Aortic region of interest extraction method, electronic device, and storage medium

Abstract

This invention provides a method, electronic device, and storage medium for extracting the region of interest (ROI) of the aorta. The method includes segmenting a medical image to be extracted; obtaining the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle based on a lung mask image; obtaining the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region based on the lower boundary location information of the lung region; obtaining the upper and lower boundary location information of the ROI of the aorta based on the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region; and extracting the ROI of the aorta based on the coordinate information of the minimum horizontal bounding rectangle and the upper and lower boundary location information of the ROI of the aorta. This invention can automatically and accurately extract the ROI of the aorta, which is not only low-cost but also highly efficient.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method for extracting regions of interest in the aorta, an electronic device, and a storage medium. Background Technology

[0002] Enhanced CT, based on a plain CT scan, uses intravenous injection of contrast agent to focus on areas of suspected lesions. It allows for non-invasive visualization of these areas on imaging, aiding doctors in assessing the patient's condition and making informed diagnoses. To avoid the slow and error-prone nature of manual confirmation of regions of interest (ROIs) in the aorta, automated methods for screening ROIs are increasingly being used. However, existing automated screening methods still have the following limitations:

[0003] (1) Deep learning-based methods require manual annotation of samples of regions of interest, which requires the annotators to have relevant medical expertise and is time-consuming.

[0004] (2) The registration-based method requires the extraction of feature points from the existing aortic model, and the extracted feature points can only be used to coarsely locate the region of interest of the aorta.

[0005] (3) The aortic region of interest is located based on morphological methods. Since morphological operations often discard small objects, the range of the aortic region of interest found is relatively small. Summary of the Invention

[0006] The purpose of this invention is to provide a method, electronic device, and storage medium for extracting regions of interest in the aorta, which can extract the regions of interest in the aorta efficiently and accurately at a low cost.

[0007] To achieve the above objectives, the present invention provides a method for extracting the region of interest in the aorta, comprising:

[0008] The acquired medical image to be extracted is segmented to obtain a lung mask image;

[0009] Based on the lung mask image, obtain the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region;

[0010] Based on the lower boundary location information of the lung region, the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the physical distance information from the ending image layer to the lower boundary of the lung region are obtained respectively.

[0011] Based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region, the upper boundary position information of the region of interest of the aorta corresponding to the medical image to be extracted is obtained; based on the physical distance information from the ending image layer of the medical image to be extracted to the lower boundary of the lung region, the lower boundary position information of the region of interest of the aorta corresponding to the medical image to be extracted is obtained.

[0012] Based on the coordinate information of the minimum horizontal bounding rectangle and the upper and lower bound position information of the region of interest of the aorta to be extracted, the region of interest of the aorta is extracted.

[0013] Optionally, before segmenting the acquired medical image to be extracted, the method further includes:

[0014] The medical image to be extracted is downsampled to reduce its size to a preset size.

[0015] The step of obtaining the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region based on the lung mask image includes:

[0016] The lung mask image is upsampled to enlarge it to the original size of the medical image to be extracted;

[0017] Based on the magnified lung mask image, the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region are obtained.

[0018] Optionally, the segmentation process of the acquired medical image to be extracted to obtain a lung mask image includes:

[0019] The medical image to be extracted is binarized according to a preset threshold to obtain a first mask image;

[0020] The hole areas in the first mask image are filled to obtain the second mask image;

[0021] A subtraction operation is performed on the second mask image and the first mask image to obtain a third mask image;

[0022] Connectivity analysis is performed on the third mask image to obtain a lung mask image.

[0023] Optionally, performing connected component analysis on the third mask image to obtain a lung mask image includes:

[0024] Perform connected component analysis on the third mask image to obtain multiple connected components;

[0025] Exclude connected components that traverse more than a preset number of layers, and use the largest connected component among the remaining connected components as the lung region to obtain a lung mask image.

[0026] Optionally, obtaining the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region based on the lower boundary location information of the lung region includes:

[0027] Based on the lower boundary location information of the lung region, calculate the layer distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region;

[0028] Based on the slice thickness information of the medical image to be extracted and the slice distance information from the starting image layer to the lower boundary of the lung region, calculate the physical distance information from the starting image layer to the lower boundary of the lung region of the medical image to be extracted.

[0029] The step of obtaining the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region based on the lower boundary location information of the lung region includes:

[0030] Based on the lower boundary location information of the lung region, calculate the layer distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region;

[0031] Based on the slice thickness information of the medical image to be extracted and the slice distance information from the terminating image layer to the lower boundary of the lung region, the physical distance information from the terminating image layer to the lower boundary of the lung region is calculated.

[0032] Optionally, obtaining the upper boundary location information of the region of interest of the aorta corresponding to the medical image to be extracted based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region includes:

[0033] Based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region obtained in advance, the upper boundary position information of the aortic region of interest corresponding to the medical image to be extracted is calculated.

[0034] The step of obtaining the lower boundary location information of the region of interest of the aorta corresponding to the medical image to be extracted, based on the physical distance information from the termination image layer to the lower boundary of the lung region, includes:

[0035] Based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region and the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region obtained in advance, the lower boundary position information of the aortic region of interest corresponding to the medical image to be extracted is calculated.

[0036] Optionally, the step of calculating the upper boundary location information of the aortic region of interest corresponding to the medical image to be extracted, based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region obtained in advance, includes:

[0037] The upper bound position information of the region of interest of the aorta corresponding to the medical image to be extracted is calculated according to the following formula:

[0038]

[0039] In the formula, Z upper L is the Z-coordinate of the upper bound of the region of interest of the aorta corresponding to the medical image to be extracted. test Let x be the Z-coordinate of the lower bound of the lung region corresponding to the medical image to be extracted, where Ceilling represents the rounding operation. s_test x is the physical distance from the starting image layer of the medical image to be extracted to the lower boundary of the lung region. s_max The maximum physical distance threshold from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region, t test The slice thickness of the medical image to be extracted;

[0040] The step of calculating the lower boundary location information of the aortic region of interest corresponding to the medical image to be extracted, based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region and the pre-acquired maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region, includes:

[0041] The lower bound position information of the region of interest of the aorta corresponding to the medical image to be extracted is calculated according to the following formula:

[0042]

[0043] In the formula, Z lower The Z-coordinate of the lower bound of the region of interest (ROI) of the aorta corresponding to the medical image to be extracted is y. s_test y is the physical distance from the termination image layer of the medical image to be extracted to the lower boundary of the lung region. s_maxIt is the maximum physical distance threshold from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region.

[0044] Optionally, the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region is obtained through the following process:

[0045] Acquire a preset number of samples, including medical images of the aorta with the region of interest marked and lung mask images corresponding to the medical images of the samples;

[0046] Based on the slice thickness information of the medical image in the sample and the slice distance information from the upper boundary of the aortic region of interest to the lower boundary of the corresponding lung region, calculate the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region in the sample.

[0047] Based on the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region for all samples, calculate the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region;

[0048] The maximum physical distance threshold from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region is obtained through the following process:

[0049] Based on the slice thickness information of the medical image in the sample and the slice distance information from the lower boundary of the aortic region of interest to the lower boundary of the corresponding lung region, calculate the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region in the sample.

[0050] Based on the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region for all samples, calculate the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region.

[0051] Optionally, the step of calculating the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region based on the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region for all samples includes:

[0052] Based on the physical distance information from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region for all samples, calculate the mean and variance of the first sample.

[0053] Based on the first sample mean and the first sample variance, calculate the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region;

[0054] The step of calculating the maximum physical distance threshold between the lower boundary of the aortic region of interest and the lower boundary of the lung region based on the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region for all samples includes:

[0055] The second sample mean and the second sample variance are calculated based on the physical distance information from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region for all samples.

[0056] Based on the second sample mean and the second sample variance, calculate the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region.

[0057] Optionally, calculating the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region based on the first sample mean and the first sample variance includes:

[0058] The maximum physical distance threshold from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region is calculated using the following formula:

[0059]

[0060] In the formula, x s_max The threshold for the maximum physical distance from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region. S is the mean of the first sample, p is the pre-set reliability, and S x 2 The variance of the first sample;

[0061] The step of calculating the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region based on the second sample mean and the second sample variance includes:

[0062] The maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region is calculated using the following formula:

[0063]

[0064] In the formula, y s_max The threshold for the maximum physical distance from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region. S is the second sample mean, p is the pre-set reliability, and S y 2 This represents the variance of the second sample.

[0065] To achieve the above objectives, the present invention also provides an electronic device, including a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, it implements the aortic region of interest extraction method described above.

[0066] To achieve the above objectives, the present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the aortic region of interest extraction method described above.

[0067] Compared with existing technologies, the aortic region of interest extraction method, electronic device, and storage medium provided by this invention have the following advantages: This invention first segments the acquired medical image to be extracted to obtain a lung mask image; then, based on the lung mask image, it obtains the lower boundary position information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region; then, based on the lower boundary position information of the lung region, it obtains the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region; then, based on the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region, it obtains the upper and lower boundary position information of the aortic region of interest corresponding to the medical image; finally, based on the coordinate information of the minimum horizontal bounding rectangle and the upper and lower boundary position information of the aortic region of interest, it extracts the aortic region of interest. Therefore, this invention can automatically and accurately extract the aortic region of interest, which is not only low-cost but also highly efficient. Furthermore, this invention is applicable to the extraction of aortic regions of interest in three-dimensional space, and the aortic region of interest covers a large area. The Region of Interest (ROI) for the aorta proposed in this invention provides prior knowledge for machine learning algorithms to compute the aortic region. This helps filter out disruptive exceptions during deep learning model training and reduces unnecessary detection areas and noise generation in false-positive aortic modeling regions during testing. Furthermore, the ROI extracted using this invention can assist trainers in conducting aortic professional knowledge training and help doctors quickly observe the aortic region. Attached Figure Description

[0068] Figure 1 This is a flowchart illustrating a method for extracting the region of interest in the aorta according to an embodiment of the present invention.

[0069] Figure 2 This is a schematic diagram of the process of acquiring a lung mask image according to one embodiment of the present invention;

[0070] Figure 3a This is a cross-sectional schematic diagram of the first mask image in a specific example of the present invention;

[0071] Figure 3b This is a cross-sectional schematic diagram of the second mask image in a specific example of the present invention;

[0072] Figure 3c This is a cross-sectional schematic diagram of the third mask image in a specific example of the present invention;

[0073] Figure 3d This is a schematic cross-sectional view of a lung mask image in a specific example of the present invention;

[0074] Figure 4 This is a schematic diagram of the lower boundary of the lung region in a specific example of the present invention;

[0075] Figure 5 This is a schematic diagram of the process for obtaining the maximum physical distance threshold in one embodiment of the present invention;

[0076] Figure 6 This is a schematic diagram of the region of interest in the aorta obtained through manual annotation in a specific example.

[0077] Figure 7 This is a schematic diagram of the region of interest in the aorta obtained using the method provided by the present invention;

[0078] Figure 8 This is a block diagram of an electronic device according to one embodiment of the present invention;

[0079] The reference numerals in the attached figures are as follows:

[0080] Lung region -10, lower boundary -11;

[0081] Processor-21; Communication interface-22; Memory-23; Communication bus-24. Detailed Implementation

[0082] The following detailed description, in conjunction with the accompanying drawings and specific embodiments, further illustrates the aortic region of interest extraction method, electronic device, and storage medium proposed in this invention. The advantages and features of this invention will become clearer from the following description. It should be noted that the drawings are in a very simplified form and use non-precise proportions, used only to facilitate and clearly illustrate the embodiments of this invention. Please refer to the drawings to make the objectives, features, and advantages of this invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only for illustrative purposes and to enable those skilled in the art to understand and read them, and are not intended to limit the implementation conditions of this invention. Any modifications to the structure, changes in proportions, or adjustments to the size, provided that the effects and objectives achieved by this invention are the same or similar, should still fall within the scope of the technical content disclosed in this invention.

[0083] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0084] The core idea of ​​this invention is to provide a method, electronic device, and storage medium for extracting regions of interest in the aorta, which can extract the regions of interest in the aorta efficiently and accurately at a low cost.

[0085] To realize the above ideas, the inventors of this invention, through extensive practice and in-depth research, discovered that although different enhanced CT sequences of the aorta cover different areas of the human body, since all enhanced CT sequences of the aorta include all or part of the thoracic and abdominal aortas, and the aorta in the thoracic and abdominal regions inevitably involves the lung region, almost all enhanced CT sequences of the aorta include all or part of the lung region to some extent. Based on this, this invention proposes a method for rapidly and efficiently predicting the region of interest of the aorta by using the lower boundary of the lung region (i.e., the horizontal plane where the end of the lung region away from the head (i.e., the lowest point of the lung region) is located).

[0086] It should be noted that the aortic region of interest extraction method of the present invention can be applied to the electronic device of the present invention, wherein the electronic device can be a personal computer, a mobile terminal, etc., and the mobile terminal can be a mobile phone, a tablet computer, or other hardware device with various operating systems. Furthermore, it should be noted that although the present invention uses a CT image sequence as an example of the medical image to be extracted, as those skilled in the art will understand, the medical image to be extracted can also be an MRI image sequence or other types of three-dimensional images, and the present invention does not limit this.

[0087] To achieve the above-mentioned goals, this invention provides a method for extracting the region of interest in the aorta. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of a method for extracting the region of interest in the aorta according to an embodiment of the present invention. Figure 1 As shown, the method for extracting the region of interest in the aorta includes the following steps:

[0088] Step S100: Segment the acquired medical image to be extracted to obtain a lung mask image.

[0089] Step S200: Based on the lung mask image, obtain the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region.

[0090] Step S300: Based on the lower boundary location information of the lung region, obtain the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the physical distance information from the ending image layer to the lower boundary of the lung region.

[0091] Step S400: Obtain the upper boundary position information of the region of interest of the aorta corresponding to the medical image to be extracted based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region; and obtain the lower boundary position information of the region of interest of the aorta corresponding to the medical image to be extracted based on the physical distance information from the ending image layer of the medical image to be extracted to the lower boundary of the lung region.

[0092] Step S500: Extract the region of interest of the aorta based on the coordinate information of the minimum horizontal bounding rectangle and the upper and lower bound position information of the region of interest of the aorta to be extracted.

[0093] Therefore, this invention can automatically and accurately extract the region of interest (ROI) of the aorta, which is not only low-cost but also highly efficient. Furthermore, this invention is applicable to the extraction of ROI in three-dimensional space, covering a large ROI area. The ROI proposed in this invention can provide prior knowledge for machine learning algorithms to calculate the aortic region, helping to filter out special cases that interfere with training during deep learning model training, and helping to reduce unnecessary detection areas and suppress noise in false positive aortic modeling areas during deep learning model testing. In addition, the ROI extracted using this invention can also help trainers conduct aortic professional knowledge training and help doctors quickly observe the aortic region. It should be noted that, as those skilled in the art will understand, the minimum horizontal bounding rectangle of the lung region refers to the minimum bounding rectangle corresponding to the maximum cross-section of the lung region, based on the coordinate information of the minimum horizontal bounding rectangle [row]. min row max ,col min ,col max The region of interest in the aorta to be extracted can be obtained on the horizontal plane, and then combined with the position Z of the upper boundary of the region of interest in the aorta to be extracted. upper and the position of the lower bound Z lowerThis allows for the extraction of the region of interest in the aorta. Furthermore, it should be noted that, as those skilled in the art will understand, the coordinates of the minimum horizontal bounding rectangle refer to the X and Y coordinates of the four vertices of the minimum horizontal bounding rectangle in the pixel coordinate system (i.e., the horizontal plane coordinates of the four vertices in the pixel coordinate system).

[0094] Specifically, the acquired medical image to be extracted can be an enhanced CT image sequence, an enhanced MRI image sequence, or other types of three-dimensional images; this invention does not limit this. The medical image to be extracted can be acquired using an image acquisition device, such as CT or MRI imaging equipment, or it can be collected via the internet or obtained through scanning equipment; this invention does not limit this either.

[0095] In one exemplary embodiment, before segmenting the acquired medical image to be extracted, the method further includes:

[0096] The medical image to be extracted is downsampled to reduce its size to a preset size.

[0097] Due to the continuous improvement in the quality of imaging equipment such as CT scanners and the increasing capacity of storage media, the image size of single-sequence CT scans has generally reached 512×512×N pixels, where N represents the total number of layers in the image sequence (i.e., the total number of images). Since three-dimensional image processing algorithms are more complex than two-dimensional image processing algorithms, the processing speed is somewhat reduced. Therefore, this invention performs downsampling processing on the medical image to be extracted before segmentation, reducing the image to a preset size, for example, reducing the image from 512×512×N pixels to (512 / R)×(512 / R)×(N / R) pixels. Segmentation of the reduced image at the preset size effectively reduces computational load and improves segmentation efficiency. The inventors of this invention have discovered through extensive experiments that reducing the medical image to be extracted by a factor of 4 (i.e., R=4) allows for more accurate and efficient segmentation of the lung region.

[0098] Correspondingly, obtaining the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region based on the lung mask image includes:

[0099] The lung mask image is upsampled to enlarge it to the original size of the medical image to be extracted;

[0100] Based on the magnified lung mask image, the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region are obtained.

[0101] Specifically, if the lung mask image is obtained by segmenting a medical image to be extracted that has been reduced by a factor of R, then by performing corresponding upsampling processing (i.e., magnifying by a factor of R) on the lung mask image, the lung mask image can be magnified to the original size of the medical image to be extracted.

[0102] Preferably, please refer to Figure 2 The diagram illustrates a flowchart of acquiring a lung mask image according to an embodiment of the present invention. Figure 2 As shown, the algorithm used to process the medical image to be extracted to obtain a lung mask image includes:

[0103] The medical image to be extracted is binarized according to a preset threshold to obtain a first mask image;

[0104] The hole areas in the first mask image are filled to obtain the second mask image;

[0105] A subtraction operation is performed on the second mask image and the first mask image to obtain a third mask image;

[0106] Connectivity analysis is performed on the third mask image to obtain a lung mask image.

[0107] Specifically, the preset threshold can be set according to specific circumstances. For example, if the medical image to be extracted is a CT image sequence, the preset threshold can be set to -500. Thus, by binarizing the medical image to be extracted, the pixel values ​​of pixels with a CT value ≥ -500 can be set to 1, and the pixel values ​​of pixels with a CT value < -500 can be set to 0, thereby obtaining a CT image of the human body structure without air, i.e., the first mask image. Please refer to... Figure 3a The diagram schematically illustrates a cross-sectional view of the first mask image (i.e., a certain image layer in the first mask image) in a specific example of the present invention. Figure 3a As shown, by performing binarization processing on the medical image to be extracted according to a preset threshold, the external air area and the internal cavity area of ​​the human body (i.e., the lung area) in the medical image to be extracted can be set to black, while the torso area and the machine tool area can be set to white.

[0108] Please continue to refer to this. Figure 3b The diagram schematically illustrates a cross-sectional view of the second mask image (i.e., a certain image layer in the second mask image) in a specific example of the present invention. Figure 3bAs shown, by filling the hole regions (i.e., black areas within white areas, i.e., lung areas) in the first mask image, the hole regions (i.e., black areas within white areas, i.e., lung areas) in the first mask image can be set to white to obtain the second mask image. Specifically, a filling algorithm in the prior art, such as the seed point growth algorithm, can be used. By setting seed points, the hole regions (i.e., black areas within white areas, i.e., black areas within white areas) in the first mask image can be filled, thus setting the hole regions (i.e., black areas within white areas, i.e., black areas within white areas) in the first mask image to white. Further details on seed point generation algorithms can be found in existing technologies, and will not be elaborated upon here.

[0109] Please continue to refer to this. Figure 3c The diagram schematically illustrates a cross-sectional view of the third mask image (i.e., a certain image layer in the third mask image) in a specific example of the present invention. Figure 3c As shown, by performing a subtraction operation on the second mask image and the first mask image (that is, subtracting the first mask image from the second mask image), a third mask image in which the lung area is white can be obtained.

[0110] Preferably, the connected component analysis of the third mask image to obtain the lung mask image includes:

[0111] Perform connected component analysis on the third mask image to obtain multiple connected components;

[0112] Exclude connected components that traverse more than a preset number of layers, and use the largest connected component among the remaining connected components as the lung region to obtain a lung mask image.

[0113] Because CT scans and other images often contain interference from background devices (such as machine tools), the gap between the machine tool and the human body can also become a candidate lung region in the third mask image. Therefore, it is necessary to remove this interfering region. This invention uses connected component analysis on the third mask image to obtain multiple connected components. Due to the long length of the machine tool, the connected components in the machine tool area traverse a large number of layers. Therefore, this invention effectively removes the interfering region of the gap between the machine tool and the human body by excluding connected components that traverse more than a preset number of layers (e.g., more than 80% of the total number of layers in the entire medical image to be extracted, such as 95%). Among the remaining connected components, the lung region has the largest volume; therefore, the largest remaining connected component is the lung region. Please refer to [reference needed]. Figure 3d The diagram schematically illustrates a cross-sectional view of a lung mask image (i.e., a specific image layer within the lung mask image) in a specific example of the present invention. Figure 3dAs shown, by performing connected component analysis on the third mask image, interference regions can be effectively removed to obtain a complete mask image of the lung region.

[0114] Please continue to refer to this. Figure 4 This schematically illustrates the lower boundary of the lung region in a specific example of the present invention. For example... Figure 4 As shown, in this invention, the plane containing the bottommost point of the lung region 10 is defined as the lower boundary 11 of the lung region. Thus, the position of the lower boundary 11 of the lung region is determined according to the number of layers in the image layer containing the bottommost point of the lung region 10 in the lung mask image / enlarged lung mask image.

[0115] In one exemplary embodiment, obtaining the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region based on the lower boundary location information of the lung region includes:

[0116] Based on the lower boundary location information of the lung region, calculate the layer distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region;

[0117] Based on the slice thickness information of the medical image to be extracted and the slice distance information from the starting image layer to the lower boundary of the lung region, calculate the physical distance information from the starting image layer to the lower boundary of the lung region of the medical image to be extracted.

[0118] The step of obtaining the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region based on the lower boundary location information of the lung region includes:

[0119] Based on the lower boundary location information of the lung region, calculate the layer distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region;

[0120] Based on the slice thickness information of the medical image to be extracted and the slice distance information from the terminating image layer to the lower boundary of the lung region, the physical distance information from the terminating image layer to the lower boundary of the lung region is calculated.

[0121] Specifically, the layer distance from the starting image layer of the medical image to the lower boundary of the lung region can be obtained by subtracting the layer number of the image layer containing the lower boundary of the lung region from the layer number of the image layer containing the lower boundary of the lung region. Similarly, the layer distance from the ending image layer of the medical image to the lower boundary of the lung region can be obtained by subtracting the layer number of the image layer containing the lower boundary of the lung region from the layer number of the ending image layer of the medical image to be extracted. It should be noted that, as those skilled in the art will understand, the layer thickness information referred to in this invention refers to the thickness of each image layer of the medical image to be extracted (i.e., the physical distance corresponding to a unit pixel, in mm). Therefore, it is assumed that the thickness of each image layer of the medical image to be extracted is t. test The distance between the starting image layer of the medical image to be extracted and the lower boundary of the lung region is x. test The layer distance from the termination image layer of the medical image to be extracted to the lower boundary of the lung region is y. test The physical distance x from the starting image layer of the medical image to be extracted to the lower boundary of the lung region is... stest For: x s_tset =x test *t test The physical distance from the termination image layer of the medical image to be extracted to the lower boundary of the lung region is: y s_tset =y test *t test .

[0122] Further, obtaining the upper boundary location information of the region of interest of the aorta corresponding to the medical image to be extracted, based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region, includes:

[0123] Based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region obtained in advance, the upper boundary position information of the aortic region of interest corresponding to the medical image to be extracted is calculated.

[0124] The step of obtaining the lower boundary location information of the region of interest of the aorta corresponding to the medical image to be extracted, based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region, includes:

[0125] Based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region and the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region obtained in advance, the lower boundary position information of the aortic region of interest corresponding to the medical image to be extracted is calculated.

[0126] Therefore, based on the physical distance from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the pre-obtained maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region, the position (in pixel coordinates) of the upper boundary of the aortic region of interest corresponding to the medical image to be extracted can be accurately calculated. Similarly, based on the physical distance from the ending image layer of the medical image to be extracted to the lower boundary of the lung region and the pre-obtained maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region, the position (in pixel coordinates) of the lower boundary of the aortic region of interest corresponding to the medical image to be extracted can be accurately calculated.

[0127] Please continue to refer to this. Figure 5 The diagram illustrates a process for obtaining the maximum physical distance threshold according to an embodiment of the present invention. Figure 5 As shown, the maximum physical distance threshold from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region is obtained through the following process:

[0128] Acquire a preset number of samples, including medical images of the aorta with the region of interest marked and lung mask images corresponding to the medical images of the samples;

[0129] Based on the slice thickness information of the medical image in the sample and the slice distance information from the upper boundary of the aortic region of interest to the lower boundary of the corresponding lung region, calculate the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region in the sample.

[0130] Based on the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region for all samples, calculate the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region.

[0131] Similarly, the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region is obtained through the following process:

[0132] Based on the slice thickness information of the medical image in the sample and the slice distance information from the lower boundary of the aortic region of interest to the lower boundary of the corresponding lung region, calculate the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region in the sample.

[0133] Based on the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region for all samples, calculate the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region.

[0134] Specifically, for each sample, the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region is calculated based on the slice thickness information of the medical image of the sample and the slice distance information from the upper boundary of the aortic region of interest to the lower boundary of the corresponding lung region. The lower boundary location information of the lung region corresponding to the sample can be obtained from the lung mask image in the sample. Therefore, based on the upper boundary location information of the aortic region of interest (location information in pixel coordinates) and the lower boundary location information of the lung region (location information in pixel coordinates), the aortic region of interest is obtained. The physical distance from the upper boundary of the region of interest (ROI) to the lower boundary of its corresponding lung region is calculated by combining the slice thickness information of the sample medical images with the slice thickness information. Finally, based on the physical distance information from the upper boundary of the ROI to the lower boundary of the lung region for all samples, the maximum physical distance threshold from the upper boundary of the ROI to the lower boundary of the lung region can be calculated. The physical distances from the upper boundary of the ROI to the lower boundary of the lung region for all samples can be stored in the same PDS set. upper middle:

[0135] PDS upper ={x i *t i}, i = 1, 2, 3, ... n

[0136] In the formula, x i t represents the layer distance from the upper boundary of the region of interest in the aorta of the i-th sample to the lower boundary of its corresponding lung region. i Let be the slice thickness of the medical image of the i-th sample, and n be the total number of samples.

[0137] The physical distance from the lower bound of the region of interest in the aorta to the lower bound of the lung region for all samples can be stored in the same PDS set. lower middle:

[0138] PDS lower ={y i *t i}, i = 1, 2, 3, ... n

[0139] In the formula, y i t represents the layer distance from the lower bound of the region of interest in the aorta of the i-th sample to the lower bound of its corresponding lung region. i Let be the slice thickness of the medical image of the i-th sample, and n be the total number of samples.

[0140] It should be noted that, as those skilled in the art will understand, the samples in this invention are collected based on real cases, and the samples cover cases of different heights, genders, and weights. Therefore, the accuracy of the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region and the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region can be guaranteed.

[0141] Further, the step of calculating the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region based on the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region for all samples includes:

[0142] Based on the physical distance information from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region for all samples, calculate the mean and variance of the first sample.

[0143] Based on the mean and variance of the first sample, calculate the maximum physical distance threshold from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region.

[0144] The step of calculating the maximum physical distance threshold between the lower boundary of the aortic region of interest and the lower boundary of the lung region based on the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region for all samples includes:

[0145] The second sample mean and the second sample variance are calculated based on the physical distance information from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region for all samples.

[0146] Based on the second sample mean and the second sample variance, calculate the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region.

[0147] Specifically, the first sample mean for:

[0148]

[0149] The first sample variance S x 2 for:

[0150]

[0151] second sample mean for:

[0152]

[0153] The second sample variance S y2 for:

[0154]

[0155] Further, the step of calculating the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region based on the first sample mean and the first sample variance includes:

[0156] The maximum physical distance threshold from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region is calculated using the following formula:

[0157]

[0158] In the formula, x s_max The threshold for the maximum physical distance from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region. S is the mean of the first sample, p is the pre-set reliability, and S x 2 The variance of the first sample is denoted as .

[0159] The step of calculating the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region based on the second sample mean and the second sample variance includes:

[0160] The maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region is calculated using the following formula:

[0161]

[0162] In the formula, y s_max The threshold for the maximum physical distance from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region. S is the second sample mean, p is the pre-set reliability, and S y 2 This represents the variance of the second sample.

[0163] Specifically, the preset reliability p can be set according to specific circumstances, and the value of the preset reliability p is between 0 and 1. This invention does not limit this value.

[0164] Therefore, this invention obtains the maximum physical distance threshold x from the upper boundary of the aortic region of interest to the lower boundary of the lung region by statistically analyzing a large number of samples. s_max The maximum physical distance threshold y from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region. s_max This allows for the accurate extraction of the region of interest (ROI) of the aorta from the medical image to be extracted.

[0165] In one exemplary embodiment, calculating the upper boundary location information of the aortic region of interest corresponding to the medical image to be extracted, based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the pre-acquired maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region, includes:

[0166] The upper bound of the region of interest in the aorta to be extracted is calculated using the following formula:

[0167]

[0168] In the formula, Z upper L is the Z-coordinate of the upper bound of the region of interest in the aorta to be extracted. test Let x be the Z-coordinate of the lower bound of the lung region corresponding to the medical image to be extracted, where Ceilling represents the rounding operation. s_test x is the physical distance from the starting image layer of the medical image to be extracted to the lower boundary of the lung region. s_max The maximum physical distance threshold from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region, t test The slice thickness is the thickness of the medical image to be extracted.

[0169] The step of calculating the lower boundary location information of the aortic region of interest corresponding to the medical image to be extracted, based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region and the pre-acquired maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region, includes:

[0170] The lower bound position information of the region of interest of the aorta corresponding to the medical image to be extracted is calculated according to the following formula:

[0171]

[0172] In the formula, Z lower The Z-coordinate of the lower bound of the region of interest (ROI) of the aorta corresponding to the medical image to be extracted is y. s_test y is the physical distance from the termination image layer of the medical image to be extracted to the lower boundary of the lung region. s_max It is the maximum physical distance threshold from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region.

[0173] Therefore, when the physical distance from the starting image layer of the medical image to be extracted to the lower boundary of the lung region is greater than the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region, the Z-coordinate of the upper boundary of the lung region corresponding to the medical image to be extracted is obtained by subtracting the rounded value of the quotient of the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region and the layer thickness of the medical image to be extracted from the Z-coordinate (Z-coordinate in pixel coordinate system) of the lower boundary of the lung region corresponding to the medical image to be extracted. upper (Z coordinate in pixel coordinate system); when the physical distance from the starting image layer of the medical image to be extracted to the lower boundary of the lung region is less than or equal to the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region, then the Z coordinate of the lower boundary of the lung region corresponding to the medical image to be extracted is set. upper The upper boundary Z-coordinate (in pixel coordinates) of the region of interest (ROI) can be obtained by subtracting the rounded value of the quotient of the physical distance from the starting image layer of the medical image to the lower boundary of its corresponding lung region and the layer thickness of the medical image to be extracted (i.e., the layer number distance from the starting image layer of the medical image to the lower boundary of its corresponding lung region). Similarly, when the physical distance from the ending image layer of the medical image to the lower boundary of the lung region is greater than the maximum physical distance threshold from the lower boundary of the aortic ROI to the lower boundary of the lung region, the lower boundary Z-coordinate (in pixel coordinates) of the corresponding lung region is subtracted by the rounded value of the quotient of the maximum physical distance threshold from the lower boundary of the aortic ROI to the lower boundary of the lung region and the layer thickness of the medical image to be extracted. lower (Z coordinate in pixel coordinate system); When the physical distance from the termination image layer of the medical image to be extracted to the lower boundary of the lung region is less than or equal to the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region, the Z coordinate (Z coordinate in pixel coordinate system) of the lower boundary of the lung region corresponding to the medical image to be extracted is subtracted from the rounded value of the quotient of the physical distance from the termination image layer of the medical image to the lower boundary of its corresponding lung region and the layer thickness of the medical image to be extracted (i.e., the layer number distance from the termination image layer of the medical image to the lower boundary of its corresponding lung region). This yields the Z coordinate Z of the lower boundary of the region of interest to be extracted. lower (Z coordinate in pixel coordinate system).

[0174] Please continue to refer to this. Figure 6 and Figure 7 ,in Figure 6A schematic diagram of the region of interest in the aorta obtained by manual annotation is given in a specific example. The area defined by the three-dimensional wireframe in the figure is the region of interest in the aorta. Figure 7 A schematic diagram of the region of interest (ROI) in the aorta obtained using the method provided by this invention is shown. The region defined by the three-dimensional frame in the diagram is the ROI of the aorta. By... Figure 6 and Figure 7 Comparison shows that the method provided by this invention can accurately extract the region of interest (ROI) of the aorta, thereby providing prior knowledge for machine learning algorithms to calculate the aortic region. This helps filter out special cases that interfere with training during deep learning model training, and reduces unnecessary detection areas and suppresses noise in false-positive aortic modeling areas during deep learning model testing. Furthermore, the ROI extracted by this invention can also help trainers conduct aortic professional knowledge training and help doctors quickly observe the aortic region. It should be noted that, as those skilled in the art will understand, the horizontal plane containing the minimum horizontal bounding rectangle A1B1C1D1 is the upper bound of the ROI, and the horizontal plane containing the minimum horizontal bounding rectangle A2B2C2D2 is the lower bound of the ROI. Based on the coordinates of the minimum horizontal bounding rectangle of the lung region, the X and Y coordinates of points A1, B1, C1, D1, A2, B2, C2, and D2 in the pixel coordinate system can be obtained. Based on the Z coordinate of the upper bound of the ROI to be extracted... upper The Z coordinates of points A1, B1, C1, and D1 in the pixel coordinate system can be obtained. Based on the lower bound Z coordinates of the region of interest to be extracted... lower This allows us to obtain the Z coordinates of points A2, B2, C2, and D2 in the pixel coordinate system, and then obtain the 3D coordinates of points A1, B1, C1, D1, A2, B2, C2, and D2 in the pixel coordinate system. The region defined by the cuboid formed by points A1, B1, C1, D1, A2, B2, C2, and D2 is the region of interest of the aorta.

[0175] Based on the same inventive concept, the present invention also provides an electronic device, please refer to... Figure 8 A block diagram illustrating an embodiment of the electronic device provided by the present invention is shown. Figure 8As shown, the electronic device includes a processor 21 and a memory 23. The memory 23 stores a computer program, which, when executed by the processor 21, implements the aortic region of interest extraction method described above. Since the electronic device provided by this invention belongs to the same inventive concept as the aortic region of interest extraction method described above, it possesses all the advantages of the aortic region of interest extraction method described above, and therefore will not be elaborated further.

[0176] like Figure 8 As shown, the electronic device also includes a communication interface 22 and a communication bus 24, wherein the processor 21, the communication interface 22, and the memory 23 communicate with each other via the communication bus 24. The communication bus 24 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 24 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used to represent it in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 22 is used for communication between the aforementioned electronic device and other devices.

[0177] The processor 21 referred to in this invention can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines.

[0178] The memory 23 can be used to store the computer program. The processor 21 implements various functions of the electronic device by running or executing the computer program stored in the memory 23 and calling the data stored in the memory 23.

[0179] The memory 23 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0180] This invention also provides a readable storage medium storing a computer program that, when executed by a processor, can implement the aortic region of interest extraction method described above. Since the readable storage medium provided by this invention and the aortic region of interest extraction method described above belong to the same inventive concept, it possesses all the advantages of the aortic region of interest extraction method described above, and therefore will not be elaborated further.

[0181] The readable storage medium of embodiments of the present invention can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0182] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0183] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0184] In summary, compared with existing technologies, the aortic region of interest extraction method, electronic device, and storage medium provided by this invention have the following advantages: This invention first segments the acquired medical image to be extracted to obtain a lung mask image; then, based on the lung mask image, it obtains the lower boundary position information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region; then, based on the lower boundary position information of the lung region, it obtains the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region; then, based on the physical distance information from the starting and ending image layers of the medical image to the lower boundary of the lung region, it obtains the upper and lower boundary position information of the aortic region of interest corresponding to the medical image; finally, based on the coordinate information of the minimum horizontal bounding rectangle and the upper and lower boundary position information of the aortic region of interest, it extracts the aortic region of interest. Therefore, this invention can automatically and accurately extract the aortic region of interest, which is not only low-cost but also highly efficient. Furthermore, this invention is applicable to the extraction of aortic regions of interest in three-dimensional space, and the aortic region of interest covers a large area. The Region of Interest (ROI) for the aorta proposed in this invention can provide prior knowledge for machine learning algorithms to compute the aortic region, helping to filter out special cases that interfere with training during deep learning model training, and reducing unnecessary detection areas and suppressing noise in false positive aortic modeling areas during deep learning model testing. Furthermore, the ROI extracted using this invention can also assist trainers in conducting aortic professional knowledge training and help doctors quickly observe the aortic region.

[0185] It should be noted that the apparatus and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0186] In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0187] The above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure are within the protection scope of the present invention. Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention also intends to include these modifications and variations.

Claims

1. A method for extracting regions of interest in the aorta, characterized in that, include: The acquired medical image to be extracted is segmented to obtain a lung mask image; Based on the lung mask image, obtain the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region; Based on the lower boundary location information of the lung region, the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the physical distance information from the ending image layer to the lower boundary of the lung region are obtained respectively. Based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region, the upper boundary position information of the region of interest of the aorta corresponding to the medical image to be extracted is obtained; based on the physical distance information from the ending image layer of the medical image to be extracted to the lower boundary of the lung region, the lower boundary position information of the region of interest of the aorta corresponding to the medical image to be extracted is obtained. Based on the coordinate information of the minimum horizontal bounding rectangle and the upper and lower bound position information of the region of interest of the aorta to be extracted, the region of interest of the aorta is extracted.

2. The method for extracting the region of interest in the aorta according to claim 1, characterized in that, Before segmenting the acquired medical image to be extracted, the method further includes: The medical image to be extracted is downsampled to reduce its size to a preset size. The step of obtaining the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region based on the lung mask image includes: The lung mask image is upsampled to enlarge it to the original size of the medical image to be extracted; Based on the magnified lung mask image, the lower boundary location information of the lung region and the coordinate information of the minimum horizontal bounding rectangle of the lung region are obtained.

3. The method for extracting the region of interest in the aorta according to claim 1, characterized in that, The segmentation process of the acquired medical image to be extracted to obtain a lung mask image includes: The medical image to be extracted is binarized according to a preset threshold to obtain a first mask image; The hole areas in the first mask image are filled to obtain a second mask image, wherein the hole areas are black areas within the white areas; A subtraction operation is performed on the second mask image and the first mask image to obtain a third mask image; Connectivity analysis is performed on the third mask image to obtain a lung mask image.

4. The method for extracting the region of interest in the aorta according to claim 3, characterized in that, The process of performing connected component analysis on the third mask image to obtain a lung mask image includes: Perform connected component analysis on the third mask image to obtain multiple connected components; Exclude connected components that traverse more than a preset number of layers, and use the largest connected component among the remaining connected components as the lung region to obtain a lung mask image.

5. The method for extracting the region of interest in the aorta according to claim 1, characterized in that, The step of obtaining the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region based on the lower boundary location information of the lung region includes: Based on the lower boundary location information of the lung region, calculate the layer distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region; Based on the slice thickness information of the medical image to be extracted and the slice distance information from the starting image layer to the lower boundary of the lung region, calculate the physical distance information from the starting image layer to the lower boundary of the lung region of the medical image to be extracted. The step of obtaining the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region based on the lower boundary location information of the lung region includes: Based on the lower boundary location information of the lung region, calculate the layer distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region; Based on the slice thickness information of the medical image to be extracted and the slice distance information from the terminating image layer to the lower boundary of the lung region, the physical distance information from the terminating image layer to the lower boundary of the lung region is calculated.

6. The method for extracting the region of interest in the aorta according to claim 5, characterized in that, The step of obtaining the upper boundary location information of the region of interest of the aorta corresponding to the medical image to be extracted based on the physical distance information from the starting image layer to the lower boundary of the lung region includes: Based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region obtained in advance, the upper boundary position information of the aortic region of interest corresponding to the medical image to be extracted is calculated. The step of obtaining the lower boundary location information of the region of interest of the aorta corresponding to the medical image to be extracted, based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region, includes: Based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region and the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region obtained in advance, the lower boundary position information of the aortic region of interest corresponding to the medical image to be extracted is calculated.

7. The method for extracting the region of interest in the aorta according to claim 6, characterized in that, The step of calculating the upper boundary location information of the aortic region of interest corresponding to the medical image to be extracted, based on the physical distance information from the starting image layer of the medical image to be extracted to the lower boundary of the lung region and the pre-acquired maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region, includes: The upper bound position information of the region of interest of the aorta corresponding to the medical image to be extracted is calculated according to the following formula: In the formula, The Z-coordinate is the upper bound of the region of interest (ROI) of the aorta corresponding to the medical image to be extracted. The Z-coordinate is the lower bound of the lung region corresponding to the medical image to be extracted, and Ceiling represents the rounding operation. The distance is the physical distance from the starting image layer of the medical image to be extracted to the lower boundary of the lung region. The threshold for the maximum physical distance from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region. The layer thickness of the medical image to be extracted; The step of calculating the lower boundary location information of the aortic region of interest corresponding to the medical image to be extracted, based on the physical distance information from the termination image layer of the medical image to be extracted to the lower boundary of the lung region and the pre-acquired maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region, includes: The lower bound position information of the region of interest of the aorta corresponding to the medical image to be extracted is calculated according to the following formula: In the formula, The Z-coordinate is the lower bound of the region of interest (ROI) of the aorta corresponding to the medical image to be extracted. The distance from the termination image layer of the medical image to be extracted to the lower boundary of the lung region is the physical distance. It is the maximum physical distance threshold from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region.

8. The method for extracting the region of interest in the aorta according to claim 6, characterized in that, The maximum physical distance threshold from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region is obtained through the following process: Acquire a preset number of samples, including medical images of the aorta with the region of interest marked and lung mask images corresponding to the medical images of the samples; Based on the slice thickness information of the medical image in the sample and the slice distance information from the upper boundary of the aortic region of interest to the lower boundary of the corresponding lung region, calculate the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region in the sample. Based on the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region for all samples, calculate the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region; The maximum physical distance threshold from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region is obtained through the following process: Based on the slice thickness information of the medical image in the sample and the slice distance information from the lower boundary of the aortic region of interest to the lower boundary of the corresponding lung region, calculate the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region in the sample. Based on the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region for all samples, calculate the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region.

9. The method for extracting the region of interest in the aorta according to claim 8, characterized in that, The step of calculating the maximum physical distance threshold between the upper boundary of the aortic region of interest and the lower boundary of the lung region based on the physical distance information from the upper boundary of the aortic region of interest to the lower boundary of the lung region for all samples includes: Based on the physical distance information from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region for all samples, calculate the mean and variance of the first sample. Based on the first sample mean and the first sample variance, calculate the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region; The step of calculating the maximum physical distance threshold between the lower boundary of the aortic region of interest and the lower boundary of the lung region based on the physical distance information from the lower boundary of the aortic region of interest to the lower boundary of the lung region for all samples includes: The second sample mean and the second sample variance are calculated based on the physical distance information from the lower boundary of the region of interest in the aorta to the lower boundary of the lung region for all samples. Based on the second sample mean and the second sample variance, calculate the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region.

10. The method for extracting the region of interest in the aorta according to claim 9, characterized in that, The step of calculating the maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region based on the first sample mean and the first sample variance includes: The maximum physical distance threshold from the upper boundary of the aortic region of interest to the lower boundary of the lung region is calculated using the following formula: In the formula, The threshold for the maximum physical distance from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region. p is the mean of the first sample, and p is the pre-set reliability. The variance of the first sample; The step of calculating the maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region based on the second sample mean and the second sample variance includes: The maximum physical distance threshold from the lower boundary of the aortic region of interest to the lower boundary of the lung region is calculated using the following formula: In the formula, The threshold for the maximum physical distance from the upper boundary of the region of interest in the aorta to the lower boundary of the lung region. p is the mean of the second sample, and p is the pre-set reliability. This represents the variance of the second sample.

11. An electronic device, characterized in that, The device includes a processor and a memory, wherein a computer program is stored in the memory, and when executed by the processor, the computer program implements the aortic region of interest extraction method according to any one of claims 1 to 10.

12. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the aortic region of interest extraction method according to any one of claims 1 to 10.

Images