A method, device and equipment for evaluating the width of the subarachnoid space of the optic nerve

Abstract

The application discloses a method, device and equipment for evaluating the width and narrowness degree of the subarachnoid space of the optic nerve, and the method comprises the following steps: collecting a target image corresponding to a target position of the optic nerve, and obtaining the resolution of the target image, wherein the target position is any one of a plurality of preset positions on the optic nerve; dividing the subarachnoid space of the optic nerve in the target image into at least two regions by using at least one division line, the division line passes through the centroid of the optic nerve sheath in the target image, and the target circle central angle is bisected, the target circle central angle is the central angle of a circle with the centroid as the center and an arbitrary length as the radius; evaluating whether the target image meets the first evaluation standard based on the images of the at least two regions and the resolution of the target image; in this way, the defect that the MR image cannot be effectively judged whether it can be used for evaluating the width and narrowness degree of the subarachnoid space of the optic nerve can be solved, and the subarachnoid space of the optic nerve can be equally divided to the maximum extent, so that the final evaluation result is more accurate and more persuasive.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical image analysis, in particular to a method, device and equipment for evaluating the width and narrowness of the subarachnoid space of the optic nerve. BACKGROUND

[0002] In the diagnosis of diseases such as glaucoma, idiopathic intracranial hypertension, high altitude eye disease, space-related eye and skull syndrome, the width and narrowness of the subarachnoid space of the optic nerve is an important means for evaluating the subarachnoid space pressure of the optic nerve and non-invasive intracranial pressure measurement. The width and narrowness of the subarachnoid space of the optic nerve can be obtained from the orbital magnetic resonance (MR) image.

[0003] Because, even in the case of fixation, the human eye still has a small movement at a frequency of several times per second. At the same time of the eye movement, the optic nerve will also move and cause the shape to be tortuous. Therefore, during the scanning process, whether the scanning section is absolutely perpendicular to the running of the optic nerve, and the degree of tortuosity of the optic nerve itself will affect the shape of the optic nerve sheath in the coronal MR image, thereby causing the evaluation of the width and narrowness of the subarachnoid space of the optic nerve to be biased, and affecting the evaluation result of the non-invasive intracranial pressure.

[0004] Therefore, whether the collected MR image can be used to evaluate the width and narrowness of the subarachnoid space of the optic nerve becomes a problem to be solved at present. SUMMARY

[0005] Therefore, the technical problem to be solved by the present application is to overcome the defect that the prior art cannot effectively determine whether the collected MR image can be used to evaluate the width and narrowness of the subarachnoid space of the optic nerve, thereby providing a method, device and equipment for evaluating the width and narrowness of the subarachnoid space of the optic nerve.

[0006] In a first aspect, the present application provides a method for evaluating the width and narrowness of the subarachnoid space of the optic nerve, comprising:

[0007] Collecting a target image corresponding to a target position of the optic nerve, and obtaining the resolution of the target image, the target position being any one of a plurality of preset positions on the optic nerve; dividing the subarachnoid space of the optic nerve in the target image into at least two regions by using at least one division line, the division line passing through the centroid of the optic nerve sheath in the target image and equally dividing the target circle central angle, the target circle central angle being the central angle of a circle with the centroid as the center and an arbitrary length as the radius; and evaluating whether the target image meets a first evaluation standard based on the images of the at least two regions and the resolution of the target image.

[0008] Since the subarachnoid space of the optic nerve in a usable MR image is approximately two concentric annular regions, the size distribution of the annular regions corresponding to each angle is uniform and not significantly different. Therefore, in this invention, when a target image of a certain target location of the optic nerve is acquired, the subarachnoid space of the optic nerve in the target image is divided into at least two regions using at least one dividing line. During segmentation, the dividing line must simultaneously pass through the centroid and equally bisect the central angle subtended by a circle with the centroid as its center and an arbitrary length as its radius. In this way, the subarachnoid space of the optic nerve can be divided at equal angles. Then, based on the images of the at least two divided regions, and combined with the resolution of the target image, the target image is evaluated to determine whether it meets the first evaluation criterion. This method allows us to obtain the size of at least two subarachnoid space regions corresponding to the same angle. When the size distribution of the at least two segmented regions is relatively uniform, it indicates that the current target image meets the first evaluation criterion and satisfies the prerequisite for image usability. Therefore, we can conclude that the target image can be used to assess the width of the subarachnoid space, resolving the current limitation of not being able to effectively determine whether MR images can be used to assess the width of the subarachnoid space. Furthermore, the final conclusion is obtained through calculation, making the final evaluation result more accurate and convincing.

[0009] In conjunction with the first aspect, in a first embodiment of the first aspect, evaluating whether a target image meets a first evaluation criterion based on the resolution of images of at least two regions and the target image includes:

[0010] Obtain the number of pixel blocks contained in the image of each region; determine the area of ​​each region based on the number of pixel blocks contained in the image of each region and the resolution of the target image; evaluate whether the target image meets the first evaluation criterion based on the area of ​​each region.

[0011] In conjunction with the first aspect, in the second embodiment of the first aspect, obtaining the number of pixel blocks contained in the image of each region includes:

[0012] Obtain the coordinates of each pixel block and the function corresponding to at least one dividing line; determine the number of pixel blocks contained in each region based on the coordinates of the pixel blocks and the function corresponding to at least one dividing line.

[0013] In conjunction with the first aspect, in the third embodiment of the first aspect, assessing whether the target image meets the first assessment criterion based on the area of ​​each region includes:

[0014] The standard deviation of the area is determined based on the area of ​​all regions; the target image is then evaluated based on the standard deviation to determine whether it meets the first evaluation criterion.

[0015] In this embodiment, the standard deviation of the area reflects the degree of difference in the size of at least two areas. The evaluation result determined based on the size of the standard deviation is more objective and accurate.

[0016] In conjunction with the first aspect, in the fourth embodiment of the first aspect, after evaluating whether the target image meets the first evaluation criterion based on the resolution of the images of at least two regions and the target image, the method further includes:

[0017] When the target image meets the first evaluation criteria, and the target position corresponding to the target image is not the first or last preset position on the optic nerve, the first image and the second image corresponding to the two preset positions adjacent to the target position are obtained respectively; based on the centroid of the optic nerve sheath in the target image, the first image and the second image are used to evaluate whether the target image meets the second evaluation criteria.

[0018] In conjunction with the first aspect, in a fifth embodiment of the first aspect, the evaluation of whether the target image meets the second evaluation criterion based on the centroid of the optic nerve sheath in the target image, the first image, and the second image includes:

[0019] Obtain the centroid of the optic nerve sheath in the first image and the second image; determine the curvature at the target location based on the centroid of the optic nerve sheath in the target image, the centroid of the optic nerve sheath in the first image, and the centroid of the optic nerve sheath in the second image; evaluate whether the target image meets the second evaluation criteria based on the curvature.

[0020] In this embodiment, provided that the target image meets the first evaluation criterion, the curvature of the target position is also needed to further determine whether the target image meets the second evaluation criterion. In this way, the target image can be screened and evaluated more accurately. This invention can not only solve the defect in the prior art that it is not possible to effectively determine whether the acquired MR image can be used to evaluate the width of the optic nerve subarachnoid space, but also improve the accuracy of the evaluation results, so that the final diagnostic results based on the MR image are more accurate.

[0021] In conjunction with the first aspect, in the sixth embodiment of the first aspect, evaluating whether a target image meets the second evaluation criterion based on curvature includes:

[0022] The curvature at the target location is compared with a preset curvature threshold; when the curvature is less than the preset curvature threshold, the target image meets the second evaluation criterion.

[0023] Secondly, the present invention provides a device for assessing the width of the subarachnoid space of the optic nerve, comprising:

[0024] The acquisition module is used to acquire a target image at the target location of the optic nerve and obtain the resolution of the target image. The target location is any one of multiple preset locations on the optic nerve. The segmentation module is used to divide the subarachnoid space of the optic nerve in the target image into at least two regions using at least one segmentation line. The segmentation line passes through the centroid of the optic nerve sheath in the target image and bisects the target central angle equally. The target central angle is the central angle of a circle with the centroid as the center and an arbitrary length as the radius. The first evaluation module is used to evaluate whether the target image meets the first evaluation criteria based on the resolution of the images of at least two regions and the target image.

[0025] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory being used to store a computer program, and when the computer program is executed by the processor, causing the processor to perform a method for assessing the width of the subarachnoid space of the optic nerve as described in any of the invention.

[0026] Fourthly, the present invention provides a computer-readable storage medium for storing computer instructions that, when executed by a processor, implement a method for assessing the width of the subarachnoid space of the optic nerve as described in any of the claims of the present invention. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 A flowchart illustrating a method for assessing the width of the subarachnoid space of the optic nerve, provided in an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the sagittal view of the eye provided in an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of the coronal slice corresponding to positioning 1 provided in an embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of the coronal slice corresponding to location 2 provided in an embodiment of the present invention;

[0032] Figure 5 This is a schematic diagram of the subarachnoid space of the optic nerve in the target image provided in an embodiment of the present invention;

[0033] Figure 6This is a schematic diagram of region division provided in an embodiment of the present invention;

[0034] Figure 7 The present invention provides a schematic diagram of the distribution of the subarachnoid region of the optic nerve.

[0035] Figure 8 A flowchart for determining whether a target image meets a first evaluation criterion, provided in an embodiment of the present invention;

[0036] Figure 9 A flowchart for determining the number of pixel blocks in each region of an image provided in an embodiment of the present invention;

[0037] Figure 10 A connection diagram of the device for assessing the width of the subarachnoid space of the optic nerve provided in an embodiment of the present invention;

[0038] Figure 11 This is a computer device connection diagram provided for an embodiment of the present invention. Detailed Implementation

[0039] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Before providing a detailed description of the invention, a brief illustration and explanation of the acquired MR images will be given to facilitate understanding of this solution. For example... Figure 2 The image shown is a schematic diagram of the eye in the sagittal plane, including the eyeball, optic nerve, and two slice locations on the optic nerve. Figure 2 The vertical lines in the diagram intersect the optic nerve at locations 1 and 2, respectively.

[0041] Figure 3 Is Figure 2 The slice image taken at location 1 of the optic nerve shows the outer circle representing the optic nerve sheath, the inner circle representing the optic nerve, and the annular area between the two circles representing the subarachnoid space of the optic nerve. Figure 3 The morphology of the middle optic nerve and optic nerve sheath is normal (approximately concentric circles), and the width of the optic nerve subarachnoid space is uniform; furthermore, in the coronal plane, the tortuosity of the optic nerve sheath at location 1 is small, therefore... Figure 3 It can be used to assess the width of the subarachnoid space of the optic nerve.

[0042] Figure 4 Is Figure 2The slice image taken at location 2 of the optic nerve shows that the optic nerve and optic sheath are elliptical in shape due to curvature, and the width of the subarachnoid space of the optic nerve varies significantly at different angles. Therefore... Figure 4 It cannot be used to assess the width of the subarachnoid space of the optic nerve.

[0043] This invention discloses a method for assessing the width of the subarachnoid space of the optic nerve, such as... Figure 1 As shown, the specific steps include the following:

[0044] Step S1: Acquire the corresponding target image at the target location of the optic nerve and obtain the resolution of the target image.

[0045] Specifically, after a sagittal MRI scan of the head, a coronal image is obtained by scanning at the target location behind the optic nerve and in a direction perpendicular to the optic nerve. The resolution information of the target image is then acquired. The target location is any one of several preset locations on the optic nerve, determined by the scan thickness during MRI.

[0046] In an optional embodiment, to obtain images clearly showing the optic nerve and optic sheath, a HASTE (Half-Fourier-Acquired Single-shot Turbo spin Echo) sequence combined with SPAIR (Spectral Attenuated Inversion Recovery) pulse technology can be used to perform a T2-weighted MR image fat-suppressed scanning sequence to obtain sagittal MR images of the head. In the scanned images, the cerebrospinal fluid shows a bright signal, the optic nerve parenchyma shows a dark signal, and the intraorbital segment of the optic sheath (i.e., the subarachnoid region) shows a bright signal.

[0047] For specific scanning parameters, please refer to the following: TR (Repetition Time) = 1830ms; TE (Echo Time) = 167ms; Imaging Matrix = 448×448; Flip Angle = 150°; Slice Thickness = 3mm; Slice Interval = 3.9mm; Pixel Spacing = 0.3125mm×0.3125mm; FOV (Field of View) = 140mm×140mm. These parameters are for reference only. In actual image acquisition, any sequence setting that clearly displays the intraorbital segment of the optic nerve's subarachnoid space can be used.

[0048] In oblique sagittal MR images, taking the right eye as an example, since the thickness of an MRI scan is 3 mm, coronal images (the target image) can be acquired at any of six preset positions: 0 mm, 3 mm, 6 mm, 9 mm, 12 mm, and 15 mm behind the eyeball, perpendicular to the optic nerve (or parallel to the tangent at the junction of the eyeball and the optic nerve). In this example, the last preset position is 15 mm because, generally, the area beyond 15 mm is already at the posterior edge of the orbit, after which the optic nerve connects to the optic chiasm and enters the cranium, no longer belonging to the orbital region. Therefore, 15 mm is generally considered the last preset acquisition position on the optic nerve.

[0049] After obtaining the target image at the target location, the resolution information of the target image is retrieved from the DICOM (Digital Imaging and Communications in Medicine) header information, such as:

[0050] X_VoxelSize=ImageFile.hdr.dime.pixdim(2);

[0051] Y_VoxelSize=ImageFile.hdr.dime.pixdim(3);

[0052] Here, ImageFile represents the imported image, and X_VoxelSize and Y_VoxelSize represent the spatial resolution in the X and Y directions, respectively, in millimeters per pixel.

[0053] Step S2: Using at least one dividing line, divide the subarachnoid space of the optic nerve in the target image into at least two regions.

[0054] Specifically, after obtaining the target image, it is necessary to first identify the optic nerve sheath, the optic nerve, and the subarachnoid space region of the optic nerve within the target image, such as... Figure 5 As shown, the outer periphery represents the scanned outline of the optic nerve sheath, the inner periphery represents the scanned outline of the optic nerve, and the annular portion between the outer and inner peripheries represents the subarachnoid space of the optic nerve. Then, the subarachnoid space of the optic nerve is divided into at least two regions using at least one dividing line. During this process, the dividing line must simultaneously satisfy two conditions: it must pass through the centroid of the optic nerve sheath in the target image and bisect the target central angle, which is the central angle of a circle with the centroid as its center and an arbitrary radius.

[0055] In one specific embodiment, a target image was acquired at a distance of 3 mm from the optic nerve. The specific distribution of the optic nerve sheath, optic nerve, and subarachnoid space of the optic nerve in the target image is as follows: Figure 5As shown. First, the centroid of the optic nerve sheath is determined based on its outline; then, the subarachnoid space of the optic nerve is divided into six regions using three straight lines passing through the centroid and bisecting the central angle of the target circle, as shown. Figure 6 As shown, the black dot represents the centroid of the optic nerve sheath. The subarachnoid space of the optic nerve, represented by the ring-shaped area, is divided into six parts.

[0056] Step S3: Evaluate whether the target image meets the first evaluation criterion based on the resolution of the images of at least two regions and the target image.

[0057] Specifically, after dividing the optic nerve subarachnoid space into at least two regions, the size difference between the at least two regions is determined based on the resolution of the images of the at least two regions and the target image. The target image is then judged to meet a first evaluation criterion based on the size difference between the at least two regions corresponding to the same angle. The first evaluation criterion is a difference threshold between regions of the optic nerve subarachnoid space corresponding to the same angle. When the size difference between the at least two regions is less than the difference threshold, the target image meets the first evaluation criterion, meaning it can be used to assess the width of the optic nerve subarachnoid space. When the size difference between the at least two regions is greater than or equal to the difference threshold, the target image does not meet the first evaluation criterion, meaning it cannot be used to assess the width of the optic nerve subarachnoid space.

[0058] Since the subarachnoid space of the optic nerve in a usable MR image is approximately two concentric annular regions, the size distribution of the annular regions corresponding to each angle is uniform and not significantly different. Therefore, in this invention, when a target image of a certain target location of the optic nerve is acquired, the subarachnoid space of the optic nerve in the target image is divided into at least two regions using at least one dividing line. During segmentation, the dividing line must simultaneously pass through the centroid and equally bisect the central angle subtended by a circle with the centroid as its center and an arbitrary length as its radius. In this way, the subarachnoid space of the optic nerve can be divided at equal angles. Then, based on the images of the at least two divided regions, and combined with the resolution of the target image, the target image is evaluated to determine whether it meets the first evaluation criterion. This method allows us to obtain the size of at least two subarachnoid space regions corresponding to the same angle. When the size distribution of the at least two segmented regions is relatively uniform, it indicates that the current target image meets the first evaluation criterion and satisfies the prerequisite for image usability. Therefore, we can conclude that the target image can be used to assess the width of the subarachnoid space, resolving the current limitation of not being able to effectively determine whether MR images can be used to assess the width of the subarachnoid space. Furthermore, the final conclusion is obtained through calculation, making the final evaluation result more accurate and convincing.

[0059] In an optional embodiment, the target image is evaluated based on the resolution of the images of at least two regions and the target image to determine whether it meets a first evaluation criterion, such as... Figure 8 As shown, the steps include: The following method steps are detailed below, including:

[0060] Step S81: Obtain the number of pixel blocks contained in the image of each region; wherein, the method of obtaining the number of pixel blocks is not limited to, directly determining the number of pixel blocks completely covered by the image of each region, or obtaining the number of pixel blocks based on the region where the center of each pixel block is located.

[0061] Step S82: Determine the area of ​​each region based on the number of pixel blocks contained in the image of each region and the resolution of the target image. The resolution indicates the length and width dimensions of each pixel block (i.e., X_VoxelSize and Y_VoxelSize). Therefore, the area of ​​each region is the product of the length and width of the pixel block and the number of pixel blocks contained in that region.

[0062] Step S83: Evaluate whether the target image meets the first evaluation criterion based on the area of ​​each region. Specifically, after obtaining the area of ​​each region, the degree of difference between the areas of each region can be determined based on the areas of all regions. The degree of difference and a preset difference threshold are used to determine whether the target image meets the first evaluation criterion. The degree of difference can be represented by mathematical characteristics that can be used to measure data fluctuations, such as the standard deviation or variance of the area. The difference threshold is calculated based on a large number of MR images available for evaluating the width of the optic nerve subarachnoid space.

[0063] In an optional embodiment, the number of pixel blocks contained in the image of each region is obtained, and the specific implementation process is as follows: Figure 9 As shown, it includes the following steps:

[0064] Step S91: Obtain the coordinates of each pixel block and the function corresponding to at least one segmentation line. Specifically, the coordinates of a pixel block include, but are not limited to, using the coordinates of the center of the pixel block as its coordinates, or using the coordinates of a vertex of the pixel block as its coordinates. The function corresponding to the segmentation line can be obtained based on the coordinates of the points on the segmentation line. In this process, the coordinate system can be a pre-built coordinate system in the system or a custom coordinate system, such as a coordinate system with the centroid of the optic nerve sheath in the coronal image at 0 mm as the origin, the direction of any radius as the X-axis, the direction perpendicular to the X-axis and passing through the centroid as the Y-axis, and the direction perpendicular to the coronal image at 0 mm as the Z-axis.

[0065] Exemplarily, still taking the previous embodiment as an example, in the target image, the centroid coordinates are (x0, y0), and the three functions corresponding to the three dividing lines are respectively:

[0066] y1 = tan60°·(x1 - x0) + y0

[0067] y2 = tan(-60°)·(x1 - x0) + y0

[0068] y3 = y0

[0069] These 3 dividing lines that meet the conditions divide the subarachnoid space of the optic nerve into 6 regions, and the distribution of the 6 regions is as Figure 7 shown.

[0070] Step S92: Determine the number of pixel blocks included in each region based on the coordinates of the pixel blocks and the function corresponding to at least one dividing line. Specifically, according to the coordinates of the pixel blocks and the function corresponding to each dividing line, determine the region where the pixel block is located. After determining the regions where all the pixel blocks included in the subarachnoid space of the optic nerve are located, the number of pixel blocks included in the image of each region can be known.

[0071] Exemplarily, for example, the coordinates of a certain pixel block are (x, y). Now it is necessary to determine the region where the pixel block is located. The specific determination method is as follows:

[0072] When y ≥ y0 and y < y1, the pixel block (x, y) belongs to partition 1;

[0073] When y ≥ y1 and y < y2, the pixel block (x, y) belongs to partition 2;

[0074] When y ≤ y2 and y > y0, the pixel block (x, y) belongs to partition 3;

[0075] When y ≤ y0 and y > y1, the pixel block (x, y) belongs to partition 4;

[0076] When y ≤ y1 and y < y2, the pixel block (x, y) belongs to partition 5;

[0077] When y ≤ y2 and y < y0, the pixel block (x, y) belongs to partition 6.

[0078] In an optional embodiment, based on the area of each region, evaluate whether the target image meets the first evaluation criterion, including:

[0079] Determine the standard deviation of the area based on the areas of all regions; evaluate whether the target image meets the first evaluation criterion based on the standard deviation.

[0080] For example, after obtaining the area of ​​each region, the standard deviation is calculated based on the area of ​​each region. When the standard deviation is greater than or equal to a preset standard deviation threshold, it is determined that the target image does not meet the first evaluation standard, and the image cannot be used to evaluate the width of the optic nerve subarachnoid space. When the standard deviation is less than the preset standard deviation threshold, it is determined that the target image meets the first evaluation standard, and further judgment can be made to determine whether the image can be used to evaluate the width of the optic nerve subarachnoid space.

[0081] For example, still using the above embodiment as an example, after calculation, the areas of the six regions of the optic nerve subarachnoid space in the target image are obtained as follows: 1.56, 0.98, 1.56, 1.66, 1.07, and 1.56. The standard deviation of the six regions is determined to be approximately 0.29; the preset standard deviation threshold is 0.1. Since 0.29 > 0.1, this target image cannot be used to assess the width of the optic nerve subarachnoid space.

[0082] In this embodiment, the standard deviation of the area reflects the degree of difference in the size of at least two areas. The evaluation result determined based on the size of the standard deviation is more objective and accurate.

[0083] In an optional embodiment, after evaluating whether the target image meets the first evaluation criterion based on the resolution of the images of at least two regions and the target image, the method further includes:

[0084] When the target image meets the first evaluation criteria, and the target position corresponding to the target image is not the first or last preset position on the optic nerve, the first image and the second image corresponding to the two preset positions adjacent to the target position are obtained respectively; based on the centroid of the optic nerve sheath in the target image, the first image and the second image are used to evaluate whether the target image meets the second evaluation criteria.

[0085] For example, when the target image meets the first evaluation criteria, it can be further determined whether the target position corresponding to the target image is the first preset position or the last preset position on the optic nerve.

[0086] When the target image is not the first or last preset location on the optic nerve, it is also necessary to evaluate whether the target image meets the second evaluation criterion. The second evaluation criterion is a threshold used to measure the degree of tortuosity of the optic nerve at the target location. This threshold is obtained by measuring the degree of tortuosity at the acquisition location of a large number of images that can be used to assess the width of the optic nerve's subarachnoid space. When evaluating whether the target image meets the second evaluation criterion, it is necessary to combine the images corresponding to the two preset locations adjacent to the target location, namely the first image and the second image. The degree of tortuosity of the target image at the target location is determined by the centroid of the target image, the first image, and the second image, thereby evaluating whether the target image meets the second evaluation criterion.

[0087] In an optional embodiment, the evaluation of whether the target image meets a second evaluation criterion is based on the centroid of the optic nerve sheath in the target image, using the first image and the second image, including:

[0088] Obtain the centroid of the optic nerve sheath in the first image and the second image; determine the curvature at the target location based on the centroid of the optic nerve sheath in the target image, the centroid of the optic nerve sheath in the first image, and the centroid of the optic nerve sheath in the second image; evaluate whether the target image meets the second evaluation criteria based on the curvature.

[0089] For example, after obtaining the first image and the second image corresponding to two preset positions adjacent to the target position, firstly, the centroid coordinates of the nerve sheath in the target image are obtained, and the centroid corresponding to the target image is determined as the target centroid. The centroid of the optic nerve sheath in the first image is determined according to the contour of the optic nerve sheath in the first image, i.e., the first centroid, and the coordinates of the first centroid are obtained. Similarly, the centroid of the nerve sheath in the second image is determined according to the contour of the optic nerve sheath in the second image, i.e., the second centroid, and the coordinates of the second centroid are obtained.

[0090] Then, based on the coordinates of the target centroid, the coordinates of the first centroid, and the coordinates of the second centroid, a circle passing through the first centroid, the second centroid, and the target centroid is determined, and the radius of the circle is obtained. Based on this radius, the curvature of the optic nerve at the target location is determined.

[0091] Since a circle can only be defined by three non-collinear points on the same plane, the curvature of the optic nerve at the target location cannot be determined when the target location is the first or last preset location of the optic nerve. Therefore, when the target image is the first or last preset location on the optic nerve, it is not necessary to determine the curvature at the target location; the ability to assess the width of the optic nerve's subarachnoid space can be determined directly based on whether the target image meets the first evaluation criteria.

[0092] In one specific embodiment, when the target image acquired at 3 mm from the optic nerve meets the first evaluation criteria, the first image and the second image corresponding to 0 mm and 6 mm from the optic nerve, respectively, are obtained. Based on the first centroid (223, 217, 0) of the first image, the target centroid (228, 220, 3) of the target image, and the second centroid (229, 222, 6) of the second image, a circle passing through the three centroids is determined based on their coordinates, and the radius of this circle is obtained. The radius is approximately 2.85 mm. Based on the radius, the curvature at the target location is determined to be approximately 0.35, where the curvature and radius are reciprocals of each other.

[0093] Finally, the curvature of the optic nerve at the target location is used to assess whether the target image meets the second evaluation criteria.

[0094] In this embodiment, provided that the target image meets the first evaluation criterion, the curvature of the target position is also needed to further determine whether the target image meets the second evaluation criterion. In this way, the target image can be screened and evaluated more accurately. This invention can not only solve the defect in the prior art that it is not possible to effectively determine whether the acquired MR image can be used to evaluate the width of the optic nerve subarachnoid space, but also improve the accuracy of the evaluation results, so that the final diagnostic results based on the MR image are more accurate.

[0095] In an optional embodiment, evaluating whether a target image meets a second evaluation criterion based on curvature includes:

[0096] Compare the curvature at the target location with a preset curvature threshold;

[0097] When the curvature is less than the preset curvature threshold, the target image meets the second evaluation criterion.

[0098] For example, after obtaining the curvature of the optic nerve at the target location, the curvature at the target location is compared with a preset curvature threshold. When the curvature is less than the preset curvature threshold, the target image meets the second evaluation criterion, and it is determined that the image can be used to evaluate the width of the optic nerve subarachnoid space. When the curvature is greater than or equal to the preset curvature threshold, the target image does not meet the second evaluation criterion, and it is determined that the image cannot be used to evaluate the width of the optic nerve subarachnoid space.

[0099] For example, continuing with the previous embodiment, after determining that the curvature at the target location is 0.35, this curvature is compared with a preset curvature threshold. In this embodiment, the preset curvature threshold is 0.5. Since 0.35 < 0.5, the target image meets the second evaluation criterion, and the target image can be used to evaluate the width of the optic nerve subarachnoid space. At this point, the evaluation operation on the target image ends.

[0100] This invention discloses a device for assessing the width of the subarachnoid space of the optic nerve, such as... Figure 10 As shown, it specifically includes the following modules:

[0101] The acquisition module 101 is used to acquire a target image at the target location of the optic nerve and obtain the resolution of the target image. The target location is any one of multiple preset locations on the optic nerve.

[0102] The segmentation module 102 is used to divide the subarachnoid space of the optic nerve in the target image into at least two regions using at least one segmentation line. The segmentation line passes through the centroid of the optic nerve sheath in the target image and bisects the target central angle equally. The target central angle is the central angle of a circle with the centroid as the center and an arbitrary length as the radius.

[0103] The first evaluation module 103 is used to evaluate whether the target image meets the first evaluation criterion based on the resolution of the images of at least two regions and the target image.

[0104] In an optional embodiment, the first evaluation module 103 includes:

[0105] The acquisition submodule 1031 is used to acquire the number of pixel blocks contained in the image of each region; the determination submodule 1032 is used to determine the area of ​​each region based on the number of pixel blocks contained in the image of each region and the resolution of the target image; the evaluation submodule 1033 is used to evaluate whether the target image meets the first evaluation criterion based on the area of ​​each region.

[0106] In an optional embodiment, the acquisition submodule 1031 includes:

[0107] The acquisition unit 10311 is used to acquire the coordinates of each pixel block and the function corresponding to at least one dividing line; the determination unit 10322 is used to determine the number of pixel blocks contained in each region based on the coordinates of the pixel blocks and the function corresponding to at least one dividing line.

[0108] In an optional embodiment, the evaluation submodule 1033 includes:

[0109] The determination unit 10331 is used to determine the standard deviation of the area based on the area of ​​all regions; the evaluation unit 10332 is used to evaluate whether the target image meets the first evaluation criterion based on the standard deviation.

[0110] In an optional embodiment, after the first evaluation module 103, the following is further included:

[0111] The acquisition module 104 is used to acquire the first image and the second image corresponding to two preset positions adjacent to the target position when the target image meets the first evaluation criteria and the target position corresponding to the target image is not the first preset position or the last preset position on the optic nerve; the second evaluation module 105 is used to evaluate whether the target image meets the second evaluation criteria based on the centroid of the optic nerve sheath in the target image, the first image and the second image.

[0112] In an optional embodiment, the second evaluation module 105 includes:

[0113] The acquisition submodule 1051 is used to acquire the centroid of the optic nerve sheath in the first image and the centroid of the optic nerve sheath in the second image; the determination submodule 1052 is used to determine the curvature at the target location based on the centroid of the optic nerve sheath in the target image, the centroid of the optic nerve sheath in the first image, and the centroid of the optic nerve sheath in the second image; and the evaluation submodule 1053 is used to evaluate whether the target image meets the second evaluation criteria based on the curvature.

[0114] In an optional embodiment, the evaluation submodule 1053 includes:

[0115] The comparison unit 10531 is used to compare the curvature at the target position with a preset curvature threshold; the evaluation unit 10532 is used to determine that the target image meets the second evaluation criterion when the curvature is less than the preset curvature threshold.

[0116] This embodiment provides a computer device, such as... Figure 11 As shown, the computer device may include at least one processor 111, at least one communication interface 112, at least one communication bus 113, and at least one memory 114. The communication interface 112 may include a display screen and a keyboard; optionally, the communication interface 112 may also include a standard wired interface or a wireless interface. The memory 114 may be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk drive. Optionally, the memory 114 may also be at least one storage device located remotely from the aforementioned processor 111. The processor 111 may be combined with... Figure 11 The described apparatus has an application program stored in memory 114, and a processor 111 calls the program code stored in memory 114 to perform a method for evaluating the width of the optic nerve subarachnoid space in any of the above method embodiments.

[0117] The communication bus 113 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 113 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 11 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0118] The memory 114 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 114 may also include a combination of the above types of memory.

[0119] The processor 111 can be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.

[0120] The processor 111 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. Optionally, the memory 114 is also used to store program instructions. The processor 111 can invoke the program instructions to implement the method for evaluating the width of the subarachnoid space of the optic nerve in any embodiment of the present invention.

[0121] This embodiment provides a computer-readable storage medium storing computer-executable instructions that can execute the method for assessing the width of the subarachnoid space of the optic nerve in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0122] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for assessing the width of the subarachnoid space of the optic nerve, characterized in that, include: Acquire a target image at the target location on the optic nerve and obtain the resolution of the target image. The target location is any one of a plurality of preset locations on the optic nerve. Using at least one dividing line, the subarachnoid space of the optic nerve in the target image is divided into at least two regions. The dividing line passes through the centroid of the optic nerve sheath in the target image and bisects the target central angle equally. The target central angle is the central angle of a circle with the centroid as its center and an arbitrary length as its radius. The resolution of the target image is used to evaluate whether the target image meets the first evaluation criterion; the first evaluation criterion is the difference threshold between regions of the optic nerve subarachnoid space corresponding to the same angle.

2. The method for assessing the width of the subarachnoid space of the optic nerve according to claim 1, characterized in that, The evaluation of whether the target image meets the first evaluation criterion based on the resolution of the images of the at least two regions and the target image includes: Get the number of pixel blocks contained in the image of each region; The area of ​​each region is determined based on the number of pixel blocks contained in the image of each region and the resolution of the target image; The target image is evaluated based on the area of ​​each region to determine whether it meets the first evaluation criterion.

3. The method for assessing the width of the subarachnoid space of the optic nerve according to claim 2, characterized in that, The process of obtaining the number of pixel blocks contained in the image of each region includes: Obtain the coordinates of each pixel block and the function corresponding to the at least one dividing line; The number of pixel blocks contained in each region is determined based on the coordinates of the pixel blocks and the function corresponding to the at least one dividing line.

4. The method for assessing the width of the subarachnoid space of the optic nerve according to claim 2, characterized in that, The step of evaluating whether the target image meets the first evaluation criterion based on the area of ​​each of the regions includes: The standard deviation of the area is determined based on the area of ​​all the said regions; The target image is evaluated based on the standard deviation to determine whether it meets the first evaluation criterion.

5. The method for assessing the width of the subarachnoid space of the optic nerve according to claim 1, characterized in that, After evaluating whether the target image meets the first evaluation criterion based on the resolution of the images of the at least two regions and the target image, the method further includes: When the target image meets the first evaluation criteria, and the target position corresponding to the target image is not the first or last preset position on the optic nerve, the first image and the second image corresponding to the two preset positions adjacent to the target position are obtained respectively. Based on the centroid of the optic nerve sheath in the target image, the first image and the second image evaluate whether the target image meets a second evaluation criterion; the second evaluation criterion is a threshold used to measure the degree of tortuosity of the optic nerve at the target location.

6. The method for assessing the width of the subarachnoid space of the optic nerve according to claim 5, characterized in that, The evaluation of whether the target image meets the second evaluation criterion based on the centroid of the optic nerve sheath in the target image, using the first image and the second image, includes: Obtain the centroid of the optic nerve sheath in the first image and the centroid of the optic nerve sheath in the second image; Based on the centroid of the optic nerve sheath in the target image, the curvature at the target location is determined by the centroid of the optic nerve sheath in the first image and the centroid of the optic nerve sheath in the second image. The curvature is used to assess whether the target image meets the second evaluation criterion.

7. The method for assessing the width of the subarachnoid space of the optic nerve according to claim 6, characterized in that, The step of evaluating whether the target image meets the second evaluation criterion based on the curvature includes: Compare the curvature at the target location with a preset curvature threshold. When the curvature is less than the preset curvature threshold, the target image meets the second evaluation criterion.

8. A device for assessing the width of the subarachnoid space of the optic nerve, characterized in that, include: The acquisition module is used to acquire a target image at a target location on the optic nerve and obtain the resolution of the target image, wherein the target location is any one of a plurality of preset locations on the optic nerve; A segmentation module is used to divide the optic nerve subarachnoid space in the target image into at least two regions using at least one segmentation line. The segmentation line passes through the centroid of the optic nerve sheath in the target image and bisects the target central angle equally. The target central angle is the central angle of a circle with the centroid as its center and an arbitrary length as its radius. The first evaluation module is used to evaluate whether the target image meets a first evaluation criterion based on the resolution of the images of the at least two regions and the target image; the first evaluation criterion is the difference threshold between regions of the optic nerve subarachnoid space corresponding to the same angle.

9. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory being used to store a computer program, which, when executed by the processor, causes the processor to perform a method for assessing the width of the subarachnoid space of the optic nerve as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store computer instructions that, when executed by a processor, implement the method for assessing the width of the subarachnoid space of the optic nerve as described in any one of claims 1 to 7.

Images