CN111462270A - Reconstruction system and method based on novel coronavirus pneumonia CT detection - Google Patents
Reconstruction system and method based on novel coronavirus pneumonia CT detection Download PDFInfo
- Publication number
- CN111462270A CN111462270A CN202010264425.9A CN202010264425A CN111462270A CN 111462270 A CN111462270 A CN 111462270A CN 202010264425 A CN202010264425 A CN 202010264425A CN 111462270 A CN111462270 A CN 111462270A
- Authority
- CN
- China
- Prior art keywords
- image
- lung
- mask
- trachea
- blood vessel
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
Abstract
The embodiment of the invention provides a reconstruction system and a method based on novel coronavirus pneumonia CT detection, wherein the method comprises the following steps: inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and an air vessel image; carrying out binarization processing on the lung image to obtain a lung mask, a left lung mask and a right lung mask, carrying out binarization processing on the blood vessel image to obtain a blood vessel mask, and carrying out binarization processing on the trachea image to obtain a trachea mask; acquiring a region of interest in the preprocessed CT image data; according to the trachea mask and the blood vessel mask, pixel values corresponding to the trachea mask and the blood vessel mask are set as global minimum values in the image in the region of interest, and therefore the trachea and the blood vessels are removed in the region of interest. The method can effectively display the position, the form and the distribution range of the lung lesion and the contrast relation of surrounding tissues, thereby providing the potential of multi-view analysis for CT detection.
Description
Technical Field
The invention relates to the field of machine vision, in particular to a reconstruction system and a reconstruction method based on novel coronavirus pneumonia CT detection.
Background
At present, the diagnosis of the novel coronavirus pneumonia is mainly based on nucleic acid detection and medical image detection. The combination of the two is more beneficial to diagnosis because the official case publication shows that some patients show positive after more than 2 times of nucleic acid detection, even show positive after 5 th time of nucleic acid detection, so that the patients with acute inflammation symptoms of lung CT are treated early according to the principle of 'suspected disease is existed' by performing lung CT image examination while performing nucleic acid detection.
After the CT image is post-processed, the imaging information which reflects the anatomical structure and pathological change condition of internal organs of a human body and is more complete, more visual and easier to read can be provided for imaging professionals and clinicians in multiple directions and multiple angles. In the CT detection of the novel coronavirus pneumonia, the CT image post-processing reconstruction technology can provide more accurate and reliable imaging information of lesions.
Multi-planar reconstruction (MPR for short) is a post-processing method for obtaining two-dimensional images of coronal, sagittal, transverse and oblique planes of any layer of a corresponding organ of a human body from an original transverse axial image. MPR can show the morphological change of each systemic organ of the whole body, and has obvious advantages in judging the nature, invasion and range and adjacency relation of lesions in the detection of novel coronavirus pneumonia.
Maximum intensity projection (MIP for short) is a projection technique for imaging all pixel values in volumetric data that have the highest intensity in the line of sight direction. Because the imaging data is derived from three-dimensional volumetric data, the direction of projection can be varied at will; because the imaging data is taken from the pixel value with the maximum density or the mean value of the pixel values in the three-dimensional volume data, the imaging data mainly reflects the density difference of tissues more truly and clearly shows the position, the form and the distribution range of the pathological changes in the detection of the novel coronavirus pneumonia.
Minimum intensity projection (MinIP for short) is a projection technique of imaging by using a pixel value of volume data with minimum intensity in the sight line direction; in the CT detection of the novel coronavirus pneumonia, MinIP is mainly used for displaying the pathological changes of central organs such as a large airway, a bronchial tree and the like.
Therefore, there is a need to develop a MIP/MinIP/MPR post-processing reconstruction technique for CT detection of novel coronavirus pneumonia, which can provide imaging information such as location, morphology, distribution range, invasion and range of pathological changes for medical workers more clearly and definitely, and provide certain help for detecting or treating patients with novel coronavirus pneumonia.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a reconstruction system and method based on a novel coronavirus pneumonia CT detection, which overcome the above problems or at least partially solve the above problems.
According to a first aspect of embodiments of the present invention, there is provided a reconstruction method based on CT detection of novel coronavirus pneumonia, the method including: inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image, wherein the segmentation network is obtained by training by taking the preprocessed CT image data as a sample and taking the lung image, the blood vessel image and the trachea image as labels; carrying out binarization processing on the lung image to obtain a left lung mask and a right lung mask, carrying out binarization processing on the blood vessel image to obtain a blood vessel mask, and carrying out binarization processing on the trachea image to obtain a trachea mask;
acquiring an interested region in the preprocessed CT image data, wherein the interested region is a human body region;
according to the trachea mask and the blood vessel mask, pixel values corresponding to the trachea mask and the blood vessel mask are set as global minimum values in the region of interest, so that the trachea and the blood vessels are removed in the region of interest, and the position, the form, the distribution range and the contrast relation with surrounding tissues of lung lesions are clearly displayed.
According to a second aspect of the embodiments of the present invention, there is provided a reconstruction system for CT detection of a novel coronavirus pneumonia, the system including: the segmentation module is used for inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image, wherein the segmentation network is obtained by training by taking the preprocessed CT image data as a sample and taking the lung image, the blood vessel image and the trachea image as labels; the binarization module is used for performing binarization processing on the lung image to obtain a left lung mask and a right lung mask, performing binarization processing on the blood vessel image to obtain a blood vessel mask, and performing binarization processing on the trachea image to obtain a trachea mask; the interest module is used for acquiring an interest region in the CT image data, wherein the interest region is a human body region; and the first reconstruction module is used for setting the pixel values corresponding to the trachea mask and the blood vessel mask as the global minimum value in the region of interest according to the trachea mask and the blood vessel mask, so that the trachea and the blood vessels are removed in the region of interest, and the position, the form, the distribution range and the contrast relation with surrounding tissues of the lung lesion are clearly displayed.
According to a third aspect of the embodiments of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement a reconstruction method based on CT detection of coronavirus pneumonia, as provided in any one of various possible implementations of the first aspect.
According to a fourth aspect of embodiments of the present invention, there is provided a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a reconstruction method based on CT detection of coronavirus pneumonia as provided in any one of the various possible implementations of the first aspect.
The reconstruction system and the reconstruction method based on the novel coronavirus pneumonia CT detection provided by the embodiment of the invention can effectively display the position, the form and the distribution range of lung lesions and the contrast relation of surrounding tissues, thereby providing the potential of multi-view analysis for the CT detection and providing certain help in resisting the novel coronavirus pneumonia.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from these without inventive effort.
Fig. 1 is a flowchart of a reconstruction method based on CT detection of coronavirus pneumonia according to an embodiment of the present invention;
FIG. 2 is an illustration of a lung MIP reconstruction in an embodiment of the present invention;
FIG. 3 is a block diagram of a split network according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a reconstruction system based on CT detection of coronavirus pneumonia according to another embodiment of the present invention;
fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but 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.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; may be mechanically coupled, may be electrically coupled or may be in communication with each other; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Fig. 1 is a flowchart of a reconstruction method based on CT detection of coronavirus pneumonia according to an embodiment of the present invention, and as shown in fig. 1, the method includes:
s1, inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image, wherein the segmentation network is obtained by training with the preprocessed CT image data as a sample and the lung image, the blood vessel image and the trachea image as labels;
s2, performing binarization processing on the lung image to obtain a left lung mask and a right lung mask, performing binarization processing on the blood vessel image to obtain a blood vessel mask, and performing binarization processing on the trachea image to obtain a trachea mask;
s3, acquiring an interested region in the preprocessed CT image data, wherein the interested region is a human body region;
s4, setting the pixel values corresponding to the trachea mask and the blood vessel mask as the global minimum value in the region of interest according to the trachea mask and the blood vessel mask, thereby removing the trachea and the blood vessels in the region of interest and clearly displaying the position, the shape, the distribution range and the contrast relation with the surrounding tissues of the lung lesion.
The method comprises the steps of firstly obtaining CT image data of a novel coronavirus pneumonia patient, preprocessing the CT image data, specifically, carrying out down-sampling and standardization processing on the CT image data to obtain preprocessed CT image data, and inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image. The segmentation network is a deep learning neural network and is obtained after training, and during training, preprocessed CT image data are used as samples, and lung images, blood vessel images and trachea images are used as labels.
And carrying out binarization processing on the lung image to obtain a lung mask, a left lung mask and a right lung mask of the whole lung, carrying out binarization processing on the blood vessel image to obtain a blood vessel mask, and carrying out binarization processing on the trachea image to obtain a trachea mask.
According to the threshold value, a region of interest in the preprocessed CT image data is then acquired, wherein the region of interest is data except human tissues.
And then setting the pixel values of pixel points corresponding to the trachea mask and the blood vessel mask to be minimum in the region of interest according to the trachea mask and the blood vessel mask, so as to remove the trachea and the blood vessels in the region of interest. And meanwhile, the window width and the window level of the image are properly adjusted to clearly display the position, the form, the distribution range and the contrast relation with the surrounding tissues of the lung lesion.
On the basis of the above embodiment, it is preferable to further include:
and superposing all axial images in the CT image data with the tracheal vessels removed according to the lung mask, the left lung mask and the right lung mask, and performing coronary, sagittal and any-angle oblique position image recombination on lung tissues corresponding to a reconstruction line marked by a preset marking line to obtain a lung MPR image, a left lung MPR image and an MPR image of the right lung.
Specifically, according to the obtained tracheal mask and vascular mask, a left lung MPR image, and a right lung MPR image are calculated, and the calculation method specifically includes: and superposing all axial position images in the CT image data without the tracheal vessels, and then carrying out coronary, sagittal and any-angle oblique position image recombination on the lung tissues designated by the recombination line marked by the selected marked line to obtain a lung MPR image, a left lung MPR image and a right lung MPR image.
On the basis of the above embodiment, it is preferable to further include:
and mapping the CT image data with the tracheal vessels removed at coronal and sagittal positions by gray scale CT values according to the lung mask, the left lung mask and the right lung mask, and acquiring a lung MIP image, a left lung MIP image and a right lung MIP image when reconstructing MIP of the novel coronavirus pneumonia in the process of projecting the mean value of the value positions.
Fig. 2 is a lung MIP reconstructed image according to an embodiment of the present invention, and as shown in fig. 2, the left image in the figure is the lung MIP reconstructed image, the upper right image is the left lung MIP image, and the lower right image is the right lung MIP image, and as can be seen from the figure, a white portion in the figure is a lesion position.
On the basis of the above embodiment, it is preferable to further include:
and mapping the CT image data with the tracheal vessels removed at coronal and sagittal positions according to the lung mask, the left lung mask and the right lung mask, wherein the mapped value is the minimum value of the current layer, and acquiring a lung MinIP image, a left lung MinIP image and a right lung MinIP image.
According to the obtained lung mask, calculating a lung MinIP image, a left lung MinIP image and a right lung MinIP image, wherein the specific calculation method comprises the following steps: and mapping the data CT data without the tracheal vessels on the coronal and sagittal positions by using a gray level CT value, wherein the mapped value is the minimum value of the current layer.
On the basis of the foregoing embodiment, preferably, the inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image, and a trachea image includes:
inputting the preprocessed CT image data into an encoder in the segmentation network to obtain a characteristic diagram;
and inputting the feature map into a decoder of the segmentation network to obtain the lung image, the blood vessel image and the trachea image, wherein the high-resolution features of the shallow layer in the encoder are directly connected with the low-resolution features of the higher layer in the decoder.
Fig. 3 is a schematic structural diagram of a segmentation network in an embodiment of the present invention, as shown in fig. 3, the segmentation network is composed of an Encoder (Encoder) and a Decoder (Decoder), the Encoder performs high-level abstract feature extraction on an input image through a convolution network and downsampling, encodes the original image into a feature map with the size of only the original image 1/32, the Decoder decodes the feature map output by the Encoder through the convolution network and upsampling, and outputs three images with the same size as the original image, namely, a lung image, a trachea image and a blood vessel image, and a pixel value of each of the three images indicates a probability that the pixel belongs to different segmentation objects.
The encoder and the decoder are connected through Skip connection (Skip connection), the Skip connection directly connects the high-resolution features of a shallow layer in the encoder with the low-resolution features of a higher layer in the decoder, and the problem that detail (high-resolution) information in the high-layer features is lost is solved.
Fig. 4 is a schematic structural diagram of a reconstruction system based on CT detection of a novel coronavirus pneumonia according to another embodiment of the present invention, as shown in fig. 4, the system includes a segmentation module 401, a binary module 402, an interest module 403, and a first reconstruction module 404, where:
the segmentation module 401 is configured to input the preprocessed CT image data into a segmentation network, and acquire a lung image, a blood vessel image, and a trachea image, where the segmentation network is obtained by training using the preprocessed CT image data as a sample and using the lung image, the blood vessel image, and the trachea image as labels;
the binarization module 402 is configured to perform binarization processing on the lung image to obtain a left lung mask and a right lung mask, perform binarization processing on the blood vessel image to obtain a blood vessel mask, and perform binarization processing on the trachea image to obtain a trachea mask;
the interest module 403 is configured to acquire a region of interest in the CT image data, where the region of interest is a human body region;
the first reconstruction module 404 is configured to set, in the region of interest, pixel values corresponding to the tracheal mask and the blood vessel mask as global minimum values in the region of interest according to the tracheal mask and the blood vessel mask, so as to remove trachea and blood vessels in the region of interest, and clearly display a position, a shape, a distribution range, and a contrast relationship with surrounding tissues of a lung lesion.
On the basis of the above embodiment, it is preferable to further include:
and the second reconstruction module is used for superposing all axial images in the CT image data after the tracheal vessels are removed according to the lung mask, the left lung mask and the right lung mask, performing image recombination of coronaries, sagittal positions and oblique positions at any angles on lung tissues corresponding to a reconstruction line marked by a preset marked line, and acquiring a lung MPR image, a left lung MPR image and an MPR image of the right lung.
On the basis of the above embodiment, it is preferable to further include:
and the third reconstruction module is used for mapping the gray-scale CT values of the CT image data with the tracheal vessels removed at the coronal and sagittal positions according to the lung mask, the left lung mask and the right lung mask, and acquiring a lung MIP image, a left lung MIP image and a right lung MIP image when MIP reconstruction of the novel coronavirus pneumonia is carried out at the projection value bit average value.
On the basis of the above embodiment, it is preferable to further include:
and the fourth reconstruction module is used for mapping the CT image data with the tracheal vessels removed at the coronal and sagittal positions by using a gray scale CT value according to the lung mask, the left lung mask and the right lung mask, wherein the mapped value is the minimum value of the current layer, and a lung MinIP image, a left lung MinIP image and a right lung MinIP image are obtained.
On the basis of the above embodiment, it is preferable to further include: a preprocessing module, wherein the preprocessing module specifically includes a feature map unit and a decoding unit, wherein:
the characteristic diagram unit is used for inputting the preprocessed CT image data into an encoder in the segmentation network to obtain a characteristic diagram;
the decoding unit is configured to input the feature map into a decoder of the segmentation network, and obtain the lung image, the blood vessel image, and the trachea image, where a high-resolution feature of a shallower layer in the encoder is directly connected to a low-resolution feature of a higher layer in the decoder.
The specific implementation process of the embodiment of the system is the same as the specific implementation process of the embodiment of the method, and please refer to the embodiment of the method for details, which is not described herein again.
An embodiment of the present invention provides an electronic device, as shown in fig. 5, the electronic device includes: a processor (processor)501, a communication Interface (Communications Interface)502, a memory (memory)503, and a communication bus 504, wherein the processor 501, the communication Interface 502, and the memory 503 are configured to communicate with each other via the communication bus 504. The processor 501 may invoke a computer program on the memory 503 and operable on the processor 501 to perform the above-mentioned intelligent lesion detection method for DR detection of novel coronavirus pneumonia provided by the embodiments, for example, including: inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image, wherein the segmentation network is obtained by training by taking the preprocessed CT image data as a sample and taking the lung image, the blood vessel image and the trachea image as labels; carrying out binarization processing on the lung image to obtain a lung mask, a left lung mask and a right lung mask, carrying out binarization processing on the blood vessel image to obtain a blood vessel mask, and carrying out binarization processing on the trachea image to obtain a trachea mask; acquiring an interested region in the preprocessed CT image data, wherein the interested region is a human body region; according to the trachea mask and the blood vessel mask, pixel values corresponding to the trachea mask and the blood vessel mask are set as global minimum values in the region of interest, so that the trachea and the blood vessels are removed in the region of interest, and the position, the form, the distribution range and the contrast relation with surrounding tissues of lung lesions are clearly displayed.
In addition, the logic instructions in the memory 503 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, is implemented to perform the intelligent abnormal lesion detection method for DR detection of coronavirus pneumonia provided in the foregoing embodiments, for example, the method includes: inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image, wherein the segmentation network is obtained by training by taking the preprocessed CT image data as a sample and taking the lung image, the blood vessel image and the trachea image as labels; carrying out binarization processing on the lung image to obtain a lung mask, a left lung mask and a right lung mask, carrying out binarization processing on the blood vessel image to obtain a blood vessel mask, and carrying out binarization processing on the trachea image to obtain a trachea mask; acquiring an interested region in the preprocessed CT image data, wherein the interested region is a human body region; according to the trachea mask and the blood vessel mask, pixel values corresponding to the trachea mask and the blood vessel mask are set as global minimum values in the region of interest, so that the trachea and the blood vessels are removed in the region of interest, and the position, the form, the distribution range and the contrast relation with surrounding tissues of lung lesions are clearly displayed.
The above-described embodiments of the electronic device and the like are merely illustrative, and units illustrated as separate components may or may not be physically separate, and components displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute the various embodiments or some parts of the methods of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A reconstruction system based on CT detection of novel coronavirus pneumonia is characterized by comprising:
the segmentation module is used for inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image, wherein the segmentation network is obtained by training by taking the preprocessed CT image data as a sample and taking the lung image, the blood vessel image and the trachea image as labels;
the binarization module is used for performing binarization processing on the lung image to obtain a left lung mask and a right lung mask, performing binarization processing on the blood vessel image to obtain a blood vessel mask, and performing binarization processing on the trachea image to obtain a trachea mask;
the interest module is used for acquiring an interest region in the CT image data, wherein the interest region is a human body region;
and the first reconstruction module is used for setting the pixel values corresponding to the trachea mask and the blood vessel mask as the global minimum value in the region of interest according to the trachea mask and the blood vessel mask, so that the trachea and the blood vessels are removed in the region of interest, and the position, the form, the distribution range and the contrast relation with surrounding tissues of the lung lesion are clearly displayed.
2. The system of claim 1, further comprising:
and the second reconstruction module is used for superposing all axial images in the CT image data after the tracheal vessels are removed according to the lung mask, the left lung mask and the right lung mask, performing image recombination of coronaries, sagittal positions and oblique positions at any angles on lung tissues corresponding to a reconstruction line marked by a preset marked line, and acquiring a lung MPR image, a left lung MPR image and an MPR image of the right lung.
3. The system of claim 1, further comprising:
and the third reconstruction module is used for mapping the gray-scale CT values of the CT image data with the tracheal vessels removed at the coronal and sagittal positions according to the lung mask, the left lung mask and the right lung mask, and acquiring a lung MIP image, a left lung MIP image and a right lung MIP image when MIP reconstruction of the novel coronavirus pneumonia is carried out at the projection value bit average value.
4. The system of claim 1, further comprising:
and the fourth reconstruction module is used for mapping the CT image data with the tracheal vessels removed at the coronal and sagittal positions by using a gray scale CT value according to the lung mask, the left lung mask and the right lung mask, wherein the mapped value is the minimum value of the current layer, and a lung MinIP image, a left lung MinIP image and a right lung MinIP image are obtained.
5. The system of claim 1, further comprising: a preprocessing module, wherein the preprocessing module specifically includes a feature map unit and a decoding unit, wherein:
the characteristic diagram unit is used for inputting the preprocessed CT image data into an encoder in the segmentation network to obtain a characteristic diagram;
the decoding unit is configured to input the feature map into a decoder of the segmentation network, and obtain the lung image, the blood vessel image, and the trachea image, where a high-resolution feature of a shallower layer in the encoder is directly connected to a low-resolution feature of a higher layer in the decoder.
6. A reconstruction method based on CT detection of novel coronavirus pneumonia is characterized by comprising the following steps:
inputting the preprocessed CT image data into a segmentation network to obtain a lung image, a blood vessel image and a trachea image, wherein the segmentation network is obtained by training by taking the preprocessed CT image data as a sample and taking the lung image, the blood vessel image and the trachea image as labels;
carrying out binarization processing on the lung image to obtain a lung mask, a left lung mask and a right lung mask, carrying out binarization processing on the blood vessel image to obtain a blood vessel mask, and carrying out binarization processing on the trachea image to obtain a trachea mask;
acquiring an interested region in the preprocessed CT image data, wherein the interested region is a human body region;
according to the trachea mask and the blood vessel mask, pixel values corresponding to the trachea mask and the blood vessel mask are set as global minimum values in the region of interest, so that the trachea and the blood vessels are removed in the region of interest, and the position, the form, the distribution range and the contrast relation with surrounding tissues of lung lesions are clearly displayed.
7. The method of claim 6, further comprising:
and superposing all axial images in the CT image data with the tracheal vessels removed according to the lung mask, the left lung mask and the right lung mask, and performing coronary, sagittal and any-angle oblique position image recombination on lung tissues corresponding to a reconstruction line marked by a preset marking line to obtain a lung MPR image, a left lung MPR image and an MPR image of the right lung.
8. The method of claim 6, further comprising:
and mapping the CT image data with the tracheal vessels removed at coronal and sagittal positions by gray scale CT values according to the lung mask, the left lung mask and the right lung mask, and acquiring a lung MIP image, a left lung MIP image and a right lung MIP image when reconstructing MIP of the novel coronavirus pneumonia in the process of projecting the mean value of the value positions.
9. The method of claim 6, further comprising:
and mapping the CT image data with the tracheal vessels removed at coronal and sagittal positions according to the lung mask, the left lung mask and the right lung mask, wherein the mapped value is the minimum value of the current layer, and acquiring a lung MinIP image, a left lung MinIP image and a right lung MinIP image.
10. The method according to claim 6, wherein the inputting the preprocessed CT image data into a segmentation network for obtaining lung images, blood vessel images and trachea images comprises:
inputting the preprocessed CT image data into an encoder in the segmentation network to obtain a characteristic diagram;
and inputting the feature map into a decoder of the segmentation network to obtain the lung image, the blood vessel image and the trachea image, wherein the high-resolution features of the shallow layer in the encoder are directly connected with the low-resolution features of the higher layer in the decoder.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010264425.9A CN111462270A (en) | 2020-04-07 | 2020-04-07 | Reconstruction system and method based on novel coronavirus pneumonia CT detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010264425.9A CN111462270A (en) | 2020-04-07 | 2020-04-07 | Reconstruction system and method based on novel coronavirus pneumonia CT detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111462270A true CN111462270A (en) | 2020-07-28 |
Family
ID=71681468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010264425.9A Pending CN111462270A (en) | 2020-04-07 | 2020-04-07 | Reconstruction system and method based on novel coronavirus pneumonia CT detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111462270A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037238A (en) * | 2020-09-01 | 2020-12-04 | 北京推想科技有限公司 | Image display method, device, equipment and medium |
| CN113066024A (en) * | 2021-03-19 | 2021-07-02 | 北京达佳互联信息技术有限公司 | Training method of image blur detection model, image blur detection method and device |
| CN113506250A (en) * | 2021-06-25 | 2021-10-15 | 沈阳东软智能医疗科技研究院有限公司 | Pulmonary aorta blood vessel extraction method, device, readable storage medium and electronic equipment |
| CN113764072B (en) * | 2021-05-13 | 2023-04-18 | 腾讯科技（深圳）有限公司 | Medical image reconstruction method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101981202B1 (en) * | 2018-12-11 | 2019-05-22 | 메디컬아이피 주식회사 | Method and apparatus for reconstructing medical image |
| CN109859217A (en) * | 2019-02-20 | 2019-06-07 | 厦门美图之家科技有限公司 | The dividing method in pore region and calculating equipment in facial image |
| CN109961059A (en) * | 2019-04-10 | 2019-07-02 | 杭州智团信息技术有限公司 | Detect the method and system in kidney tissue of interest region |
| CN110473203A (en) * | 2018-05-09 | 2019-11-19 | 西门子医疗有限公司 | Medical image segmentation |
| CN110533113A (en) * | 2019-09-04 | 2019-12-03 | 湖南大学 | Branch's point detecting method of tree in a kind of digital picture |
| CN110766713A (en) * | 2019-10-30 | 2020-02-07 | 上海微创医疗器械（集团）有限公司 | Lung image segmentation method and device and lung lesion region identification equipment |
-
2020
- 2020-04-07 CN CN202010264425.9A patent/CN111462270A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110473203A (en) * | 2018-05-09 | 2019-11-19 | 西门子医疗有限公司 | Medical image segmentation |
| KR101981202B1 (en) * | 2018-12-11 | 2019-05-22 | 메디컬아이피 주식회사 | Method and apparatus for reconstructing medical image |
| CN109859217A (en) * | 2019-02-20 | 2019-06-07 | 厦门美图之家科技有限公司 | The dividing method in pore region and calculating equipment in facial image |
| CN109961059A (en) * | 2019-04-10 | 2019-07-02 | 杭州智团信息技术有限公司 | Detect the method and system in kidney tissue of interest region |
| CN110533113A (en) * | 2019-09-04 | 2019-12-03 | 湖南大学 | Branch's point detecting method of tree in a kind of digital picture |
| CN110766713A (en) * | 2019-10-30 | 2020-02-07 | 上海微创医疗器械（集团）有限公司 | Lung image segmentation method and device and lung lesion region identification equipment |
Non-Patent Citations (2)
| Title |
|---|
| 余建明等: "《CR、DR成像技术学》", 30 September 2009, 北京：中国医药出版社 * |
| 王霞 等: "螺旋 CT三维重建技术对孤立性肺结节征象的研究进展", 《海南医学》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037238A (en) * | 2020-09-01 | 2020-12-04 | 北京推想科技有限公司 | Image display method, device, equipment and medium |
| CN113066024A (en) * | 2021-03-19 | 2021-07-02 | 北京达佳互联信息技术有限公司 | Training method of image blur detection model, image blur detection method and device |
| CN113764072B (en) * | 2021-05-13 | 2023-04-18 | 腾讯科技（深圳）有限公司 | Medical image reconstruction method, device, equipment and storage medium |
| CN113506250A (en) * | 2021-06-25 | 2021-10-15 | 沈阳东软智能医疗科技研究院有限公司 | Pulmonary aorta blood vessel extraction method, device, readable storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108648172B (en) | CT (computed tomography) map pulmonary nodule detection system based on 3D-Unet | |
| US9968257B1 (en) | Volumetric quantification of cardiovascular structures from medical imaging | |
| CN110796613B (en) | Automatic identification method and device for image artifacts | |
| CN111462270A (en) | Reconstruction system and method based on novel coronavirus pneumonia CT detection | |
| CN111640100A (en) | Tumor image processing method and device, electronic equipment and storage medium | |
| JP2016531709A (en) | Image analysis technology for diagnosing disease | |
| CN106709920B (en) | Blood vessel extraction method and device | |
| WO2022105623A1 (en) | Intracranial vascular focus recognition method based on transfer learning | |
| CN112529909A (en) | Tumor image brain region segmentation method and system based on image completion | |
| US11386555B2 (en) | Assessment of arterial calcifications | |
| CN110880366A (en) | Medical image processing system | |
| CN107146262B (en) | Three-dimensional visualization method and system for OCT (optical coherence tomography) image | |
| CN114119602B (en) | Method, apparatus and storage medium for object analysis of medical images | |
| CN110807770A (en) | Medical image processing, recognizing and displaying method and storage medium | |
| EP2052363A2 (en) | A method, apparatus, graphical user interface, computer-readable medium, and use for quantification of a structure in an object of an image dataset | |
| EP4322836A1 (en) | Systems and methods for reconstruction of 3d images from ultrasound and camera images | |
| CN110706236A (en) | Three-dimensional reconstruction method and device of blood vessel image | |
| CN111210431B (en) | Blood vessel segmentation method, device, equipment and storage medium | |
| CN116091466A (en) | Image analysis method, computer device, and storage medium | |
| CN116758087B (en) | Lumbar vertebra CT bone window side recess gap detection method and device | |
| Kiraly et al. | 3D human airway segmentation for virtual bronchoscopy | |
| CN114387464A (en) | Vulnerable plaque identification method based on IVUS image, computer device, readable storage medium and program product | |
| CN111627023B (en) | Method and device for generating coronary artery projection image and computer readable medium | |
| EP4167184A1 (en) | Systems and methods for plaque identification, plaque composition analysis, and plaque stability detection | |
| CN112116623A (en) | Image segmentation method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |