Quality Evaluation Method for Cervical Spine Images, Electronic Device, and Storage Medium

Abstract

The present invention discloses a method for evaluating the quality of cervical spine images, an electronic device, and a storage medium. Among them, the method for evaluating the quality of cervical spine images includes the following steps: obtaining a cervical spine image to be evaluated; identifying the shooting position of the cervical spine image; calling an image segmentation model corresponding to the shooting position to segment the cervical spine image, and outputting a segmentation result corresponding to the shooting position; evaluating the quality of the cervical spine image according to the features of at least one part in the segmentation result. The present invention realizes the quality evaluation of cervical spine images in different shooting positions. Further, for the cervical spine images in the anteroposterior position, the lateral position, and the oblique position of the cervical spine, quantitative analysis is respectively performed on their segmentation results, and quality evaluation results of cervical spine images in different shooting positions that meet the medical objective standards can be obtained, so as to better assist medical diagnosis and treatment and improve the accuracy of subsequent clinical diagnosis.

Description

Technical Field

[0001] The present invention relates to the field of processing cervical vertebra images, and particularly relates to a method for evaluating the quality of cervical vertebra images, an electronic device, and a storage medium. Background Art

[0002] X-ray cervical vertebra images are currently a widely used means for cervical spine medical image examinations. Doctors can diagnose cervical spine diseases such as cervical spondylosis, degenerative changes, and spinal canal stenosis by observing the physiological curvature of the cervical vertebrae and the degree of joint degeneration in the cervical vertebra images. Therefore, cervical vertebra images are an important basis for diagnosing cervical spine diseases, and the quality of cervical vertebra images will directly affect the diagnostic results. If the quality of cervical vertebra images is unqualified, it is easy to occur situations such as missed diagnosis and misdiagnosis.

[0003] Currently, the quality assessment of cervical vertebra images is mainly completed manually by radiology technicians, which easily leads to some unqualified cervical vertebra images entering clinical film reading diagnosis, thus affecting the accuracy of cervical spine disease diagnosis. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the defect that the accuracy of cervical spine disease diagnosis is affected by manually evaluating the quality of cervical vertebra images in the prior art, and to provide a method for evaluating the quality of cervical vertebra images, an electronic device, and a storage medium.

[0005] The present invention solves the above technical problem through the following technical solutions:

[0006] The first aspect of the present invention provides a method for evaluating the quality of cervical vertebra images, including the following steps:

[0007] Obtain a cervical vertebra image to be evaluated;

[0008] Identify the shooting position of the cervical vertebra image;

[0009] Call an image segmentation model corresponding to the shooting position to segment the cervical vertebra image, and output a segmentation result corresponding to the shooting position;

[0010] Evaluate the quality of the cervical vertebra image according to the features of at least one part in the segmentation result.

[0011] Optionally, the shooting position is the anteroposterior position of the cervical vertebra;

[0012] The evaluating the quality of the cervical vertebra image according to the features of at least one part in the segmentation result includes:

[0013] Judge whether the number of cervical vertebrae in the segmentation result is less than a first preset number;

[0014] If not, evaluate the quality of the cervical vertebra image as qualified;

[0015] If so, evaluate the quality of the cervical vertebra image as unqualified.

[0016] Optionally, evaluating the quality of the cervical vertebra image as qualified includes:

[0017] Determine whether the distance between the center point of the cervical vertebra in the segmentation result and the center point of the trachea is less than a first preset distance, the distance between the center point of the mandible and the center point of the occipital bone in the segmentation result is less than a second preset distance, and the number of cervical vertebrae is a second preset number; wherein, the center point of the cervical vertebra is used to represent the central position of all cervical vertebrae, the center point of the trachea is used to represent the central position of the trachea, the center point of the mandible is used to represent the central position of the mandible, and the center point of the occipital bone is used to represent the central position of the occipital bone; the second preset number is greater than the first preset number;

[0018] If so, evaluate the quality of the cervical vertebra image as first-level qualified;

[0019] If not, evaluate the quality of the cervical vertebra image as second-level qualified.

[0020] Optionally, the shooting position is the anteroposterior position of the cervical vertebra;

[0021] Evaluating the quality of the cervical vertebra image according to the characteristics of at least one part in the segmentation result includes:

[0022] Determine whether the distance between the center point of the cervical vertebra in the segmentation result and the center point of the trachea is greater than a third preset distance; wherein, the center point of the cervical vertebra is used to represent the central position of all cervical vertebrae, and the center point of the trachea is used to represent the central position of the trachea;

[0023] If not, evaluate the quality of the cervical vertebra image as qualified; if so, evaluate the quality of the cervical vertebra image as unqualified.

[0024] Optionally, the shooting position is the anteroposterior position of the cervical vertebra;

[0025] Evaluating the quality of the cervical vertebra image according to the characteristics of at least one part in the segmentation result includes:

[0026] Determine whether the distance between the center point of the mandible and the center point of the occipital bone in the segmentation result is greater than a fourth preset distance; wherein, the center point of the mandible is used to represent the central position of the mandible, and the center point of the occipital bone is used to represent the central position of the occipital bone;

[0027] If not, evaluate the quality of the cervical vertebra image as qualified; if so, evaluate the quality of the cervical vertebra image as unqualified.

[0028] Optionally, the shooting position is the lateral position of the cervical vertebra;

[0029] Evaluating the quality of the cervical vertebra image according to the features of at least one part in the segmentation result includes:

[0030] Judging whether the number of cervical vertebrae in the segmentation result is less than a second preset number;

[0031] If not, evaluate the quality of the cervical vertebra image as qualified;

[0032] If so, evaluate the quality of the cervical vertebra image as unqualified.

[0033] Optionally, evaluating the quality of the cervical vertebra image as qualified includes:

[0034] Judging whether the cervical vertebrae in the segmentation result intersect with the mandible;

[0035] If not, evaluate the quality of the cervical vertebra image as first-level qualified;

[0036] If so, evaluate the quality of the cervical vertebra image as second-level qualified.

[0037] Optionally, the shooting position is the oblique position of the cervical vertebra;

[0038] Evaluating the quality of the cervical vertebra image according to the features of at least one part in the segmentation result includes:

[0039] Judging whether the number of cervical vertebrae in the segmentation result is less than a second preset number;

[0040] If not, evaluate the quality of the cervical vertebra image as qualified;

[0041] If so, evaluate the quality of the cervical vertebra image as unqualified.

[0042] Optionally, evaluating the quality of the cervical vertebra image as qualified includes:

[0043] Judging whether there are a third preset number of pedicles in front of all cervical vertebrae in the segmentation result and the number of intervertebral foramina is a fourth preset number;

[0044] If so, evaluate the quality of the cervical vertebra image as first-level qualified;

[0045] If not, evaluate the quality of the cervical vertebra image as second-level qualified.

[0046] The second aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the quality evaluation method described in the first aspect is implemented.

[0047] The third aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the quality evaluation method described in the first aspect is implemented.

[0048] The positive and progressive effects of the present invention are as follows: By identifying the shooting position of the cervical vertebra image to be evaluated, an image segmentation model corresponding to the shooting position is called to segment different parts of the cervical vertebra image, and thus the quality of the cervical vertebra image is evaluated according to the features of at least one part in the segmentation result, realizing the quality evaluation of cervical vertebra images in different shooting positions.

[0049] Furthermore, for the cervical vertebra images in the anteroposterior position of the cervical vertebra, the lateral position of the cervical vertebra, and the oblique position of the cervical vertebra, quantitative analysis is respectively performed on their segmentation results, and quality evaluation results of cervical vertebra images in different shooting positions that meet the medical objective standards can be obtained, thus better assisting medical diagnosis and treatment and improving the accuracy of subsequent clinical diagnosis. Description of the Drawings

[0050] Figure 1 It is a flowchart of a method for evaluating the quality of a cervical vertebra image provided in Embodiment 1 of the present invention.

[0051] Figure 2 (a) It is a schematic diagram of a cervical vertebra image in the lateral position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0052] Figure 2 (b) is Figure 2 A schematic diagram of the segmentation result of the cervical vertebra body in (a).

[0053] Figure 3 (a) It is a schematic diagram of a cervical vertebra image in the lateral position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0054] Figure 3 (b) is Figure 3 A schematic diagram of the segmentation result of the mandible in (a).

[0055] Figure 4 (a) It is a schematic diagram of a cervical vertebra image in the oblique position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0056] Figure 4 (b) is Figure 4 A schematic diagram of the segmentation result of the cervical vertebra body in (a).

[0057] Figure 5(a) is a schematic diagram of a cervical vertebra image in an oblique position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0058] Figure 5 (b) is Figure 5 a schematic diagram of the segmentation result of the intervertebral foramen in (a).

[0059] Figure 6 (a) is a schematic diagram of a cervical vertebra image in an oblique position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0060] Figure 6 (b) is Figure 6 a schematic diagram of the segmentation result of the pedicle of vertebral arch in (a).

[0061] Figure 7 is a flowchart of Step S4 when the shooting position is the anteroposterior position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0062] Figure 8 is another flowchart of Step S4 when the shooting position is the anteroposterior position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0063] Figure 9 is another flowchart of Step S4 when the shooting position is the anteroposterior position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0064] Figure 10 is yet another flowchart of Step S4 when the shooting position is the anteroposterior position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0065] Figure 11 is a flowchart of Step S4 when the shooting position is the lateral position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0066] Figure 12 is a flowchart of Step S4 when the shooting position is the oblique position of the cervical vertebra provided in Embodiment 1 of the present invention.

[0067] Figure 13 is a structural block diagram of a quality evaluation device for a cervical vertebra image provided in Embodiment 1 of the present invention.

[0068] Figure 14 is a structural schematic diagram of an electronic device provided in Embodiment 2 of the present invention. Detailed Embodiments

[0069] The present invention will be further described below by way of examples, but the present invention is not limited to the scope of the described examples.

[0070] Embodiment 1

[0071] Figure 1Schematic flowchart of a method for evaluating the quality of cervical spine images provided in this embodiment. The method for evaluating the quality of cervical spine images can be executed by a device for evaluating the quality of cervical spine images, which can be implemented in software and / or hardware, and can be part or all of an electronic device. Among them, the electronic device in this embodiment can be a personal computer (PC), such as a desktop computer, an all-in-one computer, a laptop computer, a tablet computer, etc., and can also be a terminal device such as a mobile phone, a wearable device, a personal digital assistant (PDA), etc. The method for evaluating the quality of cervical spine images provided in this embodiment will be introduced below with the electronic device as the execution entity.

[0072] As Figure 1 shown, the method for evaluating the quality of cervical spine images provided in this embodiment may include the following steps S1 to S4:

[0073] Step S1, obtain a cervical spine image to be evaluated.

[0074] In a specific implementation, the cervical spine image to be evaluated can be obtained from the cloud or the server. Specifically, the cervical spine image to be evaluated can be downloaded from the cloud or the server through a wireless network. It is also possible to use an X-ray machine to take pictures of the patient to obtain the cervical spine image to be evaluated.

[0075] To improve the accuracy of evaluating the quality of cervical spine images, preprocessing such as truncation and normalization can be performed on the obtained cervical spine image. Specifically, truncation processing of the maximum gray value and the minimum gray value can be performed on the cervical spine image. For example, all pixel points of the cervical spine image are sorted according to the gray value, and the pixel points in the middle position are intercepted to improve the contrast of the cervical spine image. In a specific example, the cervical spine image has a total of 500 pixel points. After sorting according to the gray value, the pixel points between the 8th and 492nd positions are intercepted. In addition, standard normalization processing can also be performed on the cervical spine image. For example, the pixel value of the pixel point is subtracted from the average pixel value of all pixel points, and then divided by the standard deviation to obtain the normalized cervical spine image.

[0076] Step S2, identify the shooting position of the cervical spine image.

[0077] Among them, the shooting positions of the cervical spine image can include the anteroposterior position of the cervical spine, the lateral position of the cervical spine, the oblique position of the cervical spine, etc.

[0078] In a specific implementation, the shooting position of the cervical vertebra image can be classified by calling an image classification model, so as to identify the shooting position of the cervical vertebra image. Among them, the image classification model can be trained by using networks such as ResNet (Residual Network), DenseNet (Densely Connected Convolutional Networks), and SENet (Squeeze-and-Excitation Networks). In addition, other methods can also be used to identify the shooting position of the cervical vertebra image.

[0079] Step S3: Call the image segmentation model corresponding to the shooting position to segment the cervical vertebra image, and output a segmentation result corresponding to the shooting position.

[0080] Among them, the image segmentation model corresponds to the shooting position, and different parts are segmented for cervical vertebra images with different shooting positions. In a specific example, for a cervical vertebra image in the anteroposterior position of the cervical vertebra, four parts, namely the cervical vertebra body, mandible, occipital bone, and trachea, are segmented; for a cervical vertebra image in the lateral position of the cervical vertebra, two parts, namely the cervical vertebra body and mandible, are segmented; for a cervical vertebra image in the oblique position of the cervical vertebra, three parts, namely the cervical vertebra body, intervertebral foramen, and pedicle of vertebral arch, are segmented.

[0081] Figure 2 (a) and Figure 3 (a) are both used to show a cervical vertebra image in the lateral position of the cervical vertebra. Figure 2 (b) is used to show Figure 2 the segmentation result of the cervical vertebra body in Figure 3 (a). Figure 3 (b) is used to show Figure 2 the segmentation result of the mandible in Figure 2 (a). For the cervical vertebra image in the lateral position of the cervical vertebra as shown in Figure 3 (a), the segmentation result of its cervical vertebra body can be seen in Figure 3 (b). For the cervical vertebra image in the lateral position of the cervical vertebra as shown in

[0082] Figure 4 (a), Figure 5 (a) and Figure 6 (a) are both used to show a cervical vertebra image in the oblique position of the cervical vertebra. Figure 4 (b) is used to show Figure 4 the segmentation result of the cervical vertebra body in Figure 5 (a). Figure 5 (b) is used to show Figure 6 the segmentation result of the intervertebral foramen in Figure 6(a) Segmentation result of the cervical pedicle. For the cervical spine image in the cervical oblique position as shown in Figure 4 (a), the segmentation result of the cervical vertebrae can be seen in Figure 4 (b). For the cervical spine image in the cervical oblique position as shown in Figure 5 (a), the segmentation result of the intervertebral foramen can be seen in Figure 5 (b). For the cervical spine image in the cervical oblique position as shown in Figure 6 (a), the segmentation result of the pedicle can be seen in Figure 6 (b).

[0083] In a specific implementation, the image segmentation model can be trained using networks such as V-Net, U-Net, LinkNet, FC-DensNet (fully convolutional dense block network), etc.

[0084] Step S4: Evaluate the quality of the cervical spine image according to the features of at least one part in the segmentation result.

[0085] In the specific implementation of step S4, the quality of the cervical spine image can be evaluated according to the features of one part in the segmentation result, or according to the features of multiple parts in the segmentation result. Among them, the features of the part can be the number of parts, the distance between different parts, or the positional relationship between different parts, etc.

[0086] In this embodiment, by identifying the shooting position of the cervical spine image to be evaluated, calling the image segmentation model corresponding to the shooting position to segment different parts of the cervical spine image, and then evaluating the quality of the cervical spine image according to the features of at least one part in the segmentation result, the quality evaluation of cervical spine images in different shooting positions is realized.

[0087] Furthermore, in this embodiment, for the cervical spine images in the anteroposterior position, lateral position, and oblique position of the cervical spine, the segmentation results can be quantitatively analyzed respectively, so as to obtain the quality evaluation results of cervical spine images in different shooting positions that meet the medical objective standards, so as to better assist medical diagnosis and treatment, and further improve the accuracy of subsequent clinical diagnosis.

[0088] The following takes the shooting position as the anteroposterior position of the cervical spine as an example to introduce the process of quantitative analysis of the segmentation result.

[0089] In an optional implementation manner, as shown in Figure 7 the above step S4 specifically includes the following steps S41a to S41c:

[0090] Step S41a: Determine whether the number of cervical vertebrae in the segmentation result is less than the first preset number; if not, execute step S41b, if so, execute step S41c.

[0091] Among them, the segmentation result includes cervical vertebrae of all categories. For example, the first cervical vertebra C1 to the seventh cervical vertebra C7 are arranged from top to bottom in position. According to the segmentation result, the number c_n of cervical vertebrae can be directly obtained. In a specific example, the segmentation result includes C1, C2, C4, C7, and the number of cervical vertebrae can be obtained as 4.

[0092] In a specific implementation, the first preset number can be 5, that is, the quality of the cervical vertebra image is evaluated according to whether the number c_n of cervical vertebrae is less than 5.

[0093] Step S41b: Evaluate the quality of the cervical vertebra image as qualified.

[0094] It should be noted that after the cervical vertebra image evaluated as qualified enters clinical film reading and diagnosis, the doctor diagnoses cervical diseases based on the qualified cervical vertebra image, which can improve the accuracy of clinical film reading and diagnosis.

[0095] Step S41c: Evaluate the quality of the cervical vertebra image as unqualified.

[0096] It should be noted that when the doctor conducts clinical film reading and diagnosis, the cervical vertebra image evaluated as unqualified can be not considered, so as to avoid affecting the accuracy of clinical film reading and diagnosis.

[0097] In this embodiment, for the cervical vertebra image in the anteroposterior position of the cervical vertebra, a quantitative analysis is performed on the number of cervical vertebrae in its segmentation result to obtain the quality evaluation results of qualified and unqualified cervical vertebra images. This embodiment evaluates the quality of the cervical vertebra image in the anteroposterior position of the cervical vertebra based on the number of cervical vertebrae in the cervical vertebra image, and can obtain a quality evaluation result that meets the medical objective standard, so as to better assist medical diagnosis and treatment.

[0098] In the specific implementation of step S41c, a prompt message can also be output when it is evaluated as unqualified to prompt that the quality of the cervical vertebra image is unqualified, so as to guide the subsequent shooting of the cervical vertebra image.

[0099] In a specific implementation, as Figure 8 shown, step S41b may include the following steps S41b1 to S41b3:

[0100] Step S41b1: Judge whether the distance between the center point C of the cervical vertebra in the segmentation result and the center point T of the trachea is less than the first preset distance, the distance between the center point M of the mandible and the center point O of the occipital bone is less than the second preset distance, and the number c_n of cervical vertebrae is the second preset number; if so, execute step S41b2, if not, execute step S41b3.

[0101] Among them, the center point C of the cervical vertebra is used to represent the central position of all cervical vertebrae. The following introduces a method for calculating the coordinates (x c , y c ) of the center point C. First, calculate the coordinates (x i , y i ) of the central position of each cervical vertebra, where i = 1, 2, 3... 7. Among them, x 1 = the sum of the abscissas of all pixel points belonging to the first cervical vertebra C1 / the number of all pixel points belonging to the first cervical vertebra C1, and y 1 = the sum of the ordinates of all pixel points belonging to the first cervical vertebra C1 / the number of all pixel points belonging to the first cervical vertebra C1. And so on, x 7 = the sum of the abscissas of all pixel points belonging to the seventh cervical vertebra C7 / the number of all pixel points belonging to the seventh cervical vertebra C7, and y 7 = the sum of the ordinates of all pixel points belonging to the seventh cervical vertebra C7 / the number of all pixel points belonging to the seventh cervical vertebra C7. Then, calculate the coordinates (x c , y c ) of the center point C of the cervical vertebra, where x c = (x 1 + x 2 + x 3 + x 4 + x 5 + x 6 + x 7 ) / 7, and y c = (y 1 + y 2 + y 3 + y 4 + y 5 + y 6 + y 7 ) / 7. The following introduces another method for calculating the coordinates (x c , y c ) of the center point C. Calculate the minimum abscissa x cmin , the minimum ordinate y cmin , the maximum abscissa x cmax and the maximum ordinate y cmax of all pixel points belonging to the cervical vertebra. x c = (x cmax - x cmin ) / 2, and y c = (y cmax - y cmin ) / 2.

[0102] The center point T of the trachea is used to represent the central position of the trachea. The following introduces a method for calculating the coordinates (xt , y t ) method. x t = The sum of the abscissas of all pixels belonging to the trachea / The number of all pixels belonging to the trachea, y t = The sum of the ordinates of all pixels belonging to the trachea / The number of all pixels belonging to the trachea. The following introduces another method for calculating the coordinates (x t , y t ) of the center point T. Calculate the minimum abscissa x tmin , minimum ordinate y tmin , maximum abscissa x tmax and maximum ordinate y tmax of all pixels belonging to the trachea, x t = (x tmax - x tmin ) / 2, y t = (y tmax - y tmin ) / 2.

[0103] The center point M of the mandible is used to represent the central position of the mandible. The following introduces a method for calculating the coordinates (x m , y m ) of the center point M. x m = The sum of the abscissas of all pixels belonging to the mandible / The number of all pixels belonging to the mandible, y m = The sum of the ordinates of all pixels belonging to the mandible / The number of all pixels belonging to the mandible. The following introduces another method for calculating the coordinates (x m , y m ) of the center point M. Calculate the minimum abscissa x mmin , minimum ordinate y mmin , maximum abscissa x mmax and maximum ordinate y mmax , x m = x mmax - x mmin , ym = ymmax - ymm i n.

[0104] The center point O of the occipital bone is used to represent the central position of the occipital bone. The following introduces a method for calculating the coordinates (x o , y o ) of the center point O. x o = The sum of the abscissas of all pixels belonging to the occipital bone / The number of all pixels belonging to the occipital bone, y o = The sum of the ordinates of all pixels belonging to the occipital bone / The number of all pixels belonging to the occipital bone. The following introduces another method for calculating the coordinates (x o, y o ) method. Calculate the minimum abscissa x of all pixel points belonging to the occipital bone omin , the minimum ordinate y omin , the maximum abscissa x omax and the maximum ordinate y omax , x o =(x omax -x omin ) / 2, y o =(y omax -y omin ) / 2.

[0105] Wherein, the second preset quantity is greater than the first preset quantity. In a specific implementation, the first preset quantity can be 5, and the second preset quantity can be 7. The first preset distance and the second preset distance can be set according to the actual situation. For example, the first preset distance can be 4 cm, and the second preset distance can be 6 cm.

[0106] Step S41b2: Evaluate the quality of the cervical vertebra image as first-level qualified.

[0107] Specifically, the distance between the center point C of the cervical vertebra and the center point T of the trachea can be represented by |CT|, and the distance between the center point M of the mandible and the center point O of the occipital bone is represented by |MO|. In a specific example, if |CT| < 4 cm, |MO| < 6 cm, and c_n = 7, then the quality of the cervical vertebra image is evaluated as first-level qualified.

[0108] Step S41b3: Evaluate the quality of the cervical vertebra image as second-level qualified. Among them, for the qualified anteroposterior cervical vertebra images, except for the first-level qualified cervical vertebra images, they are all second-level qualified cervical vertebra images. It should be noted that the quality of the first-level qualified cervical vertebra images is better than that of the second-level qualified cervical vertebra images.

[0109] In this embodiment, for the qualified anteroposterior cervical vertebra images, further quantitative analysis is performed on the number of cervical vertebrae in the segmentation result, the distance between the cervical vertebrae and the trachea, and the distance between the mandible and the occipital bone to obtain the quality evaluation results of the first-level qualified and second-level qualified cervical vertebra images, realizing a sub-division evaluation of the qualified cervical vertebra images, so as to better assist in medical diagnosis and treatment.

[0110] In an alternative embodiment, as Figure 9 shown, the above step S4 specifically includes the following steps S42a to S42c:

[0111] Step S42a: Determine whether the distance between the center point C of the cervical vertebrae and the center point T of the trachea in the segmentation result is greater than a third preset distance; if not, execute step S42b, and if so, execute step S42c.

[0112] Among them, the center point C of the cervical vertebrae is used to represent the central position of all cervical vertebrae, and the center point T of the trachea is used to represent the central position of the trachea.

[0113] In specific implementation, the third preset distance can be set according to the actual situation. For example, the third preset distance can be 4 cm.

[0114] Step S42b: Evaluate the quality of the cervical vertebra image as qualified.

[0115] Step S42c: Evaluate the quality of the cervical vertebra image as unqualified.

[0116] Specifically, the distance between the center point C of the cervical vertebrae and the center point T of the trachea can be represented by |CT|. In a specific example, if |CT| > 4 cm, the quality of the cervical vertebra image is evaluated as unqualified, otherwise the quality of the cervical vertebra image is evaluated as qualified.

[0117] In this embodiment, for the cervical vertebra image in the anteroposterior view of the cervical vertebrae, the distance between the cervical vertebrae and the trachea in its segmentation result is quantitatively analyzed to obtain the quality evaluation results of qualified and unqualified for the cervical vertebra image. This embodiment evaluates the quality of the cervical vertebra image in the anteroposterior view based on the distance between the cervical vertebrae and the trachea in the cervical vertebra image, and can obtain the quality evaluation results that meet the medical objective standards, so as to better assist in medical diagnosis and treatment.

[0118] In an alternative embodiment, as Figure 10 shown, the above step S4 specifically includes the following steps S43a - S43c:

[0119] Step S43a: Determine whether the distance between the center point M of the mandible and the center point O of the occipital bone in the segmentation result is greater than a fourth preset distance; if not, execute step S43b, and if so, execute step S43c.

[0120] Among them, the center point M of the mandible is used to represent the central position of the mandible, and the center point O of the occipital bone is used to represent the central position of the occipital bone.

[0121] In specific implementation, the fourth preset distance can be set according to the actual situation. For example, the fourth preset distance can be 3 - 5 cm.

[0122] Step S43b: Evaluate the quality of the cervical vertebra image as qualified.

[0123] Step S43c: Evaluate the quality of the cervical vertebra image as unqualified.

[0124] Specifically, the distance between the center point M of the mandible and the center point O of the occipital bone can be represented by |MO|. In a specific example, the fourth preset distance is 4 cm. If |MO| > 4 cm, the quality of the cervical vertebra image is evaluated as unqualified; otherwise, the quality of the cervical vertebra image is evaluated as qualified.

[0125] In this embodiment, for the cervical vertebra image in the anteroposterior position of the cervical vertebra, a quantitative analysis is performed on the distance between the mandible and the occipital bone in its segmentation result to obtain the quality evaluation results of qualified and unqualified for the cervical vertebra image. This embodiment evaluates the quality of the cervical vertebra image in the anteroposterior position of the cervical vertebra based on the distance between the mandible and the occipital bone in the cervical vertebra image, and can obtain quality evaluation results that meet the medical objective standards, thereby better assisting in medical diagnosis and treatment.

[0126] Next, taking the radiographic position of the cervical vertebra in the lateral position as an example, the quantitative analysis process of the segmentation result is introduced.

[0127] In an alternative embodiment, as Figure 11 shown, the above step S4 specifically includes the following steps S44a to S44c:

[0128] Step S44a: Determine whether the number of cervical vertebrae in the segmentation result is less than the second preset number; if not, execute step S44b; if so, execute step S44c.

[0129] In a specific implementation, the second preset number can be 7, that is, the quality of the cervical vertebra image is evaluated according to whether the number c_n of cervical vertebrae is less than 7.

[0130] Step S44b: Evaluate the quality of the cervical vertebra image as qualified.

[0131] Step S44c: Evaluate the quality of the cervical vertebra image as unqualified.

[0132] In this embodiment, for the cervical vertebra image in the lateral position of the cervical vertebra, a quantitative analysis is performed on the number of cervical vertebrae in its segmentation result to obtain the quality evaluation results of qualified and unqualified for the cervical vertebra image. This embodiment evaluates the quality of the cervical vertebra image in the lateral position of the cervical vertebra based on the number of cervical vertebrae in the cervical vertebra image, and can obtain quality evaluation results that meet the medical objective standards, thereby better assisting in medical diagnosis and treatment.

[0133] In a specific implementation, step S44b may include the following steps S44b1 to S44b3:

[0134] Step S44b1: Determine whether the cervical vertebrae in the segmentation result intersect with the mandible; if not, execute Step S44b2, and if so, execute Step S44b3. Here, the intersection of the cervical vertebrae and the mandible means that there is a common part between the cervical vertebrae and the mandible in the segmentation result, and the non - intersection of the cervical vertebrae and the mandible means that there is no common part between the cervical vertebrae and the mandible in the segmentation result.

[0135] Step S44b2: Evaluate the quality of the cervical vertebra image as first - level qualified.

[0136] Step S44b3: Evaluate the quality of the cervical vertebra image as second - level qualified.

[0137] In a specific example, if the number of cervical vertebrae \(c_n = 7\) and the cervical vertebrae do not intersect with the mandible, then the quality of the cervical vertebra image is evaluated as first - level qualified; if the number of cervical vertebrae \(c_n = 7\) and the cervical vertebrae intersect with the mandible, then the quality of the cervical vertebra image is evaluated as second - level qualified.

[0138] In this embodiment, for the qualified cervical vertebra lateral images, further quantitative analysis of the position between the cervical vertebrae and the mandible in their segmentation results obtains the quality evaluation results of first - level qualified and second - level qualified for the cervical vertebra images, realizing the subdivision evaluation of qualified cervical vertebra images, and thus can better assist in medical diagnosis and treatment.

[0139] Next, taking the cervical vertebra oblique position as the shooting position as an example, the quantitative analysis process of the segmentation result is introduced.

[0140] In an alternative embodiment, as Figure 12 shown, the above - mentioned Step S4 specifically includes the following Steps S45a - S45c:

[0141] Step S45a: Determine whether the number of cervical vertebrae in the segmentation result is less than a second preset number; if not, execute Step S45b, and if so, execute Step S45c.

[0142] In a specific implementation, the second preset number can be 7, that is, the quality of the cervical vertebra image is evaluated according to whether the number of cervical vertebrae \(c_n\) is less than 7.

[0143] Step S45b: Evaluate the quality of the cervical vertebra image as qualified.

[0144] Step S45c: Evaluate the quality of the cervical vertebra image as unqualified.

[0145] In this embodiment, for the cervical vertebra images in the cervical vertebra oblique position, a quantitative analysis is performed on the number of cervical vertebrae in the segmentation result to obtain the quality evaluation results of qualified and unqualified cervical vertebra images. This embodiment evaluates the quality of the cervical vertebra oblique position images based on the number of cervical vertebrae in the cervical vertebra images, and can obtain quality evaluation results that meet the objective medical standards, thereby better assisting medical diagnosis and treatment.

[0146] In specific implementation, step S45b may include the following steps S45b1 to S45b3:

[0147] Step S45b1: Determine whether there are a third preset number of pedicles in front of all cervical vertebrae in the segmentation result and the number of intervertebral foramina is a fourth preset number; if so, execute step S45b2, if not, execute step S45b3.

[0148] In specific implementation, the third preset number may be 5, and the fourth preset number may be 6, that is, the quality of the cervical vertebra image is evaluated according to whether there are 5 pedicles in front of all cervical vertebrae and the number of intervertebral foramina is 6.

[0149] Step S45b2: Evaluate the quality of the cervical vertebra image as first-level qualified.

[0150] Step S45b3: Evaluate the quality of the cervical vertebra image as second-level qualified.

[0151] Specifically, if there are 5 pedicles in front of all cervical vertebrae and the number of intervertebral foramina is 6, the quality of the cervical vertebra image is evaluated as first-level qualified, otherwise the quality of the cervical vertebra image is evaluated as second-level qualified.

[0152] In this embodiment, for the qualified cervical vertebra images in the cervical vertebra oblique position, a further quantitative analysis is performed on the position between the pedicles and the cervical vertebrae, the number of pedicles, and the number of intervertebral foramina in the segmentation result to obtain the quality evaluation results of first-level qualified and second-level qualified for the cervical vertebra images, realizing a sub-evaluation of the qualified cervical vertebra images, thereby better assisting medical diagnosis and treatment.

[0153] This embodiment also provides a quality evaluation device 80 for cervical vertebra images, as Figure 13 shown, including an acquisition module 81, an identification module 82, a segmentation module 83, and an evaluation module 84.

[0154] The acquisition module 81 is used to acquire the cervical vertebra image to be evaluated.

[0155] The identification module 82 is used to identify the shooting position of the cervical vertebra image.

[0156] The segmentation module 83 is used to call an image segmentation model corresponding to the shooting position to segment the cervical vertebra image, and output a segmentation result corresponding to the shooting position.

[0157] The evaluation module 84 is used to evaluate the quality of the cervical vertebra image according to the features of at least one part in the segmentation result.

[0158] It should be noted that in this embodiment, the quality evaluation device for cervical vertebra images can specifically be a separate chip, chip module or electronic device, or can also be a chip or chip module integrated in an electronic device.

[0159] Regarding each module / unit included in the quality evaluation device for cervical vertebra images described in this embodiment, it can be a software module / unit, a hardware module / unit, or can also be partially a software module / unit and partially a hardware module / unit.

[0160] Embodiment 2

[0161] Figure 14 The following is a schematic structural diagram of an electronic device provided in this embodiment. The electronic device includes at least one processor and a memory communicatively connected to the at least one processor. Among them, the memory stores a computer program that can be run by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the quality evaluation method for cervical vertebra images in Embodiment 1. The electronic device provided in this embodiment can be a personal computer, such as a desktop computer, an all-in-one computer, a laptop computer, a tablet computer, etc., and can also be a terminal device such as a mobile phone, a wearable device, a handheld computer, etc. Figure 14 The electronic device 3 shown is only an example and should not bring any restrictions to the functions and usage scope of the embodiments of the present invention.

[0162] The components of the electronic device 3 may include, but are not limited to: the above-mentioned at least one processor 4, the above-mentioned at least one memory 5, and a bus 6 connecting different system components (including the memory 5 and the processor 4).

[0163] The bus 6 includes a data bus, an address bus, and a control bus.

[0164] The memory 5 may include volatile memory, such as random access memory (RAM) 51 and / or cache memory 52, and may further include read-only memory (ROM) 53.

[0165] The memory 5 may also include a program / utilities 55 having a set (at least one) of program modules 54. Such program modules 54 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0166] The processor 4 executes various functional applications and data processing by running computer programs stored in the memory 5, such as the method for evaluating the quality of cervical vertebra images described above.

[0167] The electronic device 3 can also communicate with one or more external devices 7 (such as a keyboard, a pointing device, etc.). Such communication can be carried out through the input / output (I / O) interface 8. And, the electronic device 3 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 9. As Figure 14 shown, the network adapter 9 communicates with other modules of the electronic device 3 through the bus 6. It should be understood that although Figure 14 not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 3, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (Redundant Array of Independent Disks) systems, tape drives, and data backup storage systems, etc.

[0168] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0169] Embodiment 3

[0170] This embodiment provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements the method for evaluating the quality of cervical vertebra images in Embodiment 1.

[0171] Among them, more specifically, the readable storage medium can include, but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0172] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on an electronic device, the program code is used to cause the electronic device to execute the method for evaluating the quality of cervical spine images in Embodiment 1.

[0173] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the electronic device, partially on the electronic device, executed as an independent software package, partially on the electronic device and partially on a remote device, or entirely on a remote device.

[0174] Although the specific implementation manners of the present invention have been described above, those skilled in the art should understand that this is only an example. The protection scope of the present invention is defined by the appended claims. Without departing from the principles and essence of the present invention, those skilled in the art can make various changes or modifications to these implementation manners, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for evaluating the quality of cervical spine images, characterized in that, it includes the following steps: Obtain the cervical spine image to be evaluated; Identify the shooting position of the cervical spine image; Call an image segmentation model corresponding to the shooting position to segment the cervical spine image, and output a segmentation result corresponding to the shooting position; Evaluate the quality of the cervical spine image according to the characteristics of at least one part in the segmentation result; If the shooting position is the anteroposterior position of the cervical spine, then the evaluation of the quality of the cervical spine image according to the characteristics of at least one part in the segmentation result includes: Judge whether the number of cervical vertebrae in the segmentation result is less than a first preset number; If not, evaluate the quality of the cervical spine image as qualified; If so, evaluate the quality of the cervical spine image as unqualified; Among them, the evaluation of the quality of the cervical spine image as qualified includes: Judge whether the distance between the center point of the cervical vertebrae and the center point of the trachea in the segmentation result is less than a first preset distance, the distance between the center point of the mandible and the center point of the occipital bone in the segmentation result is less than a second preset distance, and the number of cervical vertebrae is a second preset number; where, the center point of the cervical vertebrae is used to represent the central position of all cervical vertebrae, the center point of the trachea is used to represent the central position of the trachea, the center point of the mandible is used to represent the central position of the mandible, and the center point of the occipital bone is used to represent the central position of the occipital bone; the second preset number is greater than the first preset number; If so, evaluate the quality of the cervical spine image as first-level qualified; If not, evaluate the quality of the cervical spine image as second-level qualified.

2. The quality evaluation method according to claim 1, characterized in that, If the shooting position is the lateral position of the cervical spine, then the evaluation of the quality of the cervical spine image according to the characteristics of at least one part in the segmentation result includes: Judge whether the number of cervical vertebrae in the segmentation result is less than a second preset number; If not, evaluate the quality of the cervical spine image as qualified; If so, evaluate the quality of the cervical spine image as unqualified.

3. The quality evaluation method according to claim 2, characterized in that, If the shooting position is the lateral position of the cervical spine, then the evaluation of the quality of the cervical spine image as qualified includes: Judge whether the cervical vertebrae in the segmentation result intersect with the mandible; If not, evaluate the quality of the cervical spine image as first-level qualified; If so, evaluate the quality of the cervical spine image as second-level qualified.

4. The quality evaluation method according to claim 1, characterized in that, If the shooting position is the oblique position of the cervical spine, then the evaluation of the quality of the cervical spine image according to the characteristics of at least one part in the segmentation result includes: Judge whether the number of cervical vertebrae in the segmentation result is less than a second preset number; If not, evaluate the quality of the cervical spine image as qualified; If so, evaluate the quality of the cervical spine image as unqualified.

5. The quality evaluation method according to claim 4, characterized in that, If the imaging position is the cervical oblique position, then evaluating the quality of the cervical vertebra image as qualified includes: Judging whether there are a third preset number of pedicles in the front part of all cervical vertebrae in the segmentation result and the number of intervertebral foramina is a fourth preset number; If so, evaluating the quality of the cervical vertebra image as first-level qualified; If not, evaluating the quality of the cervical vertebra image as second-level qualified.

6. A method for evaluating the quality of a cervical vertebra image, characterized in that, it includes the following steps: Obtain the cervical vertebra image to be evaluated; Identify the imaging position of the cervical vertebra image; Call the image segmentation model corresponding to the imaging position to segment the cervical vertebra image and output the segmentation result corresponding to the imaging position; Evaluate the quality of the cervical vertebra image according to the characteristics of at least one part in the segmentation result; If the imaging position is the anteroposterior position of the cervical vertebra, then evaluating the quality of the cervical vertebra image according to the characteristics of at least one part in the segmentation result includes: Judging whether the distance between the center point of the cervical vertebra body and the center point of the trachea in the segmentation result is greater than a third preset distance; wherein, the center point of the cervical vertebra body is used to represent the central position of all cervical vertebrae, and the center point of the trachea is used to represent the central position of the trachea; If not, evaluating the quality of the cervical vertebra image as qualified; if so, evaluating the quality of the cervical vertebra image as unqualified; Or, Judging whether the distance between the center point of the mandible and the center point of the occipital bone in the segmentation result is greater than a fourth preset distance; wherein, the center point of the mandible is used to represent the central position of the mandible, and the center point of the occipital bone is used to represent the central position of the occipital bone; If not, evaluating the quality of the cervical vertebra image as qualified; if so, evaluating the quality of the cervical vertebra image as unqualified.

7. The quality evaluation method according to claim 6, characterized in that, If the imaging position is the lateral position of the cervical vertebra, then evaluating the quality of the cervical vertebra image according to the characteristics of at least one part in the segmentation result includes: Judging whether the number of cervical vertebra bodies in the segmentation result is less than a second preset number; If not, evaluating the quality of the cervical vertebra image as qualified; If so, evaluating the quality of the cervical vertebra image as unqualified.

8. The quality evaluation method according to claim 7, characterized in that, If the imaging position is the lateral position of the cervical vertebra, then evaluating the quality of the cervical vertebra image as qualified includes: Judging whether the cervical vertebra body in the segmentation result intersects with the mandible; If not, evaluating the quality of the cervical vertebra image as first-level qualified; If so, evaluating the quality of the cervical vertebra image as second-level qualified.

9. The quality evaluation method according to claim 6, characterized in that, If the imaging position is the cervical oblique position, then evaluating the quality of the cervical vertebra image according to the characteristics of at least one part in the segmentation result includes: Judging whether the number of cervical vertebra bodies in the segmentation result is less than a second preset number; If not, evaluating the quality of the cervical vertebra image as qualified; If so, evaluating the quality of the cervical vertebra image as unqualified.

10. The quality evaluation method according to claim 9, characterized in that, if the imaging position is the cervical oblique position, then evaluating the quality of the cervical vertebra image as qualified includes: judging whether there are a third preset number of pedicles in the front part of all cervical vertebrae in the segmentation result and the number of intervertebral foramina is a fourth preset number; if so, evaluating the quality of the cervical vertebra image as first-level qualified; if not, evaluating the quality of the cervical vertebra image as second-level qualified.

11. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, when the processor executes the computer program, the quality evaluation method according to any one of claims 1-10 is implemented.

12. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the quality evaluation method according to any one of claims 1-10 is implemented.

Images