Emphysema Disease Prediction Method, Device, Equipment and Storage Medium

Abstract

The present invention discloses a method, device, equipment and storage medium for predicting emphysema disease. The method includes: obtaining a single lung lobe image of the left lung or the right lung; identifying the emphysema region and the small airway lesion region in the single lung lobe image; determining the emphysema grade detected based on the single lung lobe image, and determining the ratio of the emphysema region to the small airway lesion region; and determining the predicted development grade of emphysema based on the detected emphysema grade and the ratio. The present invention can achieve the determination of the predicted development grade of emphysema and predict the development direction of emphysema disease.

Description

Technical Field

[0001] The present invention relates to the fields of fintech and artificial intelligence technologies, and particularly to a method, device, equipment and storage medium for predicting emphysema disease. Background Art

[0002] Emphysema disease is a common disease that can be prevented and treated, characterized by persistent respiratory symptoms and airflow limitation, caused by abnormal airways and / or alveoli due to significant exposure to harmful particulate matter or gases.

[0003] Clinically, bronchioles with an inner diameter less than 2 mm are usually referred to as small airways. Small airways have the characteristics of low airflow resistance but are easily blocked. During quiet inspiration, air enters the narrow nasopharynx, generating eddy currents. Since small airways no longer have cartilage support, after detaching from the fibrous sheath and embedding in lung tissue, the patency of the lumen is not like that of cartilaginous airways and is easily affected by changes in thoracic pressure.

[0004] Early-stage emphysema disease is a small airway lesion disease. Based on the Global Initiative for Chronic Obstructive Lung Disease (GOLD), the grades of emphysema include: GOLD 0 (nonexistent), GOLD 1 (mild), GOLD 2 (moderate), GOLD 3 (severe), and GOLD 4 (very severe).

[0005] Currently, only the grade of emphysema disease can be detected through images, but the development direction of emphysema disease cannot be predicted. Summary of the Invention

[0006] The main purpose of the present invention is to provide a method, device, equipment and storage medium for predicting emphysema disease, aiming to solve the problem that the existing method cannot predict the development direction of emphysema disease.

[0007] To achieve the above object, the present invention provides a method for predicting emphysema disease, including:

[0008] Obtain a single lung lobe image of the left lung or the right lung;

[0009] Identify the emphysema area and the small airway lesion area in the single lung lobe image;

[0010] Determine the emphysema grade detected based on the single lung lobe image, and determine the ratio of the emphysema area to the small airway lesion area;

[0011] Based on the detected emphysema grade and the ratio, determine the predicted development grade of emphysema.

[0012] Optionally, the determining the ratio of the emphysema area to the small airway lesion area includes:

[0013] Determine the volume of the emphysema region and the volume of the small airway lesion region according to the emphysema region and the small airway lesion region respectively;

[0014] Based on the volume of the emphysema region and the volume of the small airway lesion region, determine the ratio of the emphysema region to the small airway lesion region.

[0015] Optionally, the determining the volume of the emphysema region and the volume of the small airway lesion region according to the emphysema region and the small airway lesion region respectively includes:

[0016] Determine the number of layers, scan slice thickness, and slice interval of the single lung lobe image;

[0017] Perform grid processing on the emphysema region and the small airway lesion region respectively to obtain the first grid area of the emphysema region and the second grid area of the small airway lesion region;

[0018] Based on the number of layers, the scan slice thickness, the slice interval, and the first grid area, determine the volume of the emphysema region;

[0019] Based on the number of layers, the scan slice thickness, the slice interval, and the second grid area, determine the volume of the small airway lesion region.

[0020] Optionally, the performing grid processing on the emphysema region and the small airway lesion region respectively to obtain the first grid area of the emphysema region and the second grid area of the small airway lesion region includes:

[0021] Determine the edge of the emphysema region;

[0022] Draw grids within the emphysema region respectively. When the drawn grid touches the edge, perform refinement processing on the grid;

[0023] When the number of grids is greater than or equal to the first preset number, stop the refinement processing, and determine the sum of the areas of each grid as the first grid area of the edge of the emphysema region;

[0024] Perform the same grid processing on the small airway lesion region as on the emphysema region to obtain the second grid area of the small airway lesion region.

[0025] Optionally, the identifying the emphysema region and the small airway lesion region of the single lung lobe image includes:

[0026] Extract the lung parenchyma of the single lung lobe image;

[0027] Based on the lung parenchyma, determine the emphysema region and the small airway lesion region.

[0028] Optionally, determining the predicted development stage of emphysema based on the detected emphysema stage and the ratio includes:

[0029] Optionally, if the ratio is greater than a preset threshold, determine the predicted development stage of emphysema as the next stage of the detected emphysema stage;

[0030] If the ratio is less than or equal to the preset threshold, determine the predicted development stage of emphysema as the previous stage of the detected emphysema stage; wherein, the previous stage is more severe than the detected emphysema stage.

[0031] Optionally, obtaining a single lung lobe image of the left lung or the right lung includes:

[0032] Obtain a lung image;

[0033] Perform segmentation processing on the lung image to obtain a lung lobe segmentation image;

[0034] Extract the single lung lobe image from the lung lobe segmentation image.

[0035] In a second aspect, an emphysema disease prediction device provided by the present invention, the emphysema disease prediction device includes:

[0036] An acquisition module, configured to acquire a single lung lobe image of the left lung or the right lung;

[0037] An identification module, configured to identify the emphysema region and the small airway lesion region of the single lung lobe image;

[0038] A first determination module, configured to determine the emphysema stage detected based on the single lung lobe image, and determine the ratio of the emphysema region to the small airway lesion region;

[0039] A second determination module, configured to determine the predicted development stage of emphysema based on the detected emphysema stage and the ratio.

[0040] Optionally, the first determination module includes:

[0041] A first determination unit, configured to determine the volume of the emphysema region and the volume of the small airway lesion region respectively according to the emphysema region and the small airway lesion region;

[0042] A second determination unit, configured to determine the ratio of the emphysema region to the small airway lesion region based on the volume of the emphysema region and the volume of the small airway lesion region.

[0043] Optionally, the first determination unit is specifically configured to determine the number of layers, the scan slice thickness, and the slice interval of the single lung lobe image;

[0044] Perform grid processing on the emphysema region and the small airway lesion region respectively to obtain the first grid area of the emphysema region and the second grid area of the small airway lesion region;

[0045] Based on the number of layers, the scan slice thickness, the slice interval, and the first grid area, determine the volume of the emphysema region;

[0046] Based on the number of layers, the scan slice thickness, the slice interval, and the second grid area, determine the volume of the small airway lesion region.

[0047] Optionally, the first determination unit is specifically further configured to determine the edge of the emphysema region;

[0048] Draw grids within the emphysema region respectively. When the drawn grid touches the edge, perform refinement processing on the grid;

[0049] When the number of grids is greater than or equal to the first preset number, stop the refinement processing, and determine the sum of the areas of each grid as the first grid area of the edge of the emphysema region;

[0050] Perform the same grid processing on the small airway lesion region as on the emphysema region to obtain the second grid area of the small airway lesion region.

[0051] Optionally, the recognition unit is configured to extract the lung parenchyma of the single lung lobe image; and based on the lung parenchyma, determine the emphysema region and the small airway lesion region.

[0052] Optionally, the second determination module is specifically configured to, if the ratio is greater than the preset threshold, determine the predicted development level of emphysema as the next level of the detected emphysema level;

[0053] If the ratio is less than or equal to the preset threshold, determine the predicted development level of emphysema as the previous level of the detected emphysema level; wherein, the previous level is more severe than the detected emphysema level.

[0054] Optionally, the acquisition module is specifically configured to acquire a lung image; perform segmentation processing on the lung image to obtain a lung lobe segmentation image; and extract the single lung lobe image from the lung lobe segmentation image.

[0055] In a third aspect, the present invention further provides an emphysema disease prediction device, where the emphysema disease prediction device includes: a memory, a processor, and an emphysema disease prediction program stored on the memory and executable on the processor, and the emphysema disease prediction program is executed by the processor to perform the steps of the emphysema disease prediction method.

[0056] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which an emphysema disease prediction program is stored. When the emphysema disease prediction program is executed by a processor, the steps of the above-mentioned emphysema disease prediction method are implemented.

[0057] Compared with the prior art which cannot predict the development trend of emphysema in the left or right lung, for the emphysema disease prediction method, device, equipment and storage medium provided by the present invention, after obtaining a single lung lobe image of the left or right lung, it is possible to identify the emphysema area and the small airway lesion area of the single lung lobe image; determine the emphysema grade detected based on the single lung lobe image, and determine the ratio of the emphysema area to the small airway lesion area; and based on the detected emphysema grade and the ratio, determine the predicted development grade of emphysema, that is, the development direction of emphysema disease can be predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a schematic structural diagram of the hardware operating environment involved in the embodiment solution of the present invention;

[0059] Figure 2 is a schematic flowchart of a method for predicting emphysema disease according to an embodiment of the present invention;

[0060] Figure 3 is a functional schematic diagram module diagram of a preferred embodiment of the emphysema disease prediction device of the present invention.

[0061] The implementation, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0063] As Figure 1 shown, Figure 1 is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment solution of the present invention.

[0064] It should be noted that the emphysema disease prediction method provided by the embodiments of the present invention can be used to improve the detection efficiency and accuracy of the emphysema grade. The execution subject of this method can be any emphysema disease prediction device. For example, the emphysema disease prediction method can be executed by a terminal device, a server, or other processing devices. Among them, the terminal device can be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc., and no specific limitation is made here.

[0065] As Figure 1 shown, the emphysema disease prediction device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the foregoing processor 1001.

[0066] Those skilled in the art can understand that Figure 1 the device structure shown in

[0067] does not constitute a limitation on the emphysema disease prediction device, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. Figure 1 shown, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an emphysema disease prediction program. Among them, the operating system is a program for managing and controlling the hardware and software resources of the device, and supports the operation of the emphysema disease prediction program and other software or programs.

[0068] In Figure 1 the device shown, the user interface 1003 is mainly used for data communication with the client; the network interface 1004 is mainly used for establishing a communication connection with the server; and the processor 1001 may be used to call the emphysema disease prediction program stored in the memory 1005 and execute the emphysema disease prediction method of the embodiments of the present invention.

[0069] To achieve the invention objective of predicting the development trend of emphysema disease, an embodiment of the present invention provides a method for predicting emphysema disease, as Figure 2 shown, including.

[0070] S10: Obtain a single lung lobe image of the left lung or the right lung;

[0071] S20: Identify the emphysema region and the small airway lesion region of the single lung lobe image;

[0072] S30: Determine the emphysema grade detected based on the single lung lobe image, and determine the ratio of the emphysema region and the small airway lesion region;

[0073] S40: Based on the detected emphysema grade and the ratio, determine the predicted development grade of emphysema.

[0074] In some possible implementation manners, the lung image of the embodiment of the present invention can be obtained by taking a CT (Computed Tomography) scan. Among them, if the single lung lobe image is of the left lung, the single lung lobe image can be the left upper lobe or the left lower lobe. If the single lung lobe image is of the right lung, the single lung lobe image can be the right upper lobe, the right middle lobe, or the right lower lobe.

[0075] It should be noted that, in order to obtain a single lung lobe image of the left lung or the right lung, the method includes: obtaining a lung image; performing segmentation processing on the lung image to obtain a lung lobe segmentation image; and extracting the single lung lobe image from the lung lobe segmentation image. Specifically, obtain a lung CT image, and the CT image includes: a full-inspiration-phase lung image and a full-expiration-phase lung image. Respectively perform segmentation or extraction on the full-inspiration-phase lung image and the full-expiration-phase lung image to obtain a first left lung segmentation image and a first right lung segmentation image, and a second left lung segmentation image and a second right lung segmentation image; among them, the left lung image includes: the first left lung segmentation image and the second left lung segmentation image; among them, the right lung image includes: the first right lung segmentation image and the second right lung segmentation image. That is to say, perform segmentation or extraction on the full-inspiration-phase lung image to obtain a first left lung segmentation image and a first right lung segmentation image; perform segmentation or extraction on the full-expiration-phase lung image to obtain a second left lung segmentation image and a second right lung segmentation image. The first left lung segmentation image and the second left lung segmentation image are respectively the left lung segmentation images in the full-inspiration phase and the full-expiration phase. The first right lung segmentation image and the second right lung segmentation image are respectively the right lung segmentation images in the full-inspiration phase and the full-expiration phase.

[0076] In an embodiment of the present invention, in order to identify the emphysema region and the small airway lesion region of the single lung lobe image, the step S20 includes: extracting the lung parenchyma of the single lung lobe image; and determining the emphysema region and the small airway lesion region based on the lung parenchyma.

[0077] Specifically, the left lung parenchyma of the left lung image or the right lung parenchyma of the right lung image can be extracted; then the emphysema region and the small airway lesion region of the left lung are determined in the left lung parenchyma respectively, or the emphysema region and the small airway lesion region of the right lung are determined in the right lung parenchyma. In an embodiment of the present invention, the purpose of extracting the left lung parenchyma of the left lung image and the right lung parenchyma of the right lung image is to remove the trachea and blood vessels of the left lung image and the right lung image, so as to ensure the accuracy of emphysema disease prediction.

[0078] In an embodiment of the present invention, the emphysema region and the small airway lesion region are not easily determined on the image, especially the small airway lesion region, which is not obvious in imaging. The method for identifying the emphysema region of the left lung image and the right lung image is: judging whether the CT value on the lung lobe is the emphysema region according to the CT value of the first left lung segmentation image and the second left lung segmentation image and the set threshold value of emphysema. The set threshold value of emphysema is a set CT value. Since the CT value of the emphysema region basically does not change during deep inspiration, while other normal regions (non-emphysema regions) take in air, and the CT value of air is 1024 HU, and the CT of the emphysema region is close to 1024 HU because it is filled with air. In the medical field, the set threshold value of emphysema is generally selected as -950 HU. If the CT value of the lung lobe is less than -950 HU, it is judged as the emphysema region; if the CT value of the lung lobe is greater than or equal to -950 HU, it is judged as not the emphysema region. In other published papers or in some possible implementation manners, the set threshold value may fluctuate, and the present invention does not specifically limit the set threshold value, and those skilled in the art can appropriately adjust the set threshold value of emphysema.

[0079] In an embodiment of the present invention, the method for identifying the small airway lesion region of the left lung image and the right lung image is: identifying the small airway lesion region of the left lung image and the right lung image requires the full inspiration-phase lung image and the full expiration-phase lung image. The method for identifying the small airway lesion region of the left lung image and the right lung image is: obtaining the first left lung segmentation image and the first right lung segmentation image and the second left lung segmentation image and the second right lung segmentation image after segmentation of the full inspiration-phase lung image and the full expiration-phase lung image.

[0080] The method for identifying the small airway lesion area in the left lung image is as follows: registering the first left lung segmentation image of the full inspiration-phase lung image and the second left lung segmentation image of the full expiration-phase lung image. Comparing the registered first left lung segmentation image and the registered second left lung segmentation image with the inspiration-phase set threshold and the expiration-phase set threshold respectively; if the CT value of the registered first left lung segmentation image of the full inspiration-phase lung image is less than the inspiration-phase set threshold and the CT value of the registered second left lung segmentation image of the full expiration-phase lung image is less than the expiration-phase set threshold, it is considered that there is a small airway lesion in this area, and this area is the small airway lesion area; otherwise, it is considered that there is no small airway lesion in this area, and this area is not the small airway lesion area.

[0081] The method for identifying the small airway lesion area in the right lung image is as follows: registering the first right lung segmentation image of the full inspiration-phase lung image and the second right lung segmentation image of the full expiration-phase lung image. Comparing the registered first right lung segmentation image and the registered second right lung segmentation image with the inspiration-phase set threshold and the expiration-phase set threshold respectively; if the CT value of the registered first right lung segmentation image of the full inspiration-phase lung image is less than the inspiration-phase set threshold and the CT value of the registered second right lung segmentation image of the full expiration-phase lung image is less than the expiration-phase set threshold, it is considered that there is a small airway lesion in this area, and this area is the small airway lesion area; otherwise, it is considered that there is no small airway lesion in this area, and this area is not the small airway lesion area.

[0082] In the embodiment of the present invention, the full inspiration-phase lung image and the full expiration-phase lung image are the lung images of a patient. The full inspiration-phase lung image is the lung image taken by using an imaging device when the patient takes a deep breath and keeps the lung air volume at the maximum. Similarly, the full expiration-phase lung image is the lung image taken by using an imaging device when the patient takes a deep breath and keeps the lung air volume at the minimum. The full inspiration-phase lung image and the full expiration-phase lung image can be obtained by a radiologist in a hospital with the help of an imaging device (such as, CT).

[0083] It should be noted that the algorithm for registering the first left lung segmentation image of the full inspiration-phase lung image and the second left lung segmentation image of the full expiration-phase lung image can use an elastic registration algorithm or use the VGG network (VGG-net) in deep learning for registration. The embodiment of the present invention does not limit the specific registration algorithm.

[0084] In the embodiments of the present invention, the set threshold for the inhalation phase can be set to -950 HU, and the set threshold for the exhalation phase can be set to -856 HU. In other published papers or in some possible embodiments, the set threshold for the inhalation phase and the set threshold for the exhalation phase may fluctuate. The present invention does not specifically limit the set threshold, and those skilled in the art can appropriately adjust the set threshold for the inhalation phase and the set threshold for the exhalation phase.

[0085] In the embodiments of the present invention, according to the Global Initiative for Chronic Obstructive Lung Disease (COPD) (Emphysema), the emphysema grades include: GOLD 0 (none), GOLD 1 (mild), GOLD 2 (moderate), GOLD 3 (severe), and GOLD 4 (very severe). Through the above configuration, the emphysema grades of the left lung image and the right lung image can be determined. Specifically, a neural network can be used to determine the emphysema grades of the left lung image and the right lung image. For example, the left lung image and the right lung image can be input into the neural network, and through the processing of the neural network, the current grades of the left lung image and the right lung image can be classified and detected. Among them, the neural network can include a convolutional neural network. For example, it can perform feature extraction of the left lung image and the right lung image (for example, implemented through a residual network), and after obtaining the lung lobe features, the detection of the grades corresponding to the lung lobe features can be performed through a classification network (multi-classifier).

[0086] That is, for step S30, the method for determining the emphysema grade detected based on the single lung lobe image includes: inputting the single lung lobe image into a preset neural network, extracting image features through the residual network of the preset neural network, and determining the emphysema grade detected based on the single lung lobe image according to the classification network of the preset neural network.

[0087] In the embodiments of the present invention, the emphysema grade detected based on the single lung lobe image can also be determined in the following way, including: determining the volume of the emphysema region of the single lung lobe image and the total volume of the single lung lobe image, and determining the emphysema grade of the single lung lobe image according to the ratio of the volume of the emphysema region of the single lung lobe image to the total volume of the single lung lobe image. Specifically, it includes: determining the volume of the emphysema region of the left lung image and the total volume of the left lung image, and determining the emphysema grade of the left lung image according to the ratio of the volume of the emphysema region of the left lung image to the total volume of the left lung image; or determining the volume of the emphysema region of the right lung image and the total volume of the right lung image, and determining the grade of the right lung image according to the ratio of the volume of the emphysema region of the right lung image to the total volume of the right lung image.

[0088] Here, taking the determination of the emphysema grade of the left lung image as an example, for instance, four thresholds are set, namely the first threshold, the second threshold, the third threshold, and the fourth threshold. If the ratio of the volume of the emphysema region in the left lung image to the total volume of the left lung image is less than the first threshold, the emphysema grade is GOLD 0 (nonexistent); if the ratio of the volume of the emphysema region in the left lung image to the total volume of the left lung image is between the first threshold and the second threshold, the emphysema grade is GOLD 1 (mild); if the ratio of the volume of the emphysema region in the left lung image to the total volume of the left lung image is between the second threshold and the third threshold, the emphysema grade is GOLD 2 (moderate); if the ratio of the volume of the emphysema region in the left lung image to the total volume of the left lung image is between the third threshold and the fourth threshold, the emphysema grade is GOLD 3 (severe); if the ratio of the volume of the emphysema region in the left lung image to the total volume of the left lung image is greater than the fourth threshold, the emphysema grade is GOLD 4 (very severe). Among them, the first threshold, the second threshold, the third threshold, and the fourth threshold can be 20%, 30%, 50%, and 80% respectively. To determine the emphysema grade of the right lung image, it can be determined in detail with reference to the above method for determining the emphysema grade of the left lung image, and the first threshold, the second threshold, the third threshold, and the fourth threshold can be the same as the above thresholds.

[0089] In an embodiment of the present invention, for step S30, the determination of the ratio of the emphysema region to the small airway lesion region includes: determining the volume of the emphysema region and the volume of the small airway lesion region according to the emphysema region and the small airway lesion region respectively; based on the volume of the emphysema region and the volume of the small airway lesion region, determining the ratio of the emphysema region to the small airway lesion region.

[0090] It should be noted that the determination of the volume of the emphysema region and the volume of the small airway lesion region according to the emphysema region and the small airway lesion region respectively includes: determining the number of layers, the scan slice thickness, and the slice interval of the single lung lobe image; performing grid processing on the emphysema region and the small airway lesion region respectively to obtain the first grid area of the emphysema region and the second grid area of the small airway lesion region; based on the number of layers, the scan slice thickness, the slice interval, and the first grid area, determining the volume of the emphysema region; based on the number of layers, the scan slice thickness, the slice interval, and the second grid area, determining the volume of the small airway lesion region.

[0091] Specifically, the single lung lobe image of the left lung includes: the full inspiration phase lung image of the left lung or the full expiration phase lung image of the left lung. Determining the volume of the emphysema region and the volume of the small airway lesion region according to the emphysema region and the small airway lesion region respectively includes: determining the number of layers, scan slice thickness, and slice interval of the full inspiration phase lung image of the left lung or the full expiration phase lung image of the left lung; performing grid processing on the emphysema region of each layer of the left lung and the small airway lesion region of each layer of the left lung to obtain the grid area of the emphysema region of each layer of the left lung and the grid area of the small airway lesion region of each layer of the left lung, and respectively determining the volume of the emphysema region of the left lung and the volume of the small airway lesion region of the left lung according to the grid area of the emphysema region of each layer of the left lung, the grid area of the small airway lesion region, the number of layers, the scan slice thickness, and the slice interval.

[0092] Alternatively, the single lung lobe image of the right lung includes: the full inspiration phase lung image of the right lung or the full expiration phase lung image of the right lung. Determining the volume of the emphysema region and the volume of the small airway lesion region according to the emphysema region and the small airway lesion region respectively includes: determining the number of layers, scan slice thickness, and slice interval of the full inspiration phase lung image of the right lung or the full expiration phase lung image of the right lung; performing grid processing on the emphysema region of each layer of the right lung and the small airway lesion region of each layer of the right lung to obtain the grid area of the emphysema region of each layer of the right lung and the grid area of the small airway lesion region of each layer of the right lung, and respectively determining the volume of the emphysema region of the right lung and the volume of the small airway lesion region of the right lung according to the grid area of the emphysema region of each layer of the left lung, the grid area of the small airway lesion region, the number of layers, the scan slice thickness, and the slice interval. Among them, the number of layers, scan slice thickness, and slice interval of the full inspiration phase lung image and the full expiration phase lung image are the same.

[0093] In an embodiment of the present invention, performing grid processing on the emphysema region and the small airway lesion region respectively to obtain the first grid area of the emphysema region and the second grid area of the small airway lesion region includes: determining the edge of the emphysema region; respectively drawing grids within the emphysema region, and when the drawn grid touches the edge, performing refinement processing on the grid; when the number of grids is greater than or equal to the first preset number, stop the refinement processing, and determine the sum of the areas of each grid as the first grid area of the edge of the emphysema region; performing the same grid processing on the small airway lesion region as on the emphysema region to obtain the second grid area of the small airway lesion region.

[0094] It should be noted that when drawing a grid within the emphysema region, when the drawn grid touches the edge, the grid is refined, including: drawing a grid of a first specification shape within the emphysema region and extending the first specification shape grid towards the edge; when several set points of the first specification shape grid touch the edge, stop extending the first specification shape grid and generate a second specification shape grid outside the first specification shape grid, where several set points and the area of the second specification shape region are respectively smaller than those of the first specification shape region; perform the extension process towards the edge on the second specification shape grid.

[0095] For example, if the first specification shape is selected as a circle, several set points can be evenly set on the circumference of the circle, such as 20 set points. When several set points of the first specification shape touch the edge of the small airway lesion region, the first specification shape stops extending and a second specification shape is generated outside the specification shape; the second specification shape can also be selected from any one of a circle, an ellipse, a rectangle, and a square, but the second specification shape should be smaller than the first specification shape to achieve the purpose of fine division. For the setting of the value of the set quantity, those skilled in the art can set it by themselves according to the accuracy requirements.

[0096] Specifically, the emphysema region of each layer of the left lung or the right lung can be meshed to obtain the first grid area of the emphysema region of each layer of the left lung or the right lung, and the small airway lesion region of each layer of the left lung or the right lung is meshed to obtain the second grid area of the small airway lesion region of each layer of the left lung or the right lung. The meshing of the emphysema region of each layer of the left lung or the right lung to obtain the first grid area of the emphysema region of each layer of the left lung or the right lung includes: Step 1: Determine the edges of the emphysema region of each layer of the left lung or the right lung respectively; determine a first specification shape region within the emphysema region of each layer of the left lung or the right lung respectively; Step 2: Extend the first specification shape towards the edge of the emphysema region of each layer of the left lung or the right lung; Step 3: When several set points of the specification shape touch the edge of the emphysema region of each layer of the left lung or the right lung, stop extending the first specification shape and generate a second specification shape outside the specification shape; generate in sequence according to Step 2 and Step 3 until the number of specification shapes reaches the set quantity, and then calculate the areas of all specification shapes to obtain the first grid area of the emphysema region of each layer of the left lung or the right lung; where the specification shape, the second specification shape, and the area of the specification shape corresponding to the set quantity decrease in sequence. Similarly, the method of obtaining the first network area of each layer can be used to mesh the small airway lesion region of each layer of the left lung or the right lung to obtain the second grid area of the small airway lesion region of each layer of the left lung or the right lung.

[0097] For the embodiments of the present invention, in order to ensure the accuracy of the first grid area of the emphysema region, the first regular-shaped grid may be drawn starting from the geometric center of the emphysema region, that is, the first regular-shaped grid is located at the geometric center of the emphysema region. Before drawing the first regular-shaped grid within the emphysema region, the method further includes: obtaining a plurality of reference points set within the emphysema region; calculating the respective distances from each reference point to the edge; and determining the geometric center of the emphysema region based on the plurality of distances. Similarly, a grid may be drawn starting from the geometric center of the small airway lesion region, and the geometric center of the small airway lesion region may be determined.

[0098] In the embodiments of the present invention, the specific method for respectively calculating the distances from the plurality of points to the edge to obtain the respective distances from each point to the edge is as follows: respectively centering on the plurality of points, emitting in the form of a plurality of rays towards the edge, and making a plurality of marks when the plurality of rays reach the edge or intersect with the edge. The distances between the plurality of points and the plurality of marks are the respective distances from each point to the edge. Among them, the plurality of rays may be equally spaced or non-equally spaced.

[0099] For example, the plurality of points are 10 points, and the positions of the 10 points are within the emphysema region. Calculate the distances from the 10 points as the centers respectively, emitting in the form of a plurality of rays (100 rays) towards the edge, and making a plurality of marks (100 marks) when the plurality of rays reach the edge or intersect with the edge; the distances between each point and the plurality of marks are the respective distances from each point to the edge.

[0100] Specifically, a certain point is defined as OX, where X represents the nth point, and X = 1 represents the first point among the 10 points. A certain point emits in the form of 100 rays towards the edge. At this time, the number of the plurality of marks is 100, which are respectively X1 to X100; the number of distances from a certain point OX to X1 to X100 on the edge is 100, and the geometric center of the small airway lesion region is determined based on the 100 distances of each of the 10 points respectively.

[0101] It should be noted that in the embodiments of the present invention, the method for determining the geometric center of the emphysema region is the same as the method for determining the geometric center of the small airway lesion region. The method for determining the geometric center of the emphysema region is taken as an example for illustration.

[0102] Determining the geometric center of the pulmonary emphysema region based on the several distances includes: calculating the differences between the several distances respectively; counting the number of distance differences corresponding to each reference point that are less than a preset threshold; and determining the position where the number of reference points is greater than or equal to a preset number as the geometric center of the pulmonary emphysema region. Specifically, calculate the differences between the several distances from each point to the edge respectively; compare the differences between the several distances of a certain point with a set value, and if the difference is less than the set value, accumulate it; when the accumulated number is greater than or equal to the preset number, the position of the certain point is the geometric center of the small airway lesion region.

[0103] For example, taking one of the several points as an example, 100 rays centered on this point are emitted towards the edge, and the number of distances from this point to the edge is 100. Calculate the differences between the 100 distances, compare each difference with the set value, and if the difference is less than the set value, accumulate it; when the accumulated number is greater than or equal to the preset number, the position of this point is the geometric center of the pulmonary emphysema region. For the setting of the set value and the preset number, those skilled in the art can set them according to the number of distances from the point to the edge and the accuracy requirements. For example, the set value can be 0.5 - 1 mm; when the number of distances from the point to the edge is 100, the preset number can be 80.

[0104] In an embodiment of the present invention, if the positions of multiple points (such as 2 points) are all determined as the geometric center of the pulmonary emphysema region, then compare the accumulated numbers of the multiple points, and the one with the larger accumulated number is the geometric center of the small airway lesion region.

[0105] If there are multiple points such as 2 points, which are the first point and the second point respectively, and if the positions of the first point and the second point are both determined as the geometric center of the pulmonary emphysema region, then compare the accumulated number of the first point and the accumulated number of the second point. For example, if the accumulated number of the first point is greater than the accumulated number of the second point, the position of the first point is the geometric center of the pulmonary emphysema region.

[0106] In an embodiment of the present invention, the specific method for determining the geometric center of the small airway lesion region according to the several distances from each point to the edge is: calculating the differences between the several distances from each point to the edge respectively; comparing the differences between the several distances of a certain point with a set value, and if the difference is less than the set value, accumulate it; when the accumulated number is greater than or equal to the preset number, the position of the certain point is the geometric center of the pulmonary emphysema region.

[0107] In some other embodiments of the present invention, the method for determining the geometric center of the emphysema region may also be as follows: reducing the edge of the emphysema region according to a first preset scale to obtain a first edge; selecting a plurality of first reference points on the first edge, and fitting a first circle by using the first reference points; in response to the radius of the first circle being greater than a radius threshold, reducing the first edge according to a second preset scale until the radius of the circle formed by a plurality of second reference points selected on the reduced edge is less than the radius threshold; determining the geometric center of the small airway lesion region by using the position mean value of the plurality of second reference points or the center of the circle formed by the second reference points. The first preset scale is greater than the second preset scale. For example, the first preset scale may be 80%, and the second preset scale may be 10%, but this is not a specific limitation of the embodiments of the present invention.

[0108] That is to say, in the embodiments of the present invention, when the emphysema region is determined, the edge of the emphysema region can be determined to form the edge. Then, the edge can be reduced according to the first preset scale to obtain a first edge. Then, a plurality of first reference points can be selected from the first edge according to a first rule. Among them, the edge of the emphysema region can be regarded as composed of multiple points, and the corresponding first edge can also include multiple points. The first rule may include selecting a plurality of first reference points according to a preset interval number of points. For example, the preset interval number of points may be 10, then one first reference point can be selected every 10 points on the first edge, and the preset interval number of points is not specifically limited. After the first reference points are selected, curve fitting can be performed on the first reference points to form a first circle, and then the radius of the first circle can be determined. The method of curve fitting may be the least squares method, but this is not a limitation of the present invention. If the radius of the first circle is less than or equal to the radius threshold, the center of the first circle can be used as the geometric center of the small airway lesion region, or the mean position of the first reference points can also be determined as the geometric center of the small airway lesion region.

[0109] If the radius of the first circle is greater than the radius threshold, it means that the first edge needs to be further reduced to reduce the error. At this time, it can be reduced according to the second preset scale, and the second preset scale is less than the first preset scale. When reducing the first edge to form a second edge (at least one), a plurality of second reference points can be selected on the second edge, and a circle (second circle) can also be fitted by using the second reference points, and it can be judged whether the second edge needs to be reduced according to the above rules. If the radius of the second circle fitted by the second reference points is greater than the radius threshold, the second edge is further reduced according to the second preset scale. On the contrary, if the radius of the second circle is less than or equal to the radius threshold, the center of the second circle or the mean position of the second reference points can be determined as the geometric center of the emphysema region.

[0110] In an embodiment of the present invention, determining the volume of the small airway lesion area based on the number of layers, the scanning slice thickness, the slice interval, and the grid area includes: obtaining the sub-volume formed by the small airway lesion areas of two adjacent layers by using the grid areas of the small airway lesion areas of two adjacent layers, the scanning slice thickness, and the slice interval; and calculating the sum of the sub-volumes corresponding to the number of layers to obtain the volume of the small airway lesion area.

[0111] Specifically, the sub-volume formed by the small airway lesion areas of two adjacent layers is obtained by using the grid areas corresponding to the small airway lesion areas of each two adjacent layers, the slice interval, and the slice thickness, and the volume of the small airway lesion area is obtained by using the sum of the sub-volumes formed by all the adjacent two-layer small airway lesion areas. Among them, the structure formed by two adjacent layers that satisfy the lung area can be regarded as a frustum of a pyramid. The areas of the upper and lower bottom surfaces of the frustum of the pyramid are the grid areas corresponding to the small airway lesion areas, and the height of the frustum of the pyramid can be determined by the slice interval and the slice thickness. For example, when the number of layers is N, the height of the frustum of the pyramid formed by the small airway lesion areas of the first layer and the second layer can be the sum value between 2 times the slice thickness and the slice interval, and the height of the frustum of the pyramid formed by the small airway lesion areas of the remaining adjacent two layers can be the sum value between the slice thickness and the slice interval. Based on the areas of the upper and lower bottom surfaces and the height, the sub-volume of the small airway lesion area formed by adjacent layers can be determined. Then, the volume of the small airway lesion area can be obtained by using the sum value of each sub-volume. That is to say, since there may be multiple small airway lesion areas, the volume of the small airway lesion area is the total volume of all small airway lesion areas.

[0112] Similarly, the method for determining the volume of the emphysema area based on the number of layers, the scanning slice thickness, the slice interval, and the first grid area is the same as the method for determining the volume of the small airway lesion area, and the embodiments of the present invention will not be elaborated herein.

[0113] For the embodiment of the present invention, in step S40, determining the predicted development grade of emphysema based on the detected emphysema grade and the ratio includes: if the ratio is greater than a preset threshold, determining the predicted development grade of emphysema as the next grade of the detected emphysema grade; if the ratio is less than or equal to the preset threshold, determining the predicted development grade of emphysema as the previous grade of the detected emphysema grade; where the previous grade is more severe than the detected emphysema grade.

[0114] For example, in the left lung, based on image detection, the emphysema grade is GOLD 2 (moderate). The ratio obtained by dividing the volume of the emphysema area in the left lung by the volume of the small airway lesion area in the left lung is less than or equal to the preset threshold, indicating that although the emphysema area in the left lung is small, the small airway lesion area is large, and the possibility of the small airway lesion area transforming into the emphysema area is high. The emphysema grade of the left lung can be predicted to the previous grade GOLD 3 (severe). If the ratio is greater than the preset threshold, it is considered that drug treatment can be carried out, and the emphysema grade of the left lung can be predicted to the next grade GOLD 1 (mild). Among them, the preset threshold can be 0.4.

[0115] In addition, an emphysema disease prediction device is also proposed in an embodiment of the present invention. Referring to Figure 3 , the emphysema disease prediction device includes:

[0116] An acquisition module 10, configured to acquire a single lung lobe image of the left lung or the right lung;

[0117] An identification module 20, configured to identify the emphysema area and the small airway lesion area in the single lung lobe image;

[0118] A first determination module 30, configured to determine the emphysema grade detected based on the single lung lobe image, and determine the ratio of the emphysema area to the small airway lesion area;

[0119] A second determination module 40, configured to determine the predicted development grade of the emphysema based on the detected emphysema grade and the ratio.

[0120] Optionally, the first determination module 10 includes:

[0121] A first determination unit, configured to determine the volume of the emphysema area and the volume of the small airway lesion area according to the emphysema area and the small airway lesion area respectively;

[0122] A second determination unit, configured to determine the ratio of the emphysema area to the small airway lesion area based on the volume of the emphysema area and the volume of the small airway lesion area.

[0123] Optionally, the first determination unit is specifically configured to determine the number of layers, the scanning slice thickness, and the slice interval of the single lung lobe image;

[0124] Perform grid processing on the emphysema area and the small airway lesion area respectively to obtain a first grid area of the emphysema area and a second grid area of the small airway lesion area;

[0125] Determine the volume of the emphysema area based on the number of layers, the scanning slice thickness, the slice interval, and the first grid area;

[0126] Determine the volume of the small airway lesion area based on the number of layers, the scanning layer thickness, the layer spacing, and the second grid area.

[0127] Optionally, the first determination unit is further specifically configured to determine the edge of the emphysema area;

[0128] Draw grids within the emphysema area respectively, and when the drawn grid touches the edge, perform refinement processing on the grid;

[0129] When the number of grids is greater than or equal to the first preset number, stop the refinement processing, and determine the sum of the areas of each grid as the first meshed area of the edge of the emphysema area;

[0130] Perform the same meshing process on the small airway lesion area as on the emphysema area to obtain the second grid area of the small airway lesion area.

[0131] Optionally, the recognition unit is configured to extract the lung parenchyma of the single lung lobe image; and determine the emphysema area and the small airway lesion area based on the lung parenchyma.

[0132] Optionally, the second determination module 40 is specifically configured to, if the ratio is greater than a preset threshold, determine the predicted development level of emphysema as the next level of the detected emphysema level;

[0133] If the ratio is less than or equal to the preset threshold, determine the predicted development level of emphysema as the previous level of the detected emphysema level; where the previous level is more severe than the detected emphysema level.

[0134] Optionally, the acquisition module 10 is specifically configured to acquire a lung image; perform segmentation processing on the lung image to obtain a lung lobe segmentation image; and extract the single lung lobe image from the lung lobe segmentation image.

[0135] In addition, an embodiment of the present invention also provides a computer-readable storage medium, on which an emphysema disease prediction program is stored. When the emphysema disease prediction program is executed by a processor, the steps of the emphysema disease prediction method described below are implemented.

[0136] For each embodiment of the emphysema disease prediction device and the computer-readable storage medium of the present invention, reference can be made to each embodiment of the emphysema disease prediction method of the present invention, which will not be elaborated here.

[0137] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including such element.

[0138] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0139] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0140] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the description and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for predicting emphysema disease, characterized in that, it includes: Obtain a single lung lobe image of the left lung or the right lung; Identify the emphysema area and the small airway lesion area in the single lung lobe image; Determine the emphysema grade detected based on the single lung lobe image, and determine the ratio of the emphysema area to the small airway lesion area; Based on the detected emphysema grade and the ratio, determine the predicted development grade of emphysema; The determination of the ratio of the emphysema area to the small airway lesion area includes: Determine the number of layers, scan slice thickness, and slice interval of the single lung lobe image; Perform grid processing on the emphysema area and the small airway lesion area respectively to obtain the first grid area of the emphysema area and the second grid area of the small airway lesion area; Based on the number of layers, the scan slice thickness, the slice interval, and the first grid area, determine the volume of the emphysema area; Based on the number of layers, the scan slice thickness, the slice interval, and the second grid area, determine the volume of the small airway lesion area; Based on the volume of the emphysema area and the volume of the small airway lesion area, determine the ratio of the emphysema area to the small airway lesion area; The performing grid processing on the emphysema area and the small airway lesion area respectively to obtain the first grid area of the emphysema area and the second grid area of the small airway lesion area includes: Determine the edge of the emphysema area; Draw grids in the emphysema area respectively. When the drawn grid touches the edge, perform refinement processing on the grid; When the number of grids is greater than or equal to the first preset number, stop the refinement processing, and determine the sum of the areas of each grid as the first grid area of the emphysema area; Perform the same grid processing on the small airway lesion area as on the emphysema area to obtain the second grid area of the small airway lesion area; The determining the predicted development grade of emphysema based on the detected emphysema grade and the ratio includes: If the ratio is greater than the preset threshold, determine the predicted development grade of emphysema as the next grade of the detected emphysema grade; If the ratio is less than or equal to the preset threshold, determine the predicted development grade of emphysema as the previous grade of the detected emphysema grade; where the previous grade is more severe than the detected emphysema grade.

2. The method according to claim 1, characterized in that, the identifying the emphysema area and the small airway lesion area in the single lung lobe image includes: Extract the lung parenchyma of the single lung lobe image; Based on the lung parenchyma, determine the emphysema area and the small airway lesion area.

3. The method according to claim 1, characterized in that, the obtaining a single lung lobe image of the left lung or the right lung includes: Obtain a lung image; Perform segmentation processing on the lung image to obtain a lung lobe segmentation image; Extract the single lung lobe image from the lung lobe segmentation image.

4. An apparatus for predicting emphysema disease, characterized in that, the apparatus for predicting emphysema disease includes: An acquisition module for obtaining a single lung lobe image of the left lung or the right lung; An identification module, configured to identify the emphysema region and the small airway lesion region of the single lung lobe image; A first determination module, configured to determine the emphysema grade detected based on the single lung lobe image, and determine the ratio between the emphysema region and the small airway lesion region; A second determination module, configured to determine the predicted development grade of the emphysema based on the detected emphysema grade and the ratio; the second determination module is further configured to, if the ratio is greater than a preset threshold, determine the predicted development grade of the emphysema as the next grade of the detected emphysema grade; if the ratio is less than or equal to the preset threshold, determine the predicted development grade of the emphysema as the previous grade of the detected emphysema grade; wherein, the previous grade is more severe than the detected emphysema grade; The first determination module includes: A first determination unit, configured to determine the number of layers, the scan slice thickness, and the slice interval of the single lung lobe image; Perform grid processing on the emphysema region and the small airway lesion region respectively to obtain the first grid area of the emphysema region and the second grid area of the small airway lesion region; determine the volume of the emphysema region based on the number of layers, the scan slice thickness, the slice interval, and the first grid area; determine the volume of the small airway lesion region based on the number of layers, the scan slice thickness, the slice interval, and the second grid area; the first determination unit is further configured to determine the edge of the emphysema region; draw grids within the emphysema region respectively, and when the drawn grid touches the edge, perform refinement processing on the grid; when the number of grids is greater than or equal to a first preset number, stop the refinement processing, and determine the sum of the areas of each grid as the first grid area of the emphysema region; perform the same grid processing on the small airway lesion region as on the emphysema region to obtain the second grid area of the small airway lesion region; A second determination unit, configured to determine the ratio between the emphysema region and the small airway lesion region based on the volume of the emphysema region and the volume of the small airway lesion region.

5. An emphysema disease prediction device, Characterized in that, The emphysema disease prediction device includes: a memory, a processor, and an emphysema disease prediction program stored on the memory and executable on the processor, and when the emphysema disease prediction program is executed by the processor, the steps of the emphysema disease prediction method according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium, Characterized in that, An emphysema disease prediction program is stored on the computer-readable storage medium, and when the emphysema disease prediction program is executed by a processor, the steps of the emphysema disease prediction method according to any one of claims 1 to 3 are implemented.

Images