Measurement systems, methods, electronic devices, and non-transitory machine-readable storage media for expressing the morphological development characteristics of the orbital bone wall.

Abstract

This application relates to a measurement system, measurement method, electronic device, and non-transitory machine-readable storage medium for expressing the morphological development characteristics of the orbital bone wall. This measurement system can automatically identify the orbital contour, superior rectus muscle contour, inferior rectus muscle contour, medial rectus muscle contour, and lateral rectus muscle contour, and output a ratio curve expressing the morphological development characteristics of the orbital bone wall, providing a more valuable reference for the diagnosis of congenital orbital variations, analysis of orbital decompression surgery procedures, and selection of precision.

Description

Technical Field

[0001] This application belongs to the field of medical imaging, and in particular relates to a measurement system, measurement method, electronic device, and non-transitory machine-readable storage medium for expressing the morphological development characteristics of the orbital bone wall. Background Technology

[0002] Thyroid-associated ophthalmopathy (TAO) is a common orbital disease in adults, generally considered an organ-specific autoimmune disease associated with thyroid disease. Proptosis (exophthalmos) is one of the symptoms of TAO, often accompanied by eyelid retraction, eyelid swelling, and conjunctival redness. It not only affects appearance but also impairs vision, thus reducing the user's quality of life.

[0003] In related technologies, examinations for thyroid exophthalmos include routine eye examinations, CT scans, and MRI scans. CT scans require doctors to manually annotate and analyze each CT slice to determine if the extraocular muscles are hypertrophied and if the lesion involves the muscle belly. Surgical treatment for thyroid exophthalmos, known as orbital decompression surgery, essentially involves increasing the orbital volume to allow the eyeball to retract. Determining how to remove the orbital bone wall to minimize damage while achieving the same degree of volume expansion requires quantitative analysis of the orbital bone wall's morphological development characteristics before precisely planning the surgical location and extent. The orbit is a cone-shaped structure, wider at the front and narrower at the back. The shape and curvature of the orbital bone wall vary from person to person. While three-dimensional reconstructions of the orbital bone wall can be clearly displayed on CT scans, there is currently no technology to evaluate these features using a unified measurement standard. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this application provides a measurement system and method for expressing the morphological development characteristics of the orbital bone wall. This measurement system can automatically identify the orbital contour, superior rectus muscle contour, inferior rectus muscle contour, medial rectus muscle contour, and lateral rectus muscle contour, and output a ratio curve expressing the morphological development characteristics of the orbital bone wall, providing a more valuable reference for the diagnosis of congenital orbital variations, analysis of orbital decompression surgery procedures, and selection of precision.

[0005] This application provides a measurement system for expressing the morphological development characteristics of the orbital bone wall, comprising: an orbital image cutting module, an orbital contour marking module, an extraocular muscle contour marking module, an orbital quadrant segmentation module, and a terminal; the orbital image cutting module pre-customizes the cutting of the volumetric image generated by CT scan: starting from the most concave point of the outer margin of both orbits, and perpendicular to the midline of the superior and inferior orbital walls, the image is continuously cut backward with a predetermined thickness and interval, ending at the orbital apex where the four extraocular muscles are tightly attached, and outputting a coronal plane image; the coronal plane image is output to the orbital contour marking module, which predicts the orbital contour and marks the orbital quadrant on the coronal plane image. The orbital contour is generated; the coronal plane image is output to the extraocular muscle contour marking module, which predicts the extraocular muscle contour and marks it on the coronal plane image; the orbital quadrant segmentation module calculates the centroid using the extraocular muscle contour, segments the orbital contour longitudinally by connecting the centroids of the superior and inferior rectus muscles, and segments the orbital contour horizontally by connecting the centroids of the medial and lateral rectus muscles, dividing the orbital contour into four quadrants: superior medial quadrant, inferior medial quadrant, inferior lateral quadrant, and superior lateral quadrant, and calculates the area of ​​each quadrant; the ratio curve is obtained by dividing 1 / 4 of the eyeball cross-sectional area by the area of ​​each quadrant and output to the terminal.

[0006] Preferably, the orbital contours of the left and right eyes on the coronal image are manually marked, and the marked coronal image is output to the orbital contour marking module; the orbital contour marking module is based on a deep learning algorithm, and after self-training with the manually marked coronal image as a reference, it accurately predicts the orbital contour, and the program parameters are set.

[0007] Preferably, the contours of the superior rectus muscle, inferior rectus muscle, medial rectus muscle, and lateral rectus muscle of the left and right eyes are manually marked on the coronal image, and the marked coronal image is output to the extraocular muscle contour marking module; the extraocular muscle contour marking module is based on a deep learning algorithm, and after self-training with the manually marked image as a reference, it accurately predicts the extraocular muscle contour, and the program parameters are set.

[0008] Preferably, the predetermined thickness and spacing of the pre-customized cut image are both 1 mm, and the output coronal plane image is in bmp or jpg format.

[0009] The second aspect of this application provides a measurement method for expressing the morphological development characteristics of the orbital bone wall, including:

[0010] S1: The orbital image cutting module pre-customizes the cutting of the volumetric image formed by CT scan. Starting from the most concave point of the outer edge of the orbit on both sides, the module cuts the image continuously backward with a predetermined thickness and interval in a direction perpendicular to the midline of the superior and inferior orbital walls, until the four extraocular muscles of the orbital apex are tightly attached together, and outputs a coronal plane image.

[0011] S2: Input the coronal plane image output from S1 to the orbital contour marking module to mark the orbital contours of the left and right eyes; input the coronal plane image output from S1 to the extraocular muscle contour marking module to mark the superior rectus muscle contour, inferior rectus muscle contour, medial rectus muscle contour, and lateral rectus muscle contour of the left and right eyes; output the marked coronal plane image to the processing module.

[0012] S3: The processing module calculates the centroids of the superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours of the left and right eyes, respectively, and takes two lines that pass through the centroids of the superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours, respectively, to divide the orbital contour into 4 quadrants.

[0013] S4: Take the diameter of the eyeball and calculate 1 / 4 of the cross-sectional area of ​​the eyeball; calculate the area of ​​the upper inner quadrant, lower inner quadrant, lower outer quadrant, and upper outer quadrant of the left and right eyes; divide 1 / 4 of the cross-sectional area of ​​the eyeball in each quadrant by the area of ​​that quadrant to obtain the ratio curve for each quadrant.

[0014] Preferably, in S1, the bony orbital contours of the left and right eyes, as well as the contours of the superior rectus muscle, inferior rectus muscle, medial rectus muscle, and lateral rectus muscle of the left and right eyes, are marked using Labbel Me software.

[0015] Preferably, in S1, the pre-customized cut image of the orbital image is manually annotated. The manually annotated coronal image is then input to the orbital contour marking module and the extraocular muscle contour marking module for deep learning. After deep learning, the orbital contour marking module accurately predicts the orbital contour, and the extraocular muscle contour marking module accurately predicts the contours of the superior rectus muscle, inferior rectus muscle, medial rectus muscle, and lateral rectus muscle. Program parameters are then set.

[0016] Preferably, specifically, the coronal plane images of the manually annotated left and right eye orbital contours are input into the orbital contour marking module as a learning reference. After self-learning, the orbital contour marking module accurately predicts the orbital contour. The coronal plane images of the manually annotated superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours of the left and right eyes are input into the extraocular muscle contour marking module as a learning reference. After self-learning, the extraocular muscle contour marking module accurately predicts the superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours of the left and right eyes. Parameter settings are then performed for the orbital contour, superior rectus muscle contour, inferior rectus muscle contour, medial rectus muscle contour, and lateral rectus muscle contour.

[0017] A third aspect of this application provides an electronic device, comprising:

[0018] A processor; and a memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described above.

[0019] A fourth aspect of this application provides a non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0020] The technical solution provided in this application may include the following beneficial effects:

[0021] 1. This measurement system, which expresses the morphological development characteristics of the orbital bone wall, outputs a ratio curve, providing a quantitative analysis tool for the morphological development characteristics of the orbital bone wall. At the same time, it reduces the time and effort doctors spend on annotation, enables accurate annotation, reduces annotation costs, and reduces the occurrence of missed diagnoses and misdiagnoses, thus providing a quantitative tool for disease analysis.

[0022] 2. The ratio curve output by the measurement system that expresses the morphological development characteristics of the orbital bone wall provides a fully quantitative reference for the resection range and location in the surgical treatment of thyroid exophthalmos, and solves the current problems in my country such as the imbalance between supply and demand of high-quality medical resources, long doctor training cycles, and high misdiagnosis rates.

[0023] 3. Establish a database of orbital bone wall morphology and development characteristics, as well as successful orbital decompression surgeries, to provide predictable data for orbital decompression resection.

[0024] 4. The measurement system that expresses the morphological development characteristics of the orbital bone wall outputs a ratio curve, which can be used to fully quantify the shallow orbit.

[0025] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0026] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0027] Figure 1 This is a schematic diagram of the structure of a measurement system for expressing the morphological development characteristics of the orbital bone wall, as shown in an embodiment of this application;

[0028] Figure 2 This is a schematic diagram of the orbital quadrant segmentation module of the measurement system for expressing the morphological development characteristics of the orbital bone wall, as shown in the embodiments of this application, performing quadrant segmentation on the coronal plane image;

[0029] Figure 3 This is a flowchart illustrating a measurement method for expressing the morphological development characteristics of the orbital bone wall, as shown in an embodiment of this application.

[0030] Figure 4 This is the positioning step 1 of a measurement method for expressing the morphological development characteristics of the orbital bone wall, as illustrated in the embodiments of this application. Figure 1 Structural diagram;

[0031] Figure 5 This is the positioning step 1 of a measurement method for expressing the morphological development characteristics of the orbital bone wall, as illustrated in the embodiments of this application. Figure 2 Structural diagram;

[0032] Figure 6 This is a schematic diagram of the coronal plane output from step 1 of a measurement method for expressing the morphological development characteristics of the orbital bone wall, as illustrated in an embodiment of this application.

[0033] Figure 7 This is a schematic diagram of the orbital contour marking module, illustrating a measurement method for expressing the morphological development characteristics of the orbital bone wall, as shown in an embodiment of this application.

[0034] Figure 8 This is a schematic diagram of the extraocular muscle contour marking module, illustrating a measurement method for expressing the morphological development characteristics of the orbital bone wall, as shown in an embodiment of this application.

[0035] Figure 9 This is a ratio curve output from a coronal plane image of a patient before surgery, illustrating a measurement method for expressing the morphological development characteristics of the orbital bone wall as shown in an embodiment of this application.

[0036] Figure 10 yes Figure 9 A ratio curve output from the coronal plane image of a patient after surgery;

[0037] Figure 11 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0038] Preferred embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0039] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0040] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0041] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0042] This application relates to a measurement system and method for expressing the morphological development characteristics of the orbital bone wall, including a bone orbital contour marking module, an extraocular muscle contour marking module, and an orbital quadrant segmentation module. It calculates 1 / 4 of the cross-sectional area of ​​the eyeball divided by the area of ​​each quadrant of the orbit to obtain a depth-ratio curve, which expresses the morphological development characteristics of the orbital bone wall and provides a more valuable reference for the diagnosis of congenital orbital variations, the analysis of orbital decompression surgery procedures, and the selection of precision.

[0043] See Figure 1 This application proposes a measurement system for expressing the morphological development characteristics of the orbital bone wall, including an orbital image cutting module, an orbital contour marking module, an extraocular muscle contour marking module, an orbital quadrant segmentation module, a processing module, and a terminal.

[0044] The orbital image cutting module acquires images of the eye region and eye position information from CT scans, cuts them, and outputs a coronal image. The module pre-customizes the image cutting from the volumetric image generated by the CT scan, starting from the most concave point of the outer orbital margins on both sides, and cutting continuously backward at predetermined thicknesses and intervals along a direction perpendicular to the midline of the superior and inferior orbital walls, until the four extraocular muscles at the orbital apex are tightly joined together, outputting a coronal image. The predetermined continuous images have a thickness and interval of 1 mm, and the output coronal image is in bmp or jpg format.

[0045] The orbital contour marking module predicts the orbital contour from the coronal plane image output by the orbital image segmentation module and marks the orbital contour on the coronal plane image. Before prediction, this orbital contour marking module undergoes deep learning, enabling it to accurately predict the orbital contour on the coronal plane image and mark it on the input coronal plane image. Specifically, the left and right bony orbital contours are manually marked before and after surgery, and the final coronal plane image is output to the orbital contour marking module. The orbital contour marking module, based on a deep learning algorithm, uses the manually marked images as a reference and undergoes self-training to accurately predict the orbital contour, and sets parameters accordingly. The coronal plane image of the segmented target image is output to the orbital contour marking module, which predicts the orbital contour and marks it on the coronal plane image. In this embodiment, the deep learning algorithm is implemented using a convolutional neural network, the number of manually marked images exceeds 1430, and the number of self-training iterations exceeds 20,000. Manual annotation can be performed using LabelMe software.

[0046] The extraocular muscle contour marking module predicts the extraocular muscle contours from the coronal plane image output by the orbital image segmentation module and marks the extraocular muscle contours on the coronal plane image. Before prediction, this module undergoes deep learning, enabling it to accurately predict the extraocular muscle contours on the coronal plane image and mark them on the input coronal plane image. Specifically, the contours of the superior rectus muscle, inferior rectus muscle, medial rectus muscle, and lateral rectus muscle of the left and right eyes are manually marked, and the coronal plane image is finally output to the extraocular muscle contour marking module. Based on a deep learning algorithm, the module undergoes self-training using the manually marked image as a reference to accurately predict the extraocular muscle contours, and program parameters are set. The coronal plane image of the segmented target image is output to the extraocular muscle contour marking module, which predicts the extraocular muscle contours and marks them on the coronal plane image. In this embodiment, the deep learning algorithm is implemented using a convolutional neural network, the number of manually labeled images exceeds 1430, and the number of self-training iterations exceeds 20,000. Labelme software can be used for manual labeling.

[0047] The orbital quadrant segmentation module segments the coronal plane image after predicting the orbital contour and extraocular muscle contour, and outputs the segmented coronal plane image to the processing module for further processing. Specifically, the orbital quadrant segmentation module calculates the centroid using the extraocular muscle contour, segments the orbital contour longitudinally along the line connecting the centroids of the superior and inferior rectus muscles, and segments the orbital contour horizontally along the line connecting the centroids of the medial and lateral rectus muscles, as shown below. Figure 2 As shown, the orbital contour is divided into four quadrants: upper inner quadrant 1, lower inner quadrant 2, lower outer quadrant 3, and upper outer quadrant 4. The segmented coronal plane image is then output to the processing module. In this embodiment, OpenCV is used to obtain the centroid of the multi-contour image, and the centroid coordinates are displayed on the output image.

[0048] The processing module performs calculations on the coronal image that has already undergone orbital quadrant segmentation. It calculates the area of ​​the upper inner quadrant, lower inner quadrant, lower outer quadrant, and upper outer quadrant of the orbital contour, dividing both eyes into eight quadrants. By dividing one-quarter of the eyeball area by the area of ​​each quadrant, eight depth-ratio curves are obtained for both eyes and output to the terminal. Figure 9 As shown, the ratio curve represents the ratio of one-quarter of the eyeball's cross-sectional area divided by the area of ​​a specific quadrant at a given point. This specific point is the location of the horizontal axis. The unit of the horizontal axis is millimeters, indicating that the image is segmented every millimeter. The morphology of the orbital bone walls varies from person to person. The orbital walls form the orbit, and the size of the orbital volume is only meaningful when considered in relation to the volume of the eyeball within the orbit. Therefore, the formula uses one-quarter of the eyeball's cross-sectional area divided by the area of ​​a specific quadrant at a given point. This allows for comparisons between the volumes of each quadrant and with other individuals.

[0049] The ratio curve received and output by the terminal expresses the morphological development characteristics of the orbital bone wall, providing a more valuable reference for the diagnosis of congenital orbital variations, analysis of orbital decompression techniques, and precision selection.

[0050] This application discloses a measurement method for expressing the morphological development characteristics of the orbital bone wall, such as... Figure 3 As shown, the measurement method of this application generally includes several major steps: image cropping, manual annotation, deep learning, program parameter setting, target image cropping, orbital contour and extraocular muscle contour marking, orbital quadrant segmentation, calculation of eyeball cross-sectional area and orbital quadrant area, and output of ratio curve. Specifically:

[0051] Step 1, S1: Starting from the most concave point of the outer edge of both orbits, cut the image continuously backward at 1mm intervals, perpendicular to the midline of the superior and inferior orbital walls, until the four extraocular muscles at the orbital apex are tightly joined. Export the image in BMP or JPG format. Use LabBel ME software to annotate the orbital contours of the left and right eyes, as well as the contours of the superior, inferior, medial, and lateral rectus muscles of both eyes. For example... Figure 4 As shown in the diagram, point O is the most concave point on the outer edge of the eye socket. Taking the most concave points on both sides of the outer edge of the eye socket as the starting point, as... Figure 5 As shown, perpendicular to the midline L of the superior and inferior orbital walls, the image is continuously sliced ​​posteriorly at 1mm thickness and 1mm intervals until the four extraocular muscles at the orbital apex are tightly joined together, outputting a coronal image, as shown. Figure 6 As shown.

[0052] Step 2, S2: Input the manually annotated left and right eye socket contour images from S1 into the eye socket contour marking module as a learning reference. After multiple self-learning sessions, the eye socket contour marking module achieves accurate prediction of the eye socket contour, such as... Figure 7 As shown, set the program parameters. Input the manually annotated contour images of the superior, inferior, medial, and lateral rectus muscles of the left and right eyes from S1 into the extraocular muscle contour marking module for learning and reference. After multiple self-learning sessions, the extraocular muscle contour marking module accurately predicts the contours of the superior, inferior, medial, and lateral rectus muscles of the left and right eyes, as shown. Figure 8 As shown, set the program parameters.

[0053] Step 3, S3: Segmentation of the target image. Output the segmented coronal plane image to the orbital contour marking module and the extraocular muscle contour marking module for marking the orbital contour and extraocular muscle contour.

[0054] Step 4, S4: Based on the contours of the superior rectus, inferior rectus, medial rectus, and lateral rectus muscles of the left and right eyes respectively, find the centroids of the superior rectus, inferior rectus, medial rectus, and lateral rectus muscles of the left and right eyes respectively. Take two lines that pass through the centroids of the superior rectus and inferior rectus muscles, and the centroids of the medial rectus and lateral rectus muscles respectively, and divide the orbital contour into 4 quadrants.

[0055] Step 5, S5: Take the diameter of the eyeball and calculate 1 / 4 of its cross-sectional area. Calculate the areas of the upper inner quadrant, lower inner quadrant, lower outer quadrant, and upper outer quadrant for both the left and right eyes. Divide 1 / 4 of the eyeball's cross-sectional area by the area of ​​each quadrant to obtain the depth-ratio curve for each quadrant.

[0056] Current orbital decompression surgery is based on the doctor's subjective feeling to remove the lesion. With the measurement system that expresses the characteristics of orbital bone wall morphology and development, we can accurately know where (orbital bone wall development) is the key to causing orbital volume narrowing, and then precisely remove the lesion, reducing the scope of surgical damage and achieving the same effect.

[0057] Specifically, such as Figure 9 As shown, the patient's preoperative left orbital structure indicates excessive curvature of the medial and inferior orbital walls, resulting in insufficient volume in the inferior medial and inferior outer quadrants. The horizontal line represents a curve with a ratio of 1, which is 1 / 4 of the ocular interface. Figure 10 As shown in the data, the patient's left orbit after surgery can be seen to have had its medial wall expanded, but the inferior wall was not expanded.

[0058] This application first uses manually labeled images as a reference for the deep learning algorithm's training. After multiple rounds of self-learning and training, it can accurately predict the orbital contour and extraocular muscle contour. The orbital contour refers to the entire outline of the bone surrounding the orbital contents as shown on a segmented CT planar image, commonly referred to in this field as the orbital contour. Manually labeling the orbital contour involves manually drawing the edges, while the orbital contour labeling module, after training, can automatically predict the orbital contour edges and derive the corresponding contour parameters, thus labeling the orbital contour. The deep learning algorithm used here is an existing convolutional neural network, which can be executed using Python. Through repeated experiments, it was found that using more than 1430 manually labeled images as a reference and conducting more than 20,000 training iterations achieves the best learning and training results.

[0059] This application divides an orbit into four quadrants and uses a univariate function: depth-ratio curve to reflect the narrowness of each quadrant, indirectly reflecting the curvature of the orbital bone wall: the steeper the curve, the greater the curvature of the corresponding bone wall, and the narrower the orbital volume of the corresponding quadrant; the shorter the total length of the curve, the shallower the orbit; the earlier the curve crosses the horizontal line of ratio 1, the closer the place where the curvature of the corresponding bone wall increases is to the orbital opening.

[0060] This application has the following beneficial effects:

[0061] 1. To provide a quantitative analysis tool for the morphological development of the orbital bone wall.

[0062] 2. The surgical resection range and location for Graves' ophthalmopathy, providing a fully quantitative reference.

[0063] 3. Establish a database of orbital bone wall development morphology and successful orbital decompression surgeries to provide predictable data for orbital decompression resection.

[0064] 4. Fully quantify the definition of shallow eye sockets.

[0065] Figure 11 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0066] See Figure 11 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0067] The processor 1020 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0068] Memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by the processor 1020 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 1010 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0069] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to execute part or all of the methods described above.

[0070] The solution of this application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of each embodiment have different emphases; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. Those skilled in the art should also understand that the actions and modules involved in the specification are not necessarily essential to this application. Furthermore, it is understood that the steps in the method of this application embodiment can be adjusted, combined, and deleted according to actual needs, and the modules in the device of this application embodiment can be combined, divided, and deleted according to actual needs.

[0071] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0072] Alternatively, this application may be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) storing executable code (or computer program, or computer instruction code) that, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform some or all of the steps of the methods described above according to this application.

[0073] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the present application can be implemented as electronic hardware, computer software, or a combination of both.

[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0075] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A measurement system for expressing the morphological development characteristics of the orbital bone wall, characterized in that, include: The module includes an orbital image cropping module, an orbital contour marking module, an extraocular muscle contour marking module, an orbital quadrant segmentation module, and a terminal. The orbital image cutting module pre-customizes the cutting of the volumetric image formed by CT scan: taking the most concave point of the outer edge of the orbit as the starting point, and cutting the image continuously backward with a predetermined thickness and interval in a direction perpendicular to the midline of the superior and inferior orbital walls, until the four extraocular muscles of the orbital apex are tightly attached together, and outputting a coronal plane image. The coronal image is output to the orbital contour marking module, which predicts the orbital contour and marks the orbital contour on the coronal image. The coronal plane image is output to the extraocular muscle contour marking module, which predicts the extraocular muscle contour and marks the extraocular muscle contour on the coronal plane image. The orbital quadrant segmentation module calculates the centroid using the extraocular muscle contour. It vertically segments the orbital contour by connecting the centroids of the superior and inferior rectus muscles, and horizontally segments it by connecting the centroids of the medial and lateral rectus muscles. The orbital contour is divided into four quadrants: upper inner quadrant, lower inner quadrant, lower outer quadrant, and upper outer quadrant. The area of ​​each quadrant is calculated. A ratio curve is obtained by dividing one-quarter of the eyeball cross-sectional area by the area of ​​each quadrant, and then output to the terminal.

2. The measurement system for expressing the morphological development characteristics of the orbital bone wall according to claim 1, characterized in that: The orbital contours of the left and right eyes on the coronal image are manually marked, and the marked coronal image is output to the orbital contour marking module. The orbital contour marking module is based on a deep learning algorithm, which uses the manually marked coronal image as a reference and performs self-training to accurately predict the orbital contour. The program parameters are set accordingly.

3. The measurement system for expressing the morphological development characteristics of the orbital bone wall according to claim 1, characterized in that: The contours of the superior rectus muscle, inferior rectus muscle, medial rectus muscle, and lateral rectus muscle of the left and right eyes are manually labeled on the coronal image, and the labeled coronal image is output to the extraocular muscle contour labeling module. The extraocular muscle contour labeling module is based on a deep learning algorithm, which uses the manually labeled image as a reference and performs self-training to accurately predict the extraocular muscle contour. The program parameters are set accordingly.

4. The measurement system for expressing the morphological development characteristics of the orbital bone wall according to claim 1, characterized in that: The pre-customized cut image has a predetermined thickness and spacing of 1 mm, and the output coronal plane image is in bmp or jpg format.

5. A measurement method for expressing the morphological development characteristics of the orbital bone wall, characterized in that, include: S1: The orbital image cutting module pre-customizes the cutting of the volumetric image formed by CT scan. Starting from the most concave point of the outer edge of the orbit on both sides, the image is continuously cut backward with a predetermined thickness and interval in a direction perpendicular to the midline of the superior and inferior orbital walls, until the four extraocular muscles of the orbital apex are tightly attached together, and the coronal plane image is output. S2: Input the coronal plane image output from S1 to the orbital contour marking module to mark the orbital contours of the left and right eyes; input the coronal plane image output from S1 to the extraocular muscle contour marking module to mark the superior rectus muscle contour, inferior rectus muscle contour, medial rectus muscle contour, and lateral rectus muscle contour of the left and right eyes; output the marked coronal plane image to the processing module. S3: The processing module calculates the centroids of the superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours of the left and right eyes, respectively, and takes two lines that pass through the centroids of the superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours, respectively, to divide the orbital contour into 4 quadrants. S4: Take the diameter of the eyeball and calculate 1 / 4 of the cross-sectional area of ​​the eyeball; calculate the area of ​​the upper inner quadrant, lower inner quadrant, lower outer quadrant, and upper outer quadrant of the left and right eyes; divide 1 / 4 of the cross-sectional area of ​​the eyeball in each quadrant by the area of ​​that quadrant to obtain the ratio curve for each quadrant.

6. The measurement method for expressing the morphological development characteristics of the orbital bone wall according to claim 5, characterized in that: In S1, the bony orbital contours of the left and right eyes, as well as the contours of the superior rectus muscle, inferior rectus muscle, medial rectus muscle, and lateral rectus muscle of the left and right eyes, were marked using Labbel Me software.

7. The measurement method for expressing the morphological development characteristics of the orbital bone wall according to claim 5, characterized in that: In S1, the pre-customized cut images of the orbital image segmentation module are manually annotated. The manually annotated coronal plane image is then input into the orbital contour marking module and the extraocular muscle contour marking module for deep learning. After deep learning, the orbital contour marking module accurately predicts the orbital contour, and the extraocular muscle contour marking module accurately predicts the contours of the superior rectus muscle, inferior rectus muscle, medial rectus muscle, and lateral rectus muscle. Program parameters are then set.

8. The measurement method for expressing the morphological development characteristics of the orbital bone wall according to claim 7, characterized in that: Specifically, the coronal plane images of the manually annotated left and right eye orbital contours are input into the orbital contour marking module as a learning reference. After self-learning, the orbital contour marking module accurately predicts the orbital contour. The coronal plane images of the manually annotated superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours of the left and right eyes are input into the extraocular muscle contour marking module as a learning reference. After self-learning, the extraocular muscle contour marking module accurately predicts the superior rectus muscle contours, inferior rectus muscle contours, medial rectus muscle contours, and lateral rectus muscle contours of the left and right eyes. Parameter settings are then performed for the orbital contour, superior rectus muscle contour, inferior rectus muscle contour, medial rectus muscle contour, and lateral rectus muscle contour.

9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 5-8.

10. A non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 5-8.

Images