-dimensional model based on transfer learning | |
| CN112862787B (en) | CTA image data processing method, device and storage medium | |
| TWI790179B (en) | Cardiac catheterization image recognition and evaluation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |