Method and apparatus for evaluating stenosis in spinal canal and nerve root canal

Abstract

The present invention pertains to a stenosis evaluation method implemented by a processor, comprising the steps of: acquiring a medical image by photographing the spine of an individual; dividing a region for evaluating spinal stenosis in the medical image by using a division model trained to divide the region for evaluating spinal stenosis by using the medical image as an input; and calculating, on the basis of the divided region, the size of a section in which spinal stenosis of the individual can be evaluated.

Description

Methods and devices for evaluating stenosis in the spinal and nerve root canals

[0001] The present invention relates to a method and device for evaluating stenosis in the spinal canal and nerve root canal.

[0002] Diagnosis and treatment of patients are performed based on medical images captured by various medical imaging devices such as radiography (or X-ray), ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET).

[0003] Among these, MRI images required to diagnose a patient's spine number over 500 per patient, requiring doctors to identify lesions in approximately 24 vertebral bodies from hundreds of images. Diagnosing the spine through MRI takes longer to interpret and diagnose than other body parts, reducing the efficiency of the overall diagnostic process. Furthermore, even with identical images, interpretation can vary depending on the medical team's skill level, potentially leading to misdiagnosis. Various methods are being proposed to address these issues.

[0004] For example, AI model-based diagnostic systems have been proposed, utilizing AI models trained to segment specific regions of medical images based on preset segmentation criteria. While these systems can improve diagnostic process efficiency and reduce medical costs, their reliance solely on learned data limits their ability to provide helpful information to medical professionals in making diagnoses.

[0005] The background technology of the invention has been prepared to facilitate a better understanding of the present invention. It should not be construed as an admission that the matters described in the background technology of the invention constitute prior art.

[0006] In particular, with regard to spinal stenosis, conventional methods only detect the location where spinal stenosis is occurring through an artificial intelligence model or provide fragmentary results by dividing the stages of stenosis progression, which limits the provision of information that is practically helpful for medical professionals' diagnosis.

[0007] Therefore, a new method is required to segment the spinal canal and the neural root canal in MRI images of the abdomen and to evaluate the degree of progression of stenosis in the spinal canal and the neural root canal.

[0008] As a result, the inventors of the present invention sought to develop a method and device capable of evaluating the degree of stenosis progression in the spinal canal and nerve root canal through an algorithm that segments the spinal canal and nerve root canal regions in an axial MRI image and calculates the change in thickness of the spinal canal and nerve root canal in consecutive slices.

[0009] The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below.

[0010] In order to solve the above-described problem, a method for evaluating spinal stenosis in a spinal canal and a nerve root canal according to an embodiment of the present invention is provided. The method is a stenosis evaluation method implemented by a processor, and is configured to include the steps of: acquiring a medical image of a spine of an individual; using a segmentation model learned to segment an area for evaluating spinal stenosis by inputting the medical image, segmenting the area for evaluating spinal stenosis in the medical image; and calculating the size of an area capable of evaluating spinal stenosis of the individual based on the segmented area.

[0011] According to a feature of the present invention, the step of acquiring the medical image is a step of acquiring a cross-sectional (axial plane) medical image of the object, and the segmentation model may be a model learned to segment one spinal canal region and two nerve root canal regions by inputting the cross-sectional medical image.

[0012] According to another feature of the present invention, the step of calculating the size may be a step of calculating the thickness for a plurality of points designated based on one direction in each of the divided spinal canal region and the nerve root canal region.

[0013] According to another feature of the present invention, the step of calculating the size may further include the step of determining a center line on a cross section in each of the divided spinal canal region and the nerve root canal region, and the step of determining a plurality of thickness evaluation lines for diagnosing stenosis, which extend in a direction perpendicular to the center line.

[0014] According to another feature of the present invention, the step of calculating the size may further include the step of calculating the size change for the plurality of thickness evaluation lines using the plurality of slides constituting the medical image.

[0015] According to another feature of the present invention, the step of calculating the size change may further include a step of determining whether the size change value in at least one thickness evaluation line among the plurality of thickness evaluation lines is greater than or equal to a preset value.

[0016] According to another feature of the present invention, after the judging step, a step of distinguishing the type of spinal stenosis evaluation may be further included according to the position of the thickness evaluation line where the size change value is greater than or equal to a preset value.

[0017] According to another feature of the present invention, the step of calculating the size change may further include a step of determining the progression (grade) of spinal stenosis of the object according to the size change based on a preset evaluation value.

[0018] According to another feature of the present invention, the step of acquiring the medical image may further include a step of acquiring a sagittal plane or coronal plane medical image of the object, and after the calculating step, if there is a thickness evaluation line in which the size change value is greater than or equal to a preset value, the step of determining a spinal position at which the size change value is observed based on the sagittal plane or coronal plane medical image may further include.

[0019] According to another feature of the present invention, the preset evaluation value matching the size change value may have different values ​​depending on the arrangement position of the thickness evaluation line and the spine position.

[0020] In order to solve the above-described problem, a device for evaluating spinal stenosis in a spinal canal and a nerve root canal according to another embodiment of the present invention is provided. The device includes a communication interface, a memory, and a processor operably connected to the communication interface and the memory, wherein the processor is configured to acquire a medical image of a spine of an individual, segment the medical image into a region for evaluating spinal stenosis using a segmentation model learned to segment a region for evaluating spinal stenosis using the medical image as an input, and calculate the size of the area capable of evaluating spinal stenosis of the individual based on the segmented region.

[0021] In order to solve the above-described problem, a computer program stored in a computer-readable recording medium according to another embodiment of the present invention is provided. The program is a computer program stored in a computer-readable recording medium for executing a method for evaluating stenosis in a spinal canal and a nerve root canal, the method comprising the steps of: acquiring a medical image of a spine of an individual; segmenting an area for evaluating spinal stenosis in the medical image using a segmentation model learned to segment an area for evaluating spinal stenosis by inputting the medical image through the processor; and calculating, through the processor, the size of an area capable of evaluating spinal stenosis of the individual based on the segmented area.

[0022] Specific details of other embodiments are included in the detailed description and drawings.

[0023] The present invention goes beyond simply indicating the area where the spine and nerve root canal exist, and can provide numerical values ​​that serve as a basis for diagnosing stenosis in the spinal canal and nerve root canal.

[0024] The present invention can increase the reliability of medical staff in a device that provides stenosis evaluation results by providing and displaying numerical values ​​that serve as a basis for diagnosing stenosis in medical images.

[0025] The present invention assesses the degree of stenosis through an algorithm that calculates changes in the thickness of the spinal canal and nerve root canal. This effectively shortens the diagnostic process, which previously required medical professionals to visually inspect hundreds of medical images to determine changes in the thickness of the spinal canal and nerve root canal. Furthermore, this shortened diagnostic process allows medical professionals to treat more patients, and patients can reduce waiting times for treatment.

[0026] The effects according to the present invention are not limited to those exemplified above, and more diverse effects are included within the present invention.

[0027] FIG. 1 is a schematic diagram illustrating a stenosis evaluation system in a spinal canal and a nerve root canal according to one embodiment of the present invention.

[0028] Figure 2 is a block diagram showing the configuration of a stenosis evaluation device according to one embodiment of the present invention.

[0029] Figure 3 is a schematic flowchart of a method for evaluating stenosis in the spinal canal and nerve root canal according to one embodiment of the present invention.

[0030] FIG. 4 is a schematic diagram for explaining a segmentation model performed in a stenosis evaluation device according to one embodiment of the present invention.

[0031] FIG. 5a and FIG. 5b are schematic diagrams for explaining a method for calculating the size of a spinal canal and a nerve root canal performed in a stenosis evaluation device according to one embodiment of the present invention.

[0032] FIG. 6 is an example of an interface screen showing the results of a stenosis evaluation according to one embodiment of the present invention.

[0033] The advantages and features of the present invention, and the methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms. These embodiments are provided solely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. In connection with the description of the drawings, similar reference numerals may be used for similar components.

[0034] In this document, the expressions "has," "may have," "includes," or "may include" indicate the presence of a feature (e.g., a number, function, operation, or component such as a part), but do not exclude the presence of additional features.

[0035] In this document, the expressions "A or B," "at least one of A and / or B," or "one or more of A or / and B" can include all possible combinations of the listed items. For example, "A or B," "at least one of A and B," or "at least one of A or B" can all refer to cases where (1) at least one A is included, (2) at least one B is included, or (3) at least one A and at least one B are included.

[0036] The terms "first," "second," "first," or "second," as used herein, may describe various components, regardless of order and / or importance, and are only used to distinguish one component from another, without limiting the components. For example, a first user device and a second user device may represent different user devices, regardless of order or importance. For example, without departing from the scope of the rights set forth in this document, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

[0037] When it is said that a component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the component is directly coupled to the other component, or can be connected via another component (e.g., a third component). Conversely, when it is said that a component (e.g., a first component) is "directly coupled to" or "directly connected to" another component (e.g., a second component), it should be understood that no other component (e.g., a third component) exists between the first component and the other component.

[0038] The expression "configured to" as used herein can be used interchangeably with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" does not necessarily mean something is "specifically designed to" in hardware. Instead, in some contexts, the expression "a device configured to" can mean that the device, together with other devices or components, is "capable of." For example, the phrase "a processor configured (or set) to perform A, B, and C" may mean a dedicated processor (e.g., an embedded processor) for performing those operations, or a general-purpose processor (e.g., a CPU or application processor) that can perform those operations by executing one or more software programs stored in a memory device.

[0039] The terms used in this document are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this document. Terms defined in general dictionaries among the terms used in this document may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this document. In some cases, even if a term is defined in this document, it cannot be interpreted to exclude the embodiments of this document.

[0040] The individual features of the various embodiments of the present invention can be partially or wholly combined or combined with each other, and as can be fully understood by those skilled in the art, various technical connections and operations are possible, and each embodiment can be implemented independently of each other or can be implemented together in a related relationship.

[0041] For clarity in the interpretation of this specification, the terms used in this specification are defined below.

[0042] As used herein, the term "subject" may refer to any subject for which spinal stenosis is to be evaluated. For example, the subject may be a subject suspected of having spinal stenosis. As used herein, the term "subject" may include any mammal, including humans.

[0043] As used herein, the term "medical image" refers to a medical image of an individual's upper body captured by an imaging device, which may include the spinal region. For example, the medical image may be an axial plane medical image, which may include the spinal canal region and the adjacent nerve root canal region.

[0044] In addition, the medical image may be a two-dimensional image, a three-dimensional image, a single still image, or a video composed of multiple cuts. For example, if the medical image is a video composed of multiple cuts, the spinal canal and nerve root canal regions may be segmented for each of the multiple medical images according to the stenosis evaluation method according to an embodiment of the present invention, and then the spinal stenosis evaluation may be performed. As a result, the present invention can perform an evaluation of the stenosis simultaneously with the reception of the medical image from the imaging device, thereby providing information necessary for the diagnosis of the stenosis in real time.

[0045] As used herein, the term "segmentation model" may be a model configured to determine and segment the boundaries of the spinal canal and the radicular canal in medical images to assess spinal stenosis. Accordingly, the segmentation model may be a model trained to segment one spinal canal region and two radicular canal regions by inputting a cross-sectional medical image of an individual.

[0046] In various embodiments, the segmentation model may be a YOLO-based model capable of detecting and segmenting a specific object. In addition, the segmentation model may be composed of at least one model or two or more ensemble models from among VGG net, R, DenseNet based on CNN (Convolutional Neural Network), FCN (Fully Convolutional Network) with an encoder-decoder structure, SegNet, DeconvNet, DeepLAB V3+, U-net, DNN (deep neural network), SqueezeNet, Alexnet, ResNet18, MobileNet-v2, GoogLeNet, Resnet50, Resnet101, Inception-v3, or a model based on RNN (Recurrent Neural Network).

[0047] In various embodiments, the segmentation model may be a model comprising or consisting of a combination of a mathematical model learned based on statistics, a machine learning model, an artificial neural network model, and a reinforcement learning model.

[0048] FIG. 1 is a schematic diagram illustrating a stenosis evaluation system in a spinal canal and a nerve root canal according to one embodiment of the present invention.

[0049] Referring to FIG. 1, a stenosis evaluation system (1000) is a system configured to evaluate spinal stenosis in a medical image taken of the spine of an individual, and may include an imaging device (100) and a stenosis evaluation device (200) that evaluates spinal stenosis.

[0050] The imaging device (100) may be a device capable of acquiring a medical image of a target area of ​​an object (hereinafter, referred to as an "object") (10), such as a human or an animal. The imaging device (100) may include a cylindrical bore (110) into which the object (10) is introduced, a transport device (130) in which the object (10) is seated, and which transports the object (10) inside. In one embodiment of the present invention, the target area may include the spine, and among the cervical, thoracic, and lumbar vertebrae.

[0051] In addition, the imaging device (100) can obtain medical images in three-axis directions by irradiating an X-ray capable of projecting an object (10) toward the subject or irradiating a high frequency using a magnetic field toward the subject. For example, the imaging device (100) can obtain CT and MRI medical images in the axial plane, sagittal plane, and coronal plane. In addition, the imaging device (100) can obtain medical images such as a two-dimensional image, a single still image, and a video composed of multiple cuts.

[0052] The stenosis evaluation device (200) may be a device capable of acquiring a medical image of a subject from an imaging device (100) and evaluating the degree of spinal stenosis based on the acquired image. Specifically, the stenosis evaluation device (200) may be a device carried by a medical professional diagnosing a subject (10), and may include a PC, tablet PC, smartphone, etc. capable of performing deep learning on medical images and receiving and analyzing medical images.

[0053] In various embodiments, the stenosis assessment device (200) can segment a spinal canal region and two radicular canal regions from a medical image of an individual. Specifically, the stenosis assessment device (200) can segment regions composed of rectangular masks or pixel units corresponding to the spinal canal and two radicular canals from a plurality of cross-sectional medical images.

[0054] In various embodiments, the stenosis assessment device (200) can calculate the size of the area in which stenosis can be assessed based on the segmented area. Specifically, the stenosis assessment device (200) can measure the thickness of the spinal canal and the nerve root canal, and can calculate the change in the thickness of the spinal canal and the nerve root canal based on the acquisition of multiple segmented areas through multiple cross-sectional medical images.

[0055] In various embodiments, the stenosis evaluation device (200) can provide various evaluation results to medical staff based on the calculated thickness change. Specifically, the stenosis evaluation device (200) can provide overall spinal stenosis evaluation results including the cervical spine (C-spine), thoracic spine (T-spine), and lumbar spine (L-spine), or can provide evaluation results at specific points. For example, the stenosis evaluation device (200) can provide specific evaluation results to medical staff, such as “grade 1 stenosis calculated at T1,” “diagnosis of spinal canal and nerve root canal around T1 is required,” and “difference value of NM slide 3rd evaluation line is -2.3,” along with segmented medical images.

[0056] In various embodiments, the stenosis evaluation device (200) may include a configuration of an imaging device (100), in which case the stenosis evaluation device (200) may transmit the results of the spinal stenosis evaluation to a separately connected medical device (not shown).

[0057] So far, a stenosis evaluation system (1000) according to one embodiment of the present invention has been described. According to the present invention, the stenosis evaluation system (1000) goes beyond simply displaying and providing areas where the spine and nerve root canal exist, and provides numerical values ​​that serve as a basis for diagnosing stenosis of the spine and nerve root canal, thereby providing meaningful information that is helpful for medical staff's diagnosis.

[0058] Hereinafter, a stenosis evaluation device (200) owned by medical staff for evaluating spinal stenosis will be described with reference to FIGS. 2 to 6b.

[0059] Figure 2 is a block diagram showing the configuration of a stenosis evaluation device according to one embodiment of the present invention.

[0060] Referring to FIG. 2, the stenosis evaluation device (200) may include a communication interface (210), a memory (220), an I / O interface (230), and a processor (240), each component of which may communicate with each other through one or more communication buses or signal lines.

[0061] The communication interface (210) can be connected to the imaging device (100) via a wired / wireless communication network to exchange data. For example, the communication interface (210) can receive a medical image of the spine of an object from the imaging device (100). As another example, the communication interface (210) can receive training data of a segmentation model trained to segment an area for evaluating spinal stenosis from a separate medical device (not shown), and can transmit to the medical device the result of calculating the size of an area for evaluating spinal stenosis of an object within the segmented area through the segmentation model.

[0062] Meanwhile, the communication interface (210) that enables transmission and reception of such data includes a communication port (211) and a wireless circuit (212), wherein the wired communication port (211) may include one or more wired interfaces, for example, Ethernet, Universal Serial Bus (USB), FireWire, etc. In addition, the wireless circuit (212) may transmit and receive data with an external device via an RF signal or an optical signal. In addition, the wireless communication may use at least one of a plurality of communication standards, protocols, and technologies, for example, GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol.

[0063] The memory (220) can store various data used in the stenosis evaluation device (200). For example, the memory (220) can store identification data of an individual, a medical image of the individual, and the size of a previously calculated area for spinal stenosis evaluation. As another example, the memory (220) can store a segmentation model and training data used to train the segmentation model (e.g., a medical image including a spinal canal and a neuromuscular canal region).

[0064] In various embodiments, the memory (220) may include a volatile or non-volatile storage medium capable of storing various data, commands, and information. For example, the memory (220) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., an SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, cloud, and a blockchain database.

[0065] In various embodiments, the memory (220) may store configurations of at least one of an operating system (221), a communication module (222), a user interface module (223), and one or more applications (224).

[0066] An operating system (221) (e.g., embedded operating systems such as LINUX, UNIX, MAC OS, WINDOWS, VxWorks, etc.) may include various software components and drivers to control and manage general system operations (e.g., memory management, storage device control, power management, etc.) and may support communication between various hardware, firmware, and software components.

[0067] The communication module (223) can support communication with other devices through the communication interface (210). The communication module (220) can include various software components for processing data received by the wired communication port (211) or wireless circuit (212) of the communication interface (210).

[0068] The user interface module (223) can receive a user's request or input from a keyboard, touch screen, microphone, etc. through an I / O interface (230) and provide a user interface on the display.

[0069] The application (224) may include a program or module configured to be executed by one or more processors (240). Here, the application for evaluating spinal stenosis using a segmentation model and an algorithm for stenosis evaluation may be implemented on a server farm.

[0070] The I / O interface (230) can connect at least one of input / output devices (not shown) of the stenosis evaluation device (200), such as a display, a keyboard, a touch screen, and a microphone, to the user interface module (223). The I / O interface (230) can receive user input (e.g., voice input, keyboard input, touch input, etc.) together with the user interface module (223) and process commands according to the received input.

[0071] The processor (240) is connected to a communication interface (210), a memory (220), and an I / O interface (230) to control the overall operation of the stenosis evaluation device (200), and can perform various commands to provide evaluation results for spinal stenosis through an application or program stored in the memory (220).

[0072] The processor (240) may correspond to a computing device such as a Central Processing Unit (CPU) or an Application Processor (AP). Furthermore, the processor (240) may be implemented in the form of an integrated chip (IC), such as a System on Chip (SoC) in which various computing devices are integrated. Alternatively, the processor (240) may include a module for calculating an artificial neural network model, such as a Neural Processing Unit (NPU).

[0073] In various embodiments, the processor (240) may provide results for evaluating spinal stenosis by utilizing changes in the size of the spine, particularly the spinal canal and the nerve root canal, as described below with reference to FIG. 3.

[0074] Figure 3 is a schematic flowchart of a method for evaluating stenosis in the spinal canal and nerve root canal according to one embodiment of the present invention.

[0075] Referring to FIG. 3, the processor (240) can obtain a medical image of the spine of an object (S110). Specifically, the processor (240) can receive a cross-sectional (axial plane) medical image of the object from the imaging device (100) through the communication interface (210). That is, the processor (240) can receive cross-sectional medical images of the cervical, thoracic, and lumbar vertebrae of the object through the communication interface (210). However, in addition to this, the processor (240) can obtain a sagittal plane image and a coronal plane image of the spine from the imaging device (100) through the communication interface (210), which can be utilized in the process of providing a spinal stenosis evaluation result.

[0076] In various embodiments, the processor (240) may preprocess medical images into input data that can be input into a segmentation model, which will be described later. For example, the processor (240) may normalize medical images in DICOM format to a value between 0 and 1 and change the value to 8-bit depth.

[0077] After step S110, the processor (240) can segment an area for evaluating spinal stenosis from a previously acquired medical image using a segmentation model learned to segment an area for evaluating spinal stenosis by inputting a medical image (S120).

[0078] In relation to this, FIG. 4 is a schematic diagram for explaining a segmentation model performed in a stenosis evaluation device according to one embodiment of the present invention.

[0079] Referring to FIG. 4, the processor (240) can input a preprocessed medical image (11) into a segmentation model (12). Here, the preprocessed medical image (11) may be a cross-sectional medical image of an object. The processor (240) can obtain a region including a plurality of regions (13) for evaluating spinal stenosis from the segmentation model (12). Specifically, the segmentation model (12) can input a cross-sectional medical image and output one spinal canal region (13-1) and two root canal regions (13-2) as a segmentation result. For example, the processor (240) can output a mask corresponding to the spinal canal region and the root canal region, or output a boundary line corresponding to the spinal canal region and the root canal region in units of pixels constituting the medical image.

[0080] Meanwhile, the segmentation model (12) that segments two or more objects may be a model based on the YOLO structure. In addition, the segmentation model (12) may be composed of at least one model or two or more ensemble models among VGG net, R, DenseNet based on CNN (Convolutional Neural Network), FCN (Fully Convolutional Network) with encoder-decoder structure, SegNet, DeconvNet, DeepLAB V3+, DNN (deep neural network) such as U-net, SqueezeNet, Alexnet, ResNet18, MobileNet-v2, GoogLeNet, Resnet50, Resnet101, Inception-v3, or a model based on RNN (Recurrent Neural Network).

[0081] In one embodiment of the present invention, the processor (240) can evaluate spinal stenosis by using a stenosis evaluation algorithm applicable to the spinal canal region and the nerve root canal region, without diagnosing spinal stenosis by evaluating images of the spinal canal region and the nerve root canal region acquired through a segmentation model.

[0082] Referring again to FIG. 3, the processor (240) can calculate the size of an area capable of evaluating spinal stenosis of an individual based on the segmented area (S130). Specifically, the processor (240) can calculate the thickness for a plurality of points designated in one direction in each of the segmented spinal canal area and the nerve root canal area.

[0083] In relation to this, FIGS. 5a and 5b are schematic diagrams for explaining a method of calculating the size of a spinal canal and a nerve root canal performed in a stenosis evaluation device according to one embodiment of the present invention.

[0084] Referring to FIGS. 5A and 5B, the processor (240) can extract a portion of a medical image (22) including a segmented spinal canal region and a neural root canal region from a medical image (21). Here, the portion of the medical image (22) can include a spinal canal region (22-1) and a neural root canal region (22-2), and the neural root canal region (22-2) can be divided into two regions (22-21) and (22-22) on the left and right based on the spinal canal region (22-1).

[0085] The processor (240) can determine the centerline on the cross-section in each of the segmented spinal canal region and the nerve root canal region. Specifically, the processor (240) can determine the centerline (23-1) on the cross-section in the spinal canal region and the centerline (23-2) on the cross-section in the nerve root canal region using the principal component analysis (PCA) method in multiple cross-sectional medical images. However, in addition to this, the processor (240) can determine the centerline in the spinal canal region and the nerve root canal region using various analysis methods based on unsupervised learning.

[0086] The processor (240) can obtain three center lines (23-1)(23-21)(23-22) facing different directions on the same plane, and can determine a plurality of thickness evaluation lines for diagnosing stenosis that extend in a direction perpendicular to the center lines. For example, the processor (240) can determine a thickness evaluation line (23-1a)(23-21a)(23-22a) that extends vertically from the center of the three center lines (23-1)(23-21)(23-22). Since spinal stenosis cannot be accurately diagnosed with only one thickness evaluation line per region, the processor (240) can determine a plurality of thickness evaluation lines perpendicular to each of the center lines (23-1)(23-21)(23-22) based on the thickness evaluation line (23-1a)(23-21a)(23-22a) arranged at the center. For example, the processor (240) can determine a total of five thickness evaluation lines (23-1a)(23-1b)(23-1c)(23-1d)(23-1e) in the spinal canal, and can determine three thickness evaluation lines (23-21a)(23-21b)(23-21c)(23-22a)(23-22b)(23-22c) in each of the two nerve root canals. However, the number of thickness evaluation lines is not limited thereto, and more thickness evaluation lines may be used to increase the accuracy of the evaluation results of the stenosis evaluation device (200).

[0087] The processor (240) can calculate size changes for multiple thickness evaluation lines using multiple slides that constitute a medical image. That is, the processor (240) can calculate the size change values ​​for each of multiple thickness evaluation lines in adjacent slides, thereby calculating the total area of ​​the spinal canal and nerve root canal, or obtain a value that can evaluate stenosis without having to divide the area into smaller areas and observe size or shape changes.

[0088] In various embodiments, the processor (240) may determine whether a size change value in at least one thickness evaluation line among a plurality of thickness evaluation lines is greater than or equal to a preset value. The processor (240) may distinguish the type of spinal stenosis to be evaluated based on the placement position or spinal position of the thickness evaluation line where the size change value is greater than or equal to the preset value. For example, the processor (240) may distinguish whether spinal stenosis is due to a congenital factor, a degenerative factor, or other treatment-diagnosis factor such as spondylolisthesis based on the placement position of the thickness evaluation line where the size change value is observed.

[0089] In various embodiments, the processor (240) may determine the progression grade of spinal stenosis of an individual according to a size change based on a preset evaluation value. For example, the processor (240) may classify the progression grade of spinal stenosis according to the size change value into a plurality of grades, and when a size change value is observed in one or more thickness evaluation lines among them, the progression grade of spinal stenosis of an individual may be determined. Here, the evaluation value for determining the progression grade may have different values ​​depending on the arrangement position of the thickness evaluation line and the spinal position. That is, considering the difference in the size of the spinal canal and the nerve root canal, the preset evaluation value used by the processor (240) may be different for each thickness evaluation line, and this may be designated as an arbitrary value by a medical professional, for example.

[0090] After step S130, the processor (240) may provide an evaluation result for spinal stenosis based on the size calculation result (S140). Specifically, depending on the implementation method, the processor (240) may display the evaluation result based on the size change value through the I / O interface (230) or transmit it to a separate medical staff device through the communication interface (210).

[0091] In relation to this, FIGS. 6a and 6b are exemplary diagrams of interface screens showing stenosis evaluation results according to one embodiment of the present invention.

[0092] Referring to FIG. 6A, the processor (240) may provide the results of evaluating spinal stenosis of an individual as follows. For example, the evaluation results provided by the processor (240) may include identification data such as the individual's age and gender, and may display the size values ​​of thickness evaluation lines calculated in the spinal canal area and the nerve root canal area in the medical image. Here, Area1, Area2, and Area3 represent thickness evaluation lines, and the size values ​​in the current slide (current area) and the size change values ​​compared to the previous slide may be displayed as the evaluation results.

[0093] In various embodiments, the processor (240) may use sagittal and coronal medical images of the subject to determine a specific spinal location where a size change value is observed, if a thickness evaluation line exists where the size change value is greater than a preset value. Through this, the processor (240) may specifically identify a location suspected of spinal stenosis, such as “T3 spinal canal evaluation line a,” and provide the location to the medical staff.

[0094] In addition, referring to FIG. 6b, the processor (240) may provide the spinal stenosis evaluation results of the subject as follows. For example, the evaluation results provided by the processor (240) may be displayed together with a sagittal or coronal medical image of the spine, and the processor (240) may intuitively provide the degree of stenosis progression, such as “grade 1 stenosis calculated at T1,” or may display only an area requiring a specific diagnosis without showing the degree of stenosis progression, such as “diagnosis of spinal canal and nerve root canal around T1 is required,” or “difference value of NM slide 3rd evaluation line -2.3.”

[0095] So far, a stenosis evaluation device (200) according to one embodiment of the present invention has been described. According to the present invention, the stenosis evaluation device (200) does not predict stenosis based on an image like a conventional diagnosis or prediction model, but rather divides the spinal canal and nerve root canal areas through a segmentation model and then calculates a specific numerical value that serves as the basis for the stenosis evaluation through a stenosis evaluation algorithm, thereby increasing the reliability of the stenosis evaluation result.

[0096] Furthermore, automation of this process can effectively shorten the diagnostic process, which requires medical staff to visually examine changes in the thickness of the spinal canal and nerve root canal in hundreds of medical images.

[0097] Although the embodiments of the present invention have been described in more detail with reference to the attached drawings, the present invention is not necessarily limited to these embodiments, and various modifications may be implemented without departing from the technical spirit of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain it, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, it should be understood that the embodiments described above are illustrative in all aspects and not restrictive. The protection scope of the present invention should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of the rights of the present invention.

[0098] [National Research and Development Project Supporting This Invention]

[0099] [Project ID] 1711196789

[0100] [Assignment Number] 00252804

[0101] [Ministry Name] Ministry of Science and ICT

[0102] [Name of Project Management (Specialist) Institution] (Foundation) Inter-Ministry Full-cycle Medical Device Research and Development Project Group

[0103] [Research Project Name] Inter-Ministry Full-cycle Medical Device Research and Development (Ministry of Science and Technology)

[0104] [Research Project Title] Development and Verification of Core AI Technologies for Diagnosing Degenerative Spinal Diseases

[0105] [Name of the project performing organization] Catholic University Industry-Academic Cooperation Foundation

[0106] Research Period: April 1, 2023 - December 31, 2025

Claims

1. A method for evaluating stenosis implemented by a processor, A step of obtaining a medical image of the spine of an individual; A step of segmenting a region for evaluating spinal stenosis in a medical image using a segmentation model learned to segment a region for evaluating spinal stenosis by inputting a medical image; and A method for evaluating stenosis in a spinal canal and a nerve root canal, comprising: calculating the size of an area capable of evaluating spinal stenosis of the subject based on the segmented area; 2. In paragraph 1, The steps of obtaining the above medical images are: This is a step of obtaining a cross-sectional (axial plane) medical image of the above object, The above division model is, A method for assessing stenosis in the spinal canal and radicular canal, wherein the model is trained to segment one spinal canal region and two radicular canal regions using cross-sectional medical images as input.

3. In paragraph 2, The steps for calculating the above size are: A method for evaluating stenosis in a spinal canal and a nerve root canal, the method comprising: calculating a thickness for a plurality of points designated based on one direction in each of the above-mentioned divided spinal canal region and nerve root canal region.

4. In paragraph 3, The steps for calculating the above size are: A step of determining a center line on a cross-section in each of the above divided spinal canal regions and nerve root canal regions, and A method for evaluating stenosis in a spinal canal and a nerve root canal, further comprising the step of determining a plurality of thickness evaluation lines for diagnosing stenosis, the thickness evaluation lines extending in a direction perpendicular to the center line.

5. In paragraph 4, The steps for calculating the above size are: A method for evaluating stenosis in a spinal canal and a nerve root canal, further comprising the step of calculating a change in size for a plurality of thickness evaluation lines using a plurality of slides constituting the medical image.

6. In paragraph 5, The steps for calculating the above size change are: A method for evaluating stenosis in a spinal canal and a nerve root canal, further comprising a step of determining whether a size change value in at least one thickness evaluation line among the plurality of thickness evaluation lines is greater than or equal to a preset value.

7. In paragraph 6, After the above judging step, A method for evaluating stenosis in a spinal canal and a nerve root canal, further comprising a step of distinguishing the type of spinal stenosis evaluation according to the position of a thickness evaluation line having a size change value greater than a preset value.

8. In paragraph 5, The steps for calculating the above size change are: A method for evaluating stenosis in a spinal canal and a nerve root canal, further comprising a step of determining the degree of progression (grade) of spinal stenosis of the object according to the change in size based on a preset evaluation value.

9. In paragraph 5, The steps of obtaining the above medical images are: Further comprising a step of obtaining a sagittal plane or coronal plane medical image of the above object, After the above calculation steps, A method for evaluating stenosis in a spinal canal and a nerve root canal, further comprising a step of determining a spinal location where the size change value is observed based on the sagittal or coronal medical image, if a thickness evaluation line having a size change value greater than a preset value exists.

10. In either of paragraphs 8 and 9, The preset evaluation values ​​that match the above size change values ​​are: A method for evaluating stenosis in the spinal canal and nerve root canal, which has different values ​​depending on the placement location of the thickness evaluation line and the spinal location.

11. Communication interface; memory; a processor operably connected to the communication interface and the memory; The above processor, A device for evaluating spinal stenosis in a spinal canal and nerve root canal, comprising: acquiring a medical image of a spine of an individual; segmenting the medical image into an area for evaluating spinal stenosis using a segmentation model learned to segment an area for evaluating spinal stenosis using the medical image as input; and calculating the size of an area capable of evaluating spinal stenosis of the individual based on the segmented area.

12. In paragraph 11, The above processor, It is configured to acquire a cross-sectional (axial plane) medical image of the above object, The above division model is, A device for evaluating stenosis in the spinal canal and radicular canal, the model being trained to segment one spinal canal region and two radicular canal regions by inputting cross-sectional medical images.

13. In paragraph 12, The above processor, A device for evaluating stenosis in a spinal canal and a nerve root canal, configured to calculate the thickness for a plurality of points designated based on one direction in each of the above-mentioned divided spinal canal regions and nerve root canal regions.

14. In paragraph 13, The above processor, A device for evaluating stenosis in the spinal canal and nerve root canal, further configured to determine a centerline on a cross-section in each of the above-described divided spinal canal regions and nerve root canal regions, and to determine a plurality of thickness evaluation lines for diagnosing stenosis, extending in a direction perpendicular to the centerline.

15. In paragraph 14, The above processor, A device for evaluating stenosis in the spinal canal and nerve root canal, further configured to calculate size changes for the plurality of thickness evaluation lines using the plurality of slides constituting the above medical images.

16. In paragraph 15, The above processor, A device for evaluating stenosis in a spinal canal and a nerve root canal, further configured to determine whether a size change value in at least one thickness evaluation line among the above-mentioned plurality of thickness evaluation lines is equal to or greater than a preset value.

17. In paragraph 16, The above processor, A device for evaluating stenosis in a spinal canal and a nerve root canal, further configured to distinguish the type of evaluation of spinal stenosis according to the position of a thickness evaluation line having a size change value greater than or equal to a preset value after determining the above-mentioned size change.

18. In paragraph 15, The above processor, A device for evaluating stenosis in the spinal canal and nerve root canal, further configured to determine the grade of spinal stenosis progression of the object according to the change in size based on a preset evaluation value.

19. In Article 15, The above processor, Further configured to acquire a sagittal plane or coronal medical image of the above object, A device for evaluating stenosis in a spinal canal and a nerve root canal, further configured to determine a spinal location where the size change value is observed based on the sagittal or coronal medical image, if there is a thickness evaluation line whose size change value is greater than a preset value.

20. In any one of paragraphs 18 and 19, The preset evaluation values ​​that match the above size change values ​​are: A device for evaluating stenosis in the spinal canal and nerve root canal, which has different values ​​depending on the position of the thickness evaluation line and the position of the spine.

21. A computer program stored in a computer-readable recording medium for executing a method for evaluating stenosis in the spinal canal and nerve root canal, The above method, A step of obtaining a medical image of the spine of an individual; A step of segmenting a region for evaluating spinal stenosis in a medical image by using a segmentation model learned to segment a region for evaluating spinal stenosis by inputting a medical image through the above processor; and A computer program stored in a computer-readable recording medium, comprising: a step of calculating the size of an area capable of evaluating spinal stenosis of the object based on the segmented area through the processor;

Images