Image processing method, device, readable storage medium and electronic device

Abstract

The present disclosure relates to an image processing method, device, readable storage medium and electronic device. The method includes: extracting the main trachea region and the chest region from the target lung CT tomographic image sequence; determining the scanning position corresponding to the target lung CT tomographic image sequence according to the relative position of the main trachea region and the chest region. In this way, the scanning position can be quickly and automatically detected based on the relative position of the main trachea region and the chest region, avoiding the problem of time-consuming manual identification of the scanning position. In addition, since the entire process does not require human participation, human misjudgment can be effectively avoided, thereby ensuring the accuracy of the scanning position, and then the CT direction correction can be performed based on the scanning position, thereby improving the accuracy and convenience of the film reading and auxiliary diagnosis and treatment system.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular, to an image processing method, device, readable storage medium and electronic device. Background Art

[0002] With the rapid development of artificial intelligence technology in the medical field, more and more film reading and auxiliary diagnosis and treatment systems are being applied to lung CT images, which greatly improves the work efficiency of doctors, but also puts higher requirements on the input standards of lung CT images. In reality, due to the different lying directions of patients during lung CT scanning, that is, different scanning positions, the lung CT images appear upside down. In order to make the lung CT image meet the input standards, it is necessary to first determine the scanning position, and then correct the direction of the lung CT image based on the scanning position. Among them, at this stage, manual methods are often used to identify the scanning position corresponding to the lung CT image, which takes a long time. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides an image processing method, an apparatus, a readable storage medium and an electronic device.

[0004] In order to achieve the above objectives, in a first aspect, the present disclosure provides an image processing method, comprising:

[0005] Extracting the main trachea region and the thoracic cavity region from the target lung CT tomographic image sequence;

[0006] According to the relative positions of the main trachea region and the thoracic cavity region, a scanning position corresponding to the target lung CT tomographic image sequence is determined.

[0007] Optionally, extracting the main trachea region and the thoracic cavity region from the target lung CT tomographic image sequence includes:

[0008] Determining a scanning direction corresponding to the target lung CT tomographic image sequence;

[0009] Extracting the thoracic region in each tomographic image in the initial layer, wherein, when the scanning direction is from the neck to the abdomen, the initial layer includes the first M tomographic images of the target lung CT tomographic image sequence, and when the scanning direction is from the abdomen to the neck, the initial layer includes the last M tomographic images of the target lung CT tomographic image sequence;

[0010] Determine a main trachea candidate region from other regions in the initial layer except the thoracic region;

[0011] A main airway region is identified from the main airway candidate regions.

[0012] Optionally, determining the main trachea candidate region from other regions in the initial layer except the thoracic region includes:

[0013] The area in the other areas whose area is within the preset area range is determined as the main trachea candidate area.

[0014] Optionally, determining the scanning position corresponding to the target lung CT tomographic image sequence according to the relative positions of the main trachea region and the thoracic cavity region includes:

[0015] If the main trachea region is located in the upper half of the thoracic region, determining that the scanning position corresponding to the target lung CT tomographic image sequence is supine;

[0016] If the main trachea region is located in the lower half of the thoracic region, it is determined that the scanning position corresponding to the target lung CT tomographic image sequence is prone.

[0017] Optionally, the method further comprises:

[0018] If the scanning body position is prone, each slice image in the target lung CT slice image sequence is vertically mirror-flipped.

[0019] Optionally, the method further comprises:

[0020] Extracting a left lung region and a right lung region from the target lung CT tomographic image sequence;

[0021] According to the relative positions of the left lung region and the right lung region, it is determined whether there are left and right mirror images of the tomographic images in the target lung CT tomographic image sequence.

[0022] Optionally, extracting the left lung region and the right lung region from the target lung CT tomographic image sequence includes:

[0023] Performing three-dimensional reconstruction on the target lung CT tomographic image sequence to obtain a three-dimensional structure;

[0024] Extracting an intermediate layer including a lung parenchyma region from the three-dimensional structure, wherein the intermediate layer is parallel to a scanning direction corresponding to the target lung CT tomographic image sequence;

[0025] extracting two lung regions from the middle layer;

[0026] The one of the two lung regions with a larger ratio of the long and short axes is determined as the left lung region, and the one of the two lung regions with a smaller ratio of the long and short axes is determined as the right lung region.

[0027] Optionally, the method further comprises:

[0028] If the tomographic images in the target lung CT tomographic image sequence do not have left and right mirror images, each of the tomographic images in the target lung CT tomographic image sequence is horizontally mirror-flipped.

[0029] Optionally, the method further comprises:

[0030] Determining a scanning direction corresponding to the target lung CT tomographic image sequence;

[0031] If the scanning direction is from the abdomen to the neck, the target lung CT section image sequence is reversely sorted.

[0032] Optionally, determining the scanning direction corresponding to the target lung CT tomographic image sequence includes:

[0033] Extracting the chest area in the first image and the second image respectively, wherein the first image is one of the first N tomographic images in the target lung CT tomographic image sequence, and the second image is one of the last L tomographic images in the target lung CT tomographic image sequence;

[0034] The scanning direction corresponding to the target lung CT tomographic image sequence is determined according to the chest region in the first image and the chest region in the second image.

[0035] Optionally, determining the scanning direction corresponding to the target lung CT tomographic image sequence according to the chest region in the first image and the chest region in the second image includes:

[0036] Determine a first length of a minimum circumscribed rectangle of a chest region in the first image and a second length of a minimum circumscribed rectangle of a chest region in the second image;

[0037] If the first length is greater than the second length, determining that the scanning direction corresponding to the target lung CT tomographic image sequence is from the neck to the abdomen;

[0038] If the first length is smaller than the second length, it is determined that the scanning direction corresponding to the target lung CT section image sequence is from the abdomen to the neck.

[0039] In a second aspect, the present disclosure provides an image processing device, comprising:

[0040] A first extraction module is used to extract the main trachea area and the chest area from the target lung CT tomographic image sequence;

[0041] The first determination module is used to determine the scanning position corresponding to the target lung CT tomographic image sequence according to the relative positions of the main trachea area and the chest area extracted by the first extraction module.

[0042] In a third aspect, the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present disclosure.

[0043] In a fourth aspect, the present disclosure provides an electronic device, including:

[0044] a memory having a computer program stored thereon;

[0045] A processor is used to execute the computer program in the memory to implement the steps of the method provided in the first aspect of the present disclosure.

[0046] In the above technical solution, first, the main trachea region and the chest region are extracted from the target lung CT tomographic image sequence; then, according to the relative position of the main trachea region and the chest region, the scanning position corresponding to the target lung CT tomographic image sequence is determined. In this way, the scanning position can be quickly and automatically detected based on the relative position of the main trachea region and the chest region, avoiding the problem of time-consuming manual identification of the scanning position. In addition, since the entire process does not require human participation, human misjudgment can be effectively avoided, thereby ensuring the accuracy of the scanning position, and then the CT direction correction can be performed based on the scanning position, thereby improving the accuracy and convenience of the film reading and auxiliary diagnosis and treatment system.

[0047] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0049] Figure 1 The figure is a flowchart of an image processing method according to an exemplary embodiment.

[0050] Figure 2 is a flowchart of an image processing method according to another exemplary embodiment.

[0051] Figure 3 is a flowchart of an image processing method according to another exemplary embodiment.

[0052] Figure 4 is a flowchart of an image processing method according to another exemplary embodiment.

[0053] Figure 5 is a flowchart of an image processing method according to another exemplary embodiment.

[0054] Figure 6 is a block diagram of an image processing apparatus according to an exemplary embodiment.

[0055] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment.

[0056] Figure 8 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0057] As discussed in the background technology, currently, the scanning position corresponding to the lung CT image is often identified by manual methods, which takes a long time. Therefore, it is necessary to use a computer to automatically determine the scanning position. In existing studies, the scanning position is often determined by relying on the patient position field, but the field value of this field is usually manually annotated when scanning the lung CT, and there may be an error in the annotation. In this way, the accuracy of the scanning position is difficult to guarantee.

[0058] In view of this, the present disclosure provides an image processing method, an apparatus, a readable storage medium, and an electronic device.

[0059] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0060] Figure 1 FIG. 1 is a flowchart of an image processing method according to an exemplary embodiment. Figure 1 As shown, the method includes S101 and S102.

[0061] In S101 , the main trachea region and the chest cavity region are extracted from the target lung CT tomographic image sequence.

[0062] In the present disclosure, a human body may be scanned from the neck to the abdomen, or from the abdomen to the neck, to obtain a target lung CT tomographic image sequence.

[0063] In S102, the scanning position corresponding to the target lung CT tomographic image sequence is determined according to the relative positions of the main trachea region and the chest cavity region.

[0064] In the present disclosure, the scanning posture is the lying posture of the human body when scanning lung CT, which includes supine and prone. When the lying posture is supine, the main trachea is close to the upper chest cavity. Therefore, the lying posture of the human body (i.e., scanning posture) when scanning CT can be determined based on the relative position of the main trachea area and the chest cavity area.

[0065] Specifically, if the main trachea area is located in the upper half of the chest area, the scanning position corresponding to the target lung CT tomographic image sequence is determined to be supine; if the main trachea area is located in the lower half of the chest area, the scanning position corresponding to the target lung CT tomographic image sequence is determined to be prone.

[0066] In the above technical solution, first, the main trachea region and the chest region are extracted from the target lung CT tomographic image sequence; then, according to the relative position of the main trachea region and the chest region, the scanning position corresponding to the target lung CT tomographic image sequence is determined. In this way, the scanning position can be quickly and automatically detected based on the relative position of the main trachea region and the chest region, avoiding the problem of time-consuming manual identification of the scanning position. In addition, since the entire process does not require human participation, human misjudgment can be effectively avoided, thereby ensuring the accuracy of the scanning position, and then the CT direction correction can be performed based on the scanning position, thereby improving the accuracy and convenience of the film reading and auxiliary diagnosis and treatment system.

[0067] The following is a detailed description of the specific implementation method of extracting the main trachea region and the chest region from the target lung CT tomographic image sequence in the above S101. Specifically, it can be achieved by the following steps (1) to (4):

[0068] (1) Determine the scanning direction corresponding to the target lung CT image sequence.

[0069] In the present disclosure, the scanning direction includes from the neck to the abdomen and from the abdomen to the neck.

[0070] (2) Extract the chest area in each tomographic image in the initial layer.

[0071] Since the main trachea is close to the neck, in plain scan CT, the main trachea appears more clearly in a circular shape in the part close to the neck of the target lung CT tomographic image sequence. Therefore, the main trachea region and the chest region can be extracted based on the part close to the neck (i.e., the initial layer) of the target lung CT tomographic image sequence.

[0072] Specifically, when the scanning direction is from the neck to the abdomen, the main trachea appears more clearly in the front part of the target lung CT tomographic image sequence in a circular shape; when the scanning direction is from the abdomen to the neck, the main trachea appears more clearly in the back part of the target lung CT tomographic image sequence in a circular shape. Therefore, when the scanning direction is from the neck to the abdomen, the initial layer includes the first M tomographic images of the target lung CT tomographic image sequence; when the scanning direction is from the abdomen to the neck, the initial layer includes the last M tomographic images of the target lung CT tomographic image sequence.

[0073] (3) Determine the main trachea candidate region from other regions in the initial layer except the chest region.

[0074] In the present disclosure, the other regions in the initial layer except the thoracic region are lung parenchyma and other tissues (including the main trachea), and the other regions include multiple sub-regions such as lung parenchyma and the main trachea. The area of ​​the main trachea region in the tomographic image is usually within a preset area range (for example, 50mm 2 ~500mm 2 ), therefore, the sub-regions in other areas except the chest area in the initial layer and whose areas are within the preset area range can be determined as the main trachea candidate areas.

[0075] (4) Identify the main trachea region from the main trachea candidate regions.

[0076] Since the main trachea appears in a circular shape more obviously in the target lung CT tomographic image sequence near the neck in plain scan CT, the circular area in the main trachea candidate area can be determined as the main trachea area.

[0077] For example, Hough transform may be used to detect whether each main trachea candidate region is a circular region.

[0078] In addition, it should be noted that there may be one or more main trachea regions, that is, there may be one or more tomographic images containing the main trachea region in the initial layer.

[0079] In the case where there is only one tomographic image containing the main trachea region in the above initial layer, the scanning position corresponding to the target lung CT tomographic image sequence can be determined based on the relative position of the main trachea region and the chest region in the tomographic image containing the main trachea region. In the case where there are multiple tomographic images containing the main trachea region in the above initial layer, the scanning position corresponding to the target lung CT tomographic image sequence can be determined based on the relative position of the main trachea region and the chest region in any of the tomographic images containing the main trachea region.

[0080] The following is a detailed description of the specific implementation of determining the scanning direction corresponding to the target lung CT tomographic image sequence in the above step (1). Specifically, it can be achieved through the following steps (11) and (12).

[0081] (11) Extract the chest area in the first image and the second image respectively.

[0082] In the present disclosure, the first image is one of the first N tomographic images of the target lung CT tomographic image sequence, and the second image is one of the last L tomographic images of the target lung CT tomographic image sequence. For example, N=3, L=3, where N and L may be equal or unequal, and are not specifically limited in the present disclosure.

[0083] By way of example, the first image is the first tomographic image of a target lung CT tomographic image sequence; and the second image is the last image of the target lung CT tomographic image sequence.

[0084] As another example, the first image is the second tomographic image of the target lung CT tomographic image sequence; the second image is the penultimate image of the target lung CT tomographic image sequence.

[0085] As another example, the first image is the first tomographic image of a target lung CT tomographic image sequence; the second image is the penultimate image of the target lung CT tomographic image sequence.

[0086] (12) Determine a scanning direction corresponding to the target lung CT image sequence according to the chest region in the first image and the chest region in the second image.

[0087] The specific implementation of extracting the chest area in the first image and the second image respectively in the above step (11) is described in detail below.

[0088] In the present disclosure, a global threshold binary method can be used to extract the chest region in the first image and the second image respectively. Specifically, the chest region in the first image can be extracted by the following steps (111) to (115).

[0089] (111) Obtain the maximum value Tmax and the minimum value Tmin of the grayscale value of each pixel in the first image. At this time, the global threshold T=(Tmax+Tmin) / 2;

[0090] (112) According to the global threshold T, the first image is divided into foreground and background.

[0091] For example, pixels in the first image whose grayscale values ​​are greater than or equal to T are classified as foreground, and pixels in the first image whose grayscale values ​​are less than T are classified as background.

[0092] (113) Calculate the average grayscale value TF of the foreground and the average grayscale value TB of the background, and update the global threshold T = (TF + TB) / 2.

[0093] (114) Determine whether the global threshold obtained after the update is equal to the global threshold before the update.

[0094] If the global threshold obtained after the update is not equal to the global threshold before the update, then return to the above step (112) until the global threshold obtained after the update is equal to the global threshold before the update. If the global threshold obtained after the update is equal to the global threshold before the update, then execute the following step (115).

[0095] (115) According to the updated global threshold T, the first image is divided into a foreground and a background, and the maximum connected domain in the foreground of the first image is determined as the chest area in the first image.

[0096] In addition, the chest region in the second image may be extracted in a manner similar to that of extracting the chest region in the first image, which will not be described in detail in the present disclosure.

[0097] The following describes in detail the specific implementation of determining the scanning direction corresponding to the target lung CT image sequence based on the chest area in the first image and the chest area in the second image in the above step (12).

[0098] Since the width of the chest area where the lungs begin (i.e., the area of ​​the lungs near the neck) is larger than the width of the chest area where the lungs end (i.e., the area of ​​the lungs near the abdomen), the scanning direction corresponding to the target lung CT tomographic image sequence can be determined by comparing the width of the chest area where the lungs begin and the width of the chest area where the lungs end.

[0099] In one embodiment, the scanning direction corresponding to the target lung CT section image sequence can be determined by comparing the width of the chest region in any section image in the front part of the target lung CT section image sequence (i.e., the first image) with the width of the chest region in any section image in the back part (i.e., the second image).

[0100] Specifically, first, determine the first length of the minimum circumscribed rectangle of the chest area in the first image and the second length of the minimum circumscribed rectangle of the chest area in the second image; if the first length is greater than the second length, determine that the scanning direction corresponding to the target lung CT tomographic image sequence is from the neck to the abdomen; if the first length is less than the second length, determine that the scanning direction corresponding to the target lung CT tomographic image sequence is from the abdomen to the neck.

[0101] Preferably, the first image is the first image of a target lung CT tomographic image sequence, and the second image is the last image of the sequence. Since the first image and the second image are two tomographic images of the beginning and end of the lung, the width difference of the chest region in the two images is more obvious, and therefore, the accuracy of the scanning direction can be improved.

[0102] The following is a detailed description of the method for determining M in the above step (2). Specifically, it can be implemented in a variety of ways. In one implementation, M is a preset value, for example, 5.

[0103] In another embodiment, M may be determined based on the slice thickness of the tomographic image in the target lung CT tomographic image sequence. In this way, M may be adaptively determined based on the slice thickness of the tomographic image, thereby reducing the workload of chest region extraction and main trachea candidate region determination as much as possible, thereby improving the efficiency of determining the scanning position.

[0104] In the present disclosure, the layer thickness and M are negatively correlated.

[0105] For example, if the layer thickness is greater than 5 mm, then M=3; if the layer thickness is less than or equal to 5 mm, then M=5.

[0106] In addition, the above step (2) can extract the chest region in each tomographic image in the initial layer in a manner similar to the above-mentioned method of extracting the chest region in the first image, which will not be repeated in the present disclosure.

[0107] Figure 2 FIG. 1 is a flowchart of an image processing method according to another exemplary embodiment. Figure 2 As shown, the above method also includes the following S103.

[0108] In S103, if the scanning position is prone, each slice image in the target lung CT slice image sequence is vertically mirror-flipped.

[0109] In the present disclosure, if the scanning position is prone, it indicates that each tomographic image in the target lung CT tomographic image sequence is upside down. At this time, each tomographic image in the target lung CT tomographic image sequence can be vertically mirrored (i.e., flipped 180 degrees up and down); if the scanning position is supine, it indicates that each tomographic image in the target lung CT tomographic image sequence does not have the problem of being upside down. At this time, each tomographic image in the target lung CT tomographic image sequence is not flipped. In this way, the direction of the tomographic image in the target lung CT tomographic image sequence can be automatically corrected, thereby achieving the standardization of the target lung CT tomographic image sequence.

[0110] Due to the differences in CT scanning devices, some CT scanning devices have left and right mirror images, while others do not. In order to make the lung CT image meet the input standard, it is necessary to first determine whether the tomographic images in the target lung CT tomographic image sequence have left and right mirror images, and then perform direction correction on the lung CT image based on the determination result. Specifically, it can be done by Figure 3 S104 and S105 shown are used to determine whether there are left and right mirror images in the target lung CT tomographic image sequence.

[0111] In S104, a left lung region and a right lung region are extracted from the target lung CT sectional image sequence.

[0112] In S105, based on the relative positions of the left lung region and the right lung region, it is determined whether there are left and right mirror images of the tomographic images in the target lung CT tomographic image sequence.

[0113] Specifically, if the left lung region is located on the left side of the right lung region, it is determined that the tomographic images in the target lung CT tomographic image sequence have left and right mirror images; if the left lung region is located on the right side of the right lung region, it is determined that the tomographic images in the target lung CT tomographic image sequence do not have left and right mirror images.

[0114] The following is a detailed description of the specific implementation of extracting the left lung region and the right lung region from the target lung CT tomographic image sequence in S104. Specifically, it can be achieved by the following steps [1] to [4]:

[0115] [1] The target lung CT tomographic image sequence is reconstructed in three dimensions to obtain a three-dimensional structure.

[0116] In the present disclosure, when the slice thickness of the tomographic image in the target lung CT tomographic image sequence is greater than a preset threshold value (for example, 5 mm), the target lung CT tomographic image sequence can be interpolated to obtain sufficient data for constructing a three-dimensional structure, and then three-dimensional reconstruction is performed based on the target lung CT tomographic image sequence obtained after interpolation. When the slice thickness of the tomographic image in the target lung CT tomographic image sequence is less than a preset threshold value, it indicates that the amount of data contained in the current target lung CT tomographic image sequence is sufficient to construct a three-dimensional structure. At this time, three-dimensional reconstruction can be performed directly based on the target lung CT tomographic image sequence.

[0117] [2] The middle layer containing the lung parenchymal region is extracted from the three-dimensional structure.

[0118] In the present disclosure, the middle layer is parallel to the scanning direction corresponding to the target lung CT tomographic image sequence. Specifically, the three-dimensional structure can be divided into multiple layers along the above scanning direction, and then any layer containing the lung parenchyma area is selected from the multiple layers obtained by division as the middle layer.

[0119] For example, the middle layer is parallel to the scanning direction corresponding to the target lung CT tomographic image sequence and passes through the center point of the three-dimensional structure.

[0120] [3] Extract two lung regions from the middle layer.

[0121] Specifically, the lung parenchyma is first extracted from the middle layer; if two larger connected regions are obtained (i.e., two connected regions whose areas are larger than a preset area threshold), the two larger connected regions are directly determined as two lung regions; if one larger connected region is obtained, a morphological corrosion operation is performed (for example, a 7*1 region can be used to perform morphological corrosion on the larger connected region) until two larger connected regions are obtained, at which point the two larger connected regions are determined as two lung regions.

[0122] The global threshold binary method may be used to extract the lung parenchyma from the middle layer. Specifically, the lung parenchyma may be extracted from the middle layer in a manner similar to that of extracting the chest region in the first image, which will not be described in detail in this disclosure.

[0123] In addition, in order to further accurately distinguish the left lung from the right lung, after obtaining two larger connected areas through the above-mentioned morphological corrosion operation, for each corroded pixel point, the pixel point can be divided into the two larger connected areas and the area closer to the pixel point; then, the two larger connected areas obtained are determined as two lung areas.

[0124] [4] The lung region with the larger ratio of the long diameter to the short diameter is determined as the left lung region, and the lung region with the smaller ratio of the long diameter to the short diameter is determined as the right lung region.

[0125] In the present disclosure, due to the presence of the heart, there are certain differences in the shape and size of the left and right lungs. Usually, the left lung is relatively narrow and long, and its length-to-short diameter ratio is relatively large, while the right lung is relatively wide and short, and its length-to-short diameter ratio is relatively small. Therefore, the area with a larger length-to-short diameter ratio in the two lung areas is determined as the left lung area, and the area with a smaller length-to-short diameter ratio in the two lung areas is determined as the right lung area. The length-to-short diameter ratio may be the ratio of the length to the width of the smallest circumscribed rectangle of the corresponding lung area.

[0126] Figure 4 FIG. 1 is a flowchart of an image processing method according to another exemplary embodiment. Figure 4 As shown, the above method also includes the following S106.

[0127] In S106, if the slice images in the target lung CT slice image sequence do not have left and right mirror images, each slice image in the target lung CT slice image sequence is horizontally mirror-flipped.

[0128] In the present disclosure, if there are no left and right mirror images in the tomographic images in the target lung CT tomographic image sequence, it indicates that the positions of the left lung region and the right lung region in the tomographic image do not conform to the conventional image viewing habits. At this time, each tomographic image in the target lung CT tomographic image sequence can be horizontally mirrored (i.e., flipped 180 degrees left and right); if there are left and right mirror images in the tomographic images in the target lung CT tomographic image sequence, it indicates that the positions of the left lung region and the right lung region in the tomographic image conform to the conventional image viewing habits. At this time, each tomographic image in the target lung CT tomographic image sequence is not flipped. In this way, the direction of the tomographic images in the target lung CT tomographic image sequence can be automatically corrected, thereby achieving the standardization of the target lung CT tomographic image sequence.

[0129] It should be noted that the above S104 can be executed after the above S101 (eg Figure 3 , Figure 4 As shown), it can also be executed before the above S101, or it can be executed simultaneously with the above S101, which is not specifically limited in the present disclosure.

[0130] Figure 5 FIG. 1 is a flowchart of an image processing method according to another exemplary embodiment. Figure 5 As shown, the above method also includes the following S107 and S108.

[0131] In S107, the scanning direction corresponding to the target lung CT tomographic image sequence is determined.

[0132] In S108, if the scanning direction is from the abdomen to the neck, the target lung CT tomographic image sequence is reversely sorted.

[0133] In the present disclosure, if the scanning direction is from the abdomen to the neck, it indicates that the target lung CT tomographic image sequence is in reverse order, and at this time, the target lung CT tomographic image sequence can be reversely sorted; if the scanning direction is from the neck to the abdomen, it indicates that the target lung CT tomographic image sequence is in positive order, and at this time, the target lung CT tomographic image sequence is not reordered. In this way, the direction of the tomographic image in the target lung CT tomographic image sequence can be automatically corrected, thereby achieving the standardization of the target lung CT tomographic image sequence.

[0134] It should be noted that the above S107 can be executed after the above S101 (eg Figure 5 As shown), it can also be executed before the above S101, or it can be executed simultaneously with the above S101, which is not specifically limited in the present disclosure.

[0135] Figure 6 FIG. 1 is a block diagram of an image processing apparatus according to an exemplary embodiment. Figure 6 As shown, the device 600 includes:

[0136] The first extraction module 601 is used to extract the main trachea area and the chest area from the target lung CT tomographic image sequence;

[0137] The first determination module 602 is used to determine the scanning position corresponding to the target lung CT tomographic image sequence according to the relative positions of the main trachea area and the chest area extracted by the first extraction module 601.

[0138] In the above technical solution, first, the main trachea region and the chest region are extracted from the target lung CT tomographic image sequence; then, according to the relative position of the main trachea region and the chest region, the scanning position corresponding to the target lung CT tomographic image sequence is determined. In this way, the scanning position can be quickly and automatically detected based on the relative position of the main trachea region and the chest region, avoiding the problem of time-consuming manual identification of the scanning position. In addition, since the entire process does not require human participation, human misjudgment can be effectively avoided, thereby ensuring the accuracy of the scanning position, and then the CT direction correction can be performed based on the scanning position, thereby improving the accuracy and convenience of the film reading and auxiliary diagnosis and treatment system.

[0139] Optionally, the first extraction module 601 includes:

[0140] A first determination submodule is used to determine a scanning direction corresponding to the target lung CT tomographic image sequence;

[0141] A first extraction submodule is used to extract the chest area in each tomographic image in the initial layer, wherein when the scanning direction is from the neck to the abdomen, the initial layer includes the first M tomographic images of the target lung CT tomographic image sequence, and when the scanning direction is from the abdomen to the neck, the initial layer includes the last M tomographic images of the target lung CT tomographic image sequence;

[0142] A second determination submodule is used to determine a main trachea candidate region from other regions in the initial layer except the thoracic region;

[0143] The identification submodule is used to identify the main trachea area from the main trachea candidate areas.

[0144] Optionally, the second determining submodule is used to determine a region among the other regions whose area is within a preset area range as a main trachea candidate region.

[0145] Optionally, the first determining module 602 is used to:

[0146] If the main trachea region is located in the upper half of the thoracic region, determining that the scanning position corresponding to the target lung CT tomographic image sequence is supine;

[0147] If the main trachea region is located in the lower half of the thoracic region, it is determined that the scanning position corresponding to the target lung CT tomographic image sequence is prone.

[0148] Optionally, the device 600 further includes:

[0149] The first flipping module is used to vertically mirror flip each slice image in the target lung CT slice image sequence if the scanning position is prone.

[0150] Optionally, the device 600 further includes:

[0151] A second extraction module is used to extract a left lung region and a right lung region from the target lung CT tomographic image sequence;

[0152] The second determination module is used to determine whether there are left and right mirror images of the tomographic images in the target lung CT tomographic image sequence according to the relative positions of the left lung area and the right lung area.

[0153] Optionally, the second extraction module includes:

[0154] A reconstruction submodule, used for performing three-dimensional reconstruction on the target lung CT tomographic image sequence to obtain a three-dimensional structure;

[0155] A second extraction submodule is used to extract an intermediate layer including a lung parenchyma region from the three-dimensional structure, wherein the intermediate layer is parallel to a scanning direction corresponding to the target lung CT tomographic image sequence;

[0156] a third extraction submodule, for extracting two lung regions from the middle layer;

[0157] The third determination submodule is used to determine the one of the two lung regions with a larger long-short diameter ratio as the left lung region, and to determine the one of the two lung regions with a smaller long-short diameter ratio as the right lung region.

[0158] Optionally, the device 600 further includes:

[0159] The second flipping module is used to horizontally flip each of the tomographic images in the target lung CT tomographic image sequence if there is no left and right mirror image in the tomographic image sequence of the target lung CT tomographic image.

[0160] Optionally, the device 600 further includes:

[0161] A third determination module is used to determine the scanning direction corresponding to the target lung CT tomographic image sequence;

[0162] A sorting module is used to reversely sort the target lung CT tomographic image sequence if the scanning direction is from the abdomen to the neck.

[0163] Optionally, the third determining module includes:

[0164] a fourth extraction submodule, configured to extract the chest region in the first image and the second image, respectively, wherein the first image is one of the first N tomographic images in the target lung CT tomographic image sequence, and the second image is one of the last L tomographic images in the target lung CT tomographic image sequence;

[0165] The fourth determination submodule is used to determine the scanning direction corresponding to the target lung CT tomographic image sequence according to the chest area in the first image and the chest area in the second image.

[0166] Optionally, the fourth determining submodule includes:

[0167] a length determination submodule, used to determine a first length of a minimum circumscribed rectangle of a chest region in the first image and a second length of a minimum circumscribed rectangle of a chest region in the second image;

[0168] a first scanning direction determining submodule, configured to determine that the scanning direction corresponding to the target lung CT tomographic image sequence is from the neck to the abdomen if the first length is greater than the second length;

[0169] The second scanning direction determining submodule is used to determine that the scanning direction corresponding to the target lung CT tomographic image sequence is from the abdomen to the neck if the first length is smaller than the second length.

[0170] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0171] The present disclosure also provides a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the above-mentioned image processing method provided by the present disclosure are implemented.

[0172] Figure 7 FIG. 7 is a block diagram of an electronic device 700 according to an exemplary embodiment. Figure 7 As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0173] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned image processing method. The memory 702 is used to store various types of data to support the operation of the electronic device 700. For example, these data may include instructions for any application or method used to operate on the electronic device 700, and application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 705 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0174] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned image processing method.

[0175] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned image processing method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned image processing method.

[0176] Figure 8 8 is a block diagram of an electronic device 800 according to an exemplary embodiment. For example, the electronic device 800 may be provided as a server. Figure 8 The electronic device 800 includes a processor 822, which may be one or more, and a memory 832 for storing a computer program executable by the processor 822. The computer program stored in the memory 832 may include one or more modules each corresponding to a set of instructions. In addition, the processor 822 may be configured to execute the computer program to perform the above-mentioned image processing method.

[0177] In addition, the electronic device 800 may further include a power supply component 826 and a communication component 850. The power supply component 826 may be configured to perform power management of the electronic device 800, and the communication component 850 may be configured to implement communication of the electronic device 800, for example, wired or wireless communication. In addition, the electronic device 800 may further include an input / output (I / O) interface 858. The electronic device 800 may operate based on an operating system stored in the memory 832, such as Windows Server 2000. TM , Mac OSX TM , Unix TM , Linux TM etc.

[0178] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by the processor, the steps of the above-mentioned image processing method are implemented. For example, the non-transitory computer-readable storage medium can be the above-mentioned memory 832 including program instructions, and the above-mentioned program instructions can be executed by the processor 822 of the electronic device 800 to complete the above-mentioned image processing method.

[0179] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned image processing method when executed by the programmable device.

[0180] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0181] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0182] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. An image processing method, characterized in that: include: Determine the scanning direction corresponding to the target lung CT tomographic image sequence; Extracting the thoracic region in each tomographic image in the initial layer, wherein, when the scanning direction is from the neck to the abdomen, the initial layer includes the first M tomographic images of the target lung CT tomographic image sequence, and when the scanning direction is from the abdomen to the neck, the initial layer includes the last M tomographic images of the target lung CT tomographic image sequence; Determine a main trachea candidate region from other regions in the initial layer except the thoracic region; identifying a main trachea region from the main trachea candidate regions; According to the relative positions of the main trachea region and the thoracic cavity region, a scanning position corresponding to the target lung CT tomographic image sequence is determined.

2. The method according to claim 1, characterized in that The determining of the main trachea candidate region from other regions in the initial layer except the thoracic region comprises: The area in the other areas whose area is within the preset area range is determined as the main trachea candidate area.

3. The method according to claim 1, characterized in that Determining the scanning position corresponding to the target lung CT tomographic image sequence according to the relative positions of the main trachea region and the thoracic cavity region includes: If the main trachea region is located in the upper half of the thoracic region, determining that the scanning position corresponding to the target lung CT tomographic image sequence is supine; If the main trachea region is located in the lower half of the thoracic region, it is determined that the scanning position corresponding to the target lung CT tomographic image sequence is prone.

4. The method according to claim 1, characterized in that: The method further comprises: If the scanning body position is prone, each slice image in the target lung CT slice image sequence is vertically mirror-flipped.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Extracting a left lung region and a right lung region from the target lung CT tomographic image sequence; According to the relative positions of the left lung region and the right lung region, it is determined whether there are left and right mirror images of the tomographic images in the target lung CT tomographic image sequence.

6. The method according to claim 5, characterized in that The step of extracting the left lung region and the right lung region from the target lung CT tomographic image sequence comprises: Performing three-dimensional reconstruction on the target lung CT tomographic image sequence to obtain a three-dimensional structure; Extracting an intermediate layer including a lung parenchyma region from the three-dimensional structure, wherein the intermediate layer is parallel to a scanning direction corresponding to the target lung CT tomographic image sequence; extracting two lung regions from the middle layer; The one of the two lung regions with a larger ratio of the long and short axes is determined as the left lung region, and the one of the two lung regions with a smaller ratio of the long and short axes is determined as the right lung region.

7. The method according to claim 5, characterized in that The method further comprises: If the tomographic images in the target lung CT tomographic image sequence do not have left and right mirror images, each of the tomographic images in the target lung CT tomographic image sequence is horizontally mirror-flipped.

8. The method according to claim 1, characterized in that: The method further comprises: Determining a scanning direction corresponding to the target lung CT tomographic image sequence; If the scanning direction is from the abdomen to the neck, the target lung CT section image sequence is reversely sorted.

9. The method according to claim 1 or 8, characterized in that: Determining the scanning direction corresponding to the target lung CT tomographic image sequence includes: Extracting the chest area in the first image and the second image respectively, wherein the first image is one of the first N tomographic images in the target lung CT tomographic image sequence, and the second image is one of the last L tomographic images in the target lung CT tomographic image sequence; The scanning direction corresponding to the target lung CT tomographic image sequence is determined according to the chest region in the first image and the chest region in the second image.

10. The method according to claim 9, characterized in that Determining the scanning direction corresponding to the target lung CT tomographic image sequence according to the chest region in the first image and the chest region in the second image includes: Determine a first length of a minimum circumscribed rectangle of a chest region in the first image and a second length of a minimum circumscribed rectangle of a chest region in the second image; If the first length is greater than the second length, determining that the scanning direction corresponding to the target lung CT tomographic image sequence is from the neck to the abdomen; If the first length is smaller than the second length, it is determined that the scanning direction corresponding to the target lung CT section image sequence is from the abdomen to the neck.

11. An image processing device, characterized in that: include: A first extraction module is used to extract the main trachea area and the chest area from the target lung CT tomographic image sequence; A first determination module is used to determine the scanning position corresponding to the target lung CT tomographic image sequence according to the relative positions of the main trachea area and the chest area extracted by the first extraction module; Wherein, the first extraction module includes: A first determination submodule is used to determine a scanning direction corresponding to the target lung CT tomographic image sequence; A first extraction submodule is used to extract the chest area in each tomographic image in the initial layer, wherein when the scanning direction is from the neck to the abdomen, the initial layer includes the first M tomographic images of the target lung CT tomographic image sequence, and when the scanning direction is from the abdomen to the neck, the initial layer includes the last M tomographic images of the target lung CT tomographic image sequence; A second determination submodule is used to determine a main trachea candidate region from other regions in the initial layer except the thoracic region; The identification submodule is used to identify the main trachea area from the main trachea candidate areas.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 10 are implemented.

13. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 10.

Images