Neurodegenerative change assessment method and device based on nerve melanin MRI

Abstract

The invention discloses a neurodegenerative change assessment method and device based on nerve melanin MRI, and relates to the technical field of medical imaging and neuroscience assessment, and the method comprises the steps: obtaining MRI image data of a to-be-assessed individual; the MRI image data comprises multi-sequence MRI image data including three-dimensional T1 weighted imaging, two-dimensional T2 weighted imaging and magnetization transfer imaging; preprocessing the MRI image data to obtain preprocessed MRI image data; extracting a region of interest from the preprocessed MRI image data to obtain the region of interest; performing MRI signal feature analysis on the region of interest to obtain MRI signal features; and inputting the MRI signal features into a neurodegenerative change evaluation model, and outputting a neurodegenerative change evaluation result of the individual to be evaluated. According to the application, the non-invasive and accurate evaluation of the neurodegenerative change can be realized by using the unique signal characteristics of the nerve melanin in MRI imaging.

Description

Technical Field

[0001] This application relates to the field of medical imaging and neuroscience assessment technology, and in particular to a method and device for assessing neurodegenerative changes based on neuromelanin MRI. Background Technology

[0002] Neurodegenerative diseases such as Parkinson's disease and Alzheimer's disease seriously threaten human health and quality of life. Currently, assessment methods for neurodegenerative changes mainly include invasive brain biopsies, subjective cognitive assessments based on clinical symptoms, and some biomarker-dependent detection methods. While brain biopsies can directly observe pathological changes in neural tissue, they are invasive procedures that cause pain and potential risks to patients, limiting their widespread application. Subjective assessments based on clinical symptoms rely on physician experience and patient self-reporting, resulting in poor accuracy and objectivity. Biomarker detection suffers from insufficient sensitivity and specificity. Therefore, there is an urgent need for a non-invasive, accurate, and highly reproducible method for assessing neurodegenerative changes.

[0003] Neuromelanin (NM) is a pigment found in dopaminergic neurons of the midbrain and is closely related to neurodegenerative diseases. In the progression of neurodegenerative diseases, neurons containing neuromelanin undergo degeneration, leading to changes in the content and distribution of neuromelanin. Magnetic resonance imaging (MRI), as a non-invasive imaging method, has been widely used in clinical diagnosis. However, there is currently no mature, systematic, and non-invasive technical solution for assessing individual neurodegenerative changes based on neuromelanin MRI signals. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for assessing neurodegenerative changes based on neuromelanin MRI, which can utilize the unique signal characteristics of neuromelanin in MRI imaging to achieve non-invasive and accurate assessment of neurodegenerative changes.

[0005] To achieve the above objectives, this application provides the following solution.

[0006] In a first aspect, this application provides a method for assessing neurodegenerative changes based on neuromelanin MRI, which specifically includes the following steps.

[0007] Acquire MRI image data of the individual to be evaluated; the MRI image data includes multi-sequence MRI image data including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging.

[0008] The MRI image data is preprocessed to obtain preprocessed MRI image data.

[0009] The region of interest is extracted from the preprocessed MRI image data to obtain the region of interest.

[0010] MRI signal feature analysis is performed on the region of interest to obtain MRI signal features.

[0011] The MRI signal features are input into the neurodegenerative change assessment model, and the neurodegenerative change assessment result of the individual to be assessed is output; the neurodegenerative change assessment model is a pre-trained model based on machine learning algorithm and used for neurodegenerative change assessment; the neurodegenerative change assessment result is a graded result of the degree of neurodegenerative change, which is used to represent the degree level of neurodegenerative change of the individual to be assessed.

[0012] Optionally, MRI image data of the individual to be evaluated may be acquired, specifically including the following steps.

[0013] Using an MRI device with a field strength greater than or equal to 3T, the brain of the individual to be evaluated was scanned with a neuromelanin-sensitive sequence to acquire MRI image data in multiple directions and with different scanning parameters.

[0014] Optionally, the MRI image data is preprocessed to obtain preprocessed MRI image data, specifically including the following steps.

[0015] The MRI image data is denoised to obtain denoised MRI image data.

[0016] Image registration technology is used to spatially align the denoised MRI image data to obtain spatially aligned MRI image data.

[0017] The spatially aligned MRI image data is subjected to grayscale normalization to obtain preprocessed MRI image data.

[0018] Optionally, the region of interest is extracted from the preprocessed MRI image data to obtain the region of interest, specifically including the following steps.

[0019] Based on brain anatomical atlases, image segmentation is used to manually or automatically delineate brain regions containing neuromelanin on the preprocessed MRI image data, and these brain regions containing neuromelanin are designated as regions of interest; the brain regions containing neuromelanin include: substantia nigra pars compacta and locus coeruleus.

[0020] Optionally, MRI signal feature analysis is performed on the region of interest to obtain MRI signal features, specifically including the following steps.

[0021] Based on the region of interest, MRI signal characteristic parameters of neuronal melanin within the region of interest are calculated, and these MRI signal characteristic parameters are used as input MRI signal characteristics into the neurodegenerative change assessment model. The MRI signal characteristic parameters include: MRI signal intensity, signal homogeneity, T1 relaxation time, and T2 relaxation time. The signals in the MRI signal intensity and signal homogeneity include: T1-weighted imaging signal, T2-weighted imaging signal, and magnetization transfer imaging signal.

[0022] Optionally, the neurodegenerative change assessment model is an SVM model or a CNN model.

[0023] Secondly, this application provides a neurodegenerative change assessment device based on neuromelanin MRI, which includes the following functional modules.

[0024] The MRI image acquisition module is used to acquire MRI image data of the individual to be evaluated; the MRI image data includes multi-sequence MRI image data, including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging.

[0025] The image preprocessing module is used to preprocess the MRI image data to obtain preprocessed MRI image data.

[0026] The region of interest extraction module is used to extract the region of interest from the preprocessed MRI image data to obtain the region of interest.

[0027] The signal feature analysis module is used to perform MRI signal feature analysis on the region of interest to obtain MRI signal features.

[0028] The neurodegenerative change assessment module is used to input the MRI signal features into the neurodegenerative change assessment model and output the neurodegenerative change assessment result of the individual to be assessed; the neurodegenerative change assessment model is a pre-trained model based on machine learning algorithm and used for neurodegenerative change assessment; the neurodegenerative change assessment result is a graded result of the degree of neurodegenerative change, used to represent the degree level of neurodegenerative change of the individual to be assessed.

[0029] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the aforementioned method for assessing neurodegenerative changes based on neuromelanin MRI.

[0030] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned method for assessing neurodegenerative changes based on neuromelanin MRI.

[0031] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method for assessing neurodegenerative changes based on neuromelanin MRI.

[0032] According to the specific embodiments provided in this application, this application has the following technical effects.

[0033] This application provides a method and apparatus for assessing neurodegenerative changes based on neuromelanin MRI. It acquires multi-sequence MRI image data, including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging. Based on the MRI image data, preprocessing, region-of-interest extraction, and MRI signal feature analysis are performed sequentially to obtain MRI signal features. Then, a neurodegenerative change assessment model based on machine learning algorithms is used to assess neurodegenerative changes according to the MRI signal features, resulting in an assessment of the degree of neurodegenerative changes in the individual being assessed. This application combines MRI imaging technology and machine learning technology. On the one hand, since the final neurodegenerative change assessment result is obtained from multi-sequence MRI image data including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging, by analyzing the MRI signal features in the MRI images, it can accurately capture changes in neuromelanin during the neurodegenerative process, making the assessment results more objective, reasonable, scientific, and reliable. Compared with traditional subjective assessments that rely on physician experience and patient self-reporting, this application can effectively improve the accuracy of neurodegenerative change assessment. On the other hand, since the entire assessment process relies on MRI images and machine learning models, no invasive procedures are required, and no harm is caused to the individual being assessed. This truly achieves non-invasive assessment, and the assessment can be repeated multiple times, making it reproducible. It can provide a reliable basis for the early diagnosis, disease monitoring, and efficacy evaluation of neurodegenerative diseases, and can be widely used in clinical screening and long-term disease monitoring. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This diagram illustrates the application environment of a neurodegenerative change assessment method based on neuromelanin MRI, as provided in one embodiment of this application.

[0036] Figure 2 This is a flowchart illustrating a method for assessing neurodegenerative changes based on neuromelanin MRI, as provided in an embodiment of this application.

[0037] Figure 3 This is a structural framework diagram of a neurodegenerative change assessment device based on neuromelanin MRI, provided as an embodiment of this application.

[0038] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

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

[0040] This application aims to provide a method and device for assessing neurodegenerative changes based on neuromelanin MRI. By utilizing the unique signal characteristics of neuromelanin in MRI imaging, it can achieve non-invasive and accurate assessment of neurodegenerative changes, providing a reliable basis for the early diagnosis, disease monitoring and efficacy evaluation of neurodegenerative diseases.

[0041] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] The neurodegenerative change assessment method based on neuromelanin MRI provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can send MRI image data to server 104. After receiving the MRI image data, server 104 preprocesses the MRI image data to obtain preprocessed MRI image data; extracts regions of interest (ROIs) from the preprocessed MRI image data; performs MRI signal feature analysis on the ROIs to obtain MRI signal features; inputs the MRI signal features into a neurodegenerative change assessment model, and outputs the neurodegenerative change assessment results for the individual being assessed. Server 104 can feed back the obtained neurodegenerative change assessment results to terminal 102. In addition, in some embodiments, the neurodegenerative change assessment method based on neuromelanin MRI can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can directly perform neurodegenerative change assessment processing on the MRI image data, or the server 104 can obtain the MRI image data from the data storage system and perform neurodegenerative change assessment processing on the MRI image data.

[0043] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, and IoT devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0044] In one exemplary embodiment, such as Figure 2 As shown, a method for assessing neurodegenerative changes based on neuromelanin MRI is provided. This method is executed by a computer device, specifically a terminal or server, or both. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S1 to S5.

[0045] S1: Acquire MRI image data of the individual to be evaluated. The MRI image data includes multi-sequence MRI image data, including three-dimensional T1-weighted imaging (3D-T1WI), two-dimensional T2-weighted imaging (2D-T2WI), and magnetization transfer imaging (MTI).

[0046] S2: Preprocess the MRI image data to obtain preprocessed MRI image data.

[0047] S3: Extract the region of interest from the preprocessed MRI image data to obtain the region of interest.

[0048] S4: Perform MRI signal feature analysis on the region of interest to obtain MRI signal features.

[0049] S5: Input the MRI signal features into the neurodegenerative change assessment model and output the neurodegenerative change assessment result for the individual to be assessed. The neurodegenerative change assessment model is a pre-trained model based on a machine learning algorithm and used for neurodegenerative change assessment; the neurodegenerative change assessment result is a graded result of the degree of neurodegenerative change, used to represent the degree level of neurodegenerative change in the individual to be assessed.

[0050] By implementing steps S1 to S5 above, and combining MRI imaging technology with machine learning technology, the final assessment of neurodegenerative changes is based on multi-sequence MRI image data, including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging. By analyzing the MRI signal characteristics in the MRI images, changes in neuromelanin during neurodegenerative changes can be accurately captured, making the assessment results more objective, reasonable, scientific, and reliable. Compared to traditional subjective assessments that rely on physician experience and patient self-reporting, this application effectively improves the accuracy of neurodegenerative change assessment. Furthermore, since the entire assessment process relies on MRI images and machine learning models, no invasive procedures are required, causing no harm to the individual being assessed. This truly achieves non-invasive assessment and allows for repeated examinations and assessments, ensuring repeatability. It provides a reliable basis for the early diagnosis, disease monitoring, and efficacy evaluation of neurodegenerative diseases and can be widely applied in clinical screening and long-term disease monitoring.

[0051] In this embodiment, step S1, acquiring MRI image data of the individual to be evaluated, specifically includes the following steps.

[0052] Using an MRI device with an electric field strength greater than or equal to 3T (Tesla), the brain of the individual to be evaluated was scanned with neuromelanin-sensitive sequences, and MRI image data under multiple directions and different scanning parameters were acquired.

[0053] In this embodiment, step S2 preprocesses the MRI image data to obtain preprocessed MRI image data, specifically including the following steps.

[0054] S21: Denoise the MRI image data to obtain denoised MRI image data.

[0055] S22: Using image registration technology, spatial alignment processing is performed on the denoised MRI image data to obtain spatially aligned MRI image data.

[0056] S23: Perform grayscale normalization on the spatially aligned MRI image data to obtain preprocessed MRI image data.

[0057] In this embodiment, step S3 extracts the region of interest from the preprocessed MRI image data to obtain the region of interest, specifically including the following steps.

[0058] Based on brain anatomical atlases, image segmentation methods are used to manually or automatically delineate brain regions containing neuromelanin on the preprocessed MRI image data, and these brain regions containing neuromelanin are designated as regions of interest.

[0059] In this embodiment, the brain regions containing neuromelanin include the substantia nigra pars compacta and the locus coeruleus (LC).

[0060] In this embodiment, step S4 involves performing MRI signal feature analysis on the region of interest to obtain MRI signal features, specifically including the following steps.

[0061] Based on the region of interest, the MRI signal characteristic parameters of neuromelanin within the region of interest are calculated, and the MRI signal characteristic parameters are used as the input MRI signal characteristics of the neurodegenerative change assessment model.

[0062] In this embodiment, the MRI signal characteristic parameters include: MRI signal intensity, signal uniformity, T1 relaxation time (longitudinal relaxation time) and T2 relaxation time (lateral relaxation time), etc. The signals in the MRI signal intensity and signal uniformity include: T1-weighted imaging signal, T2-weighted imaging signal and magnetization transfer imaging signal.

[0063] In this embodiment, the neurodegenerative change assessment model is an SVM (Support Vector Machine) model or a CNN (Convolutional Neural Network) model, etc.

[0064] Based on the same inventive concept, this application also provides a neurodegenerative change assessment processing device for implementing the aforementioned neurodegenerative change assessment method based on neuromelanin MRI. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations of one or more embodiments of the neurodegenerative change assessment processing device provided below can be found in the limitations of the neurodegenerative change assessment method based on neuromelanin MRI described above, and will not be repeated here.

[0065] In one exemplary embodiment, such as Figure 3 As shown, a neurodegenerative change assessment device based on neuromelanin MRI is provided, which includes the following functional modules.

[0066] The MRI image acquisition module is used to acquire MRI image data of the individual to be evaluated. The MRI image data includes multi-sequence MRI image data, including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging.

[0067] The image preprocessing module is used to preprocess the MRI image data to obtain preprocessed MRI image data.

[0068] The region of interest extraction module is used to extract the region of interest from the preprocessed MRI image data to obtain the region of interest.

[0069] The signal feature analysis module is used to perform MRI signal feature analysis on the region of interest to obtain MRI signal features.

[0070] The neurodegenerative change assessment module is used to input the MRI signal features into the neurodegenerative change assessment model and output the neurodegenerative change assessment results for the individual to be assessed. The neurodegenerative change assessment model is a pre-trained model based on a machine learning algorithm and used for neurodegenerative change assessment; the neurodegenerative change assessment results are a grading result of the degree of neurodegenerative changes, used to represent the degree level of neurodegenerative changes in the individual to be assessed.

[0071] To make the technical solution of this application clearer, the specific implementation process of the method and the specific structure of the system in this application are explained in detail below with examples.

[0072] This embodiment proposes a method for assessing neurodegenerative changes based on neuromelanin MRI, which mainly includes the following implementation steps.

[0073] Step 1: MRI image data acquisition.

[0074] In this embodiment, when acquiring MRI image data, a high-field MRI device (e.g., 3T and above) is used to perform neuromelanin-sensitive sequence scans on the brain of the individual to be evaluated. Scanning sequences include, but are not limited to, three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging, acquiring MRI image data from multiple directions and with different parameters to obtain rich neuromelanin signal information. During the scanning process, it is ensured that the individual's head remains still; appropriate head frames and fixation devices can be used to reduce motion artifacts.

[0075] Step 2: Image preprocessing.

[0076] In this embodiment, during image preprocessing, the acquired MRI image data is first imported into image analysis software for denoising to remove interference signals caused by factors such as equipment noise and the movement of the individual being evaluated. Then, image registration technology is used to spatially align images acquired at different times and sequences to ensure accurate correspondence of anatomical structures between images. Finally, grayscale normalization is performed to bring the image grayscale values ​​into a uniform range for easier subsequent analysis.

[0077] Step 3: Region of Interest Extraction.

[0078] In this embodiment, when extracting regions of interest (ROIs), brain regions rich in neuromelanin, such as the substantia nigra pars compacta and the locus coeruleus, are manually or automatically delineated on the preprocessed MRI images based on brain anatomical atlases. Image segmentation algorithms, combined with the signal characteristics of neuromelanin on MRI images, can be used to achieve precise extraction of ROIs.

[0079] Step 4: MRI signal feature analysis.

[0080] In this embodiment, when analyzing MRI signal characteristics, the MRI signal intensity and signal uniformity (including T1-weighted imaging signal, T2-weighted imaging signal and magnetization transfer imaging signal), relaxation time (including T1 relaxation time and T2 relaxation time) and other MRI signal characteristic parameters of neuronal melanin in the region of interest are calculated.

[0081] In this embodiment, MRI signal intensity characterizes the strength of the MRI signal, mainly depending on proton density, T1 relaxation time, T2 relaxation time, magnetic field strength, and radio frequency pulse sequence parameters. MRI signal strength reflects the number and relaxation characteristics of hydrogen nuclei within the detection area, directly affecting image contrast and resolution. This embodiment uses the locus coeruleus (and similarly the substantia nigra compacta) as the region of interest. For the MRI signal intensity of the locus coeruleus, the region of interest (3mm) is manually marked. 2 The signal intensity of the left and right locus coeruleus was extracted from the cross-shaped region and averaged; the pontine tegmentum (PT) was also marked as a reference region (10 mm). 2 The signal intensity of the blue spot kernel is extracted from a square region. Finally, the contrast-to-noise ratio of the blue spot kernel is calculated using the following formula. This index is used to reflect the structural integrity of the locus coeruleus. A higher value indicates a higher density of neurons in the locus coeruleus and a more complete structure.

[0082] ; in, This represents the contrast-to-noise ratio of the blue spot nucleus. Indicates the signal strength of the locus coeruleus. This indicates the signal intensity in the pontine tegmentum.

[0083] In this embodiment, signal homogeneity refers to the homogeneity of the MRI signal, specifically the uniformity of the MRI signal intensity distribution within the region of interest (e.g., substantia nigra pars compacta, locus coeruleus). In neurodegenerative diseases, the degeneration of neurons rich in melanin leads to abnormal distribution, manifested as decreased signal homogeneity. Therefore, this parameter can reflect the structural integrity of neural tissue. This embodiment assesses MRI signal intensity and homogeneity primarily by evaluating three types of signals: T1-weighted imaging signals, T2-weighted imaging signals, and melanin sequence signals. For these three signals, statistical measures (e.g., standard deviation, coefficient of variation) can be calculated from the MRI signal intensity data of the region of interest (e.g., substantia nigra pars compacta, locus coeruleus), and the signal homogeneity of the MRI signal is determined based on these statistical measures.

[0084] In this embodiment, the coefficient of variation is calculated using the following formula.

[0085] ; ; ; in, Represents the coefficient of variation. Indicates standard deviation, This represents the average signal strength of all pixels within the region of interest. The number of pixels in the region of interest. This represents the signal strength of the i-th pixel.

[0086] in, The smaller the value, the better the signal uniformity of the MRI signal (typically under ideal conditions). (less than 5%), if An excessively high value may indicate an uneven magnetic field, differences in coil sensitivity, or image artifacts.

[0087] As an optional implementation, the signal intensity and signal uniformity of the T1-weighted imaging signal, T2-weighted imaging signal, and neuromelanin sequence signal can be evaluated by adding weights to the calculation of the T1-weighted imaging signal, T2-weighted imaging signal, and neuromelanin sequence signal, respectively, and finally a total signal intensity and signal uniformity can be calculated.

[0088] In this embodiment, T1 relaxation time and T2 relaxation time are two key parameters used in magnetic resonance imaging (MRI) to describe tissue characteristics. T1 relaxation time refers to the time required for the longitudinal magnetization vector to recover from 0 to 63% of its equilibrium state after radiofrequency pulse excitation. T2 relaxation time refers to the time required for the transverse magnetization vector to decay from its maximum value to 37% after the radiofrequency pulse is turned off. In the definition of relaxation time in MRI, 63% and 37% are key thresholds derived from the exponential law of magnetization vector changes over time based on T1 and T2 relaxation times, used to quantify the characteristic time of the relaxation process. By comparing the changes in characteristic parameters at different time points in different individuals or the same patient, neurodegenerative changes are assessed.

[0089] For example, during a typical MRI scan, T1 relaxation time and T2 relaxation time affect the signal intensity values ​​of T1-weighted and T2-weighted imaging signals, respectively. Therefore, with the progression of neurodegenerative diseases, T1-weighted imaging signals decrease, T2-weighted imaging signals increase, neuromelanin sequence signals decrease, and the signal uniformity of each neuromelanin sequence signal decreases. Neurodegenerative changes are assessed using cognitive function scores and serum neurofilament light chains, including the MMSE (Minor Mental State Examination), Moca (Montreal Cognitive Test), RAVLT (Rayssee Auditory Word Learning Test), SDMT (Digit Symbol Transformation Test), and Stroop test. Predictive models are established by comparing the correlation between cognitive scores, serum neurofilament light chains, and blue spot neuromelanin T1 relaxation time and neuromelanin signal intensity in subjects with different cognitive states (dementia, mild cognitive impairment, subjective cognitive impairment), and by incorporating other clinical variables such as gender, age, blood pressure, and BMI (Body Mass Index).

[0090] Step 5: Assessment of neurodegenerative changes.

[0091] In this embodiment, when assessing neurodegenerative changes, a neurodegenerative change assessment model is first established. This model can be constructed based on machine learning algorithms, such as SVM and CNN. The model is trained and optimized using MRI image data and clinical information of patients with known degrees of neurodegenerative changes as a training set. The MRI signal characteristic parameters of the individual to be assessed are input into the neurodegenerative change assessment model, which outputs a grading result of the degree of neurodegenerative changes. The grading result can be classified into mild, moderate, and severe according to severity from low to high. Thresholds can be set to distinguish between these three levels.

[0092] This embodiment proposes a neurodegenerative change assessment device based on neuromelanin MRI, which mainly includes an MRI image acquisition module, an image preprocessing module, a region of interest extraction module, a signal feature analysis module, and a neurodegenerative change assessment module.

[0093] In this embodiment, the MRI image acquisition module can use a high-field MRI device to perform neuromelanin-sensitive sequence scanning and acquire MRI image data of the brain of the individual to be evaluated.

[0094] In this embodiment, the image preprocessing module includes a denoising unit, an image registration unit, and a grayscale normalization unit, which are used to perform preprocessing operations such as denoising, spatial alignment, and grayscale normalization on the MRI image data, respectively.

[0095] In this embodiment, the region of interest extraction module integrates an image segmentation algorithm, which can automatically or manually extract the region of interest based on brain anatomical atlases and neural melanin signal characteristics.

[0096] In this embodiment, the signal feature analysis module is used to calculate MRI signal feature parameters such as MRI signal intensity, signal uniformity, T1 relaxation time, and T2 relaxation time of neural melanin in the region of interest.

[0097] In this embodiment, the neurodegenerative change assessment module has a built-in neurodegenerative change assessment model based on machine learning algorithms. This neurodegenerative change assessment model is responsible for receiving MRI signal feature parameters output by the signal feature analysis module, assessing the neurodegenerative change status of the individual to be assessed, and outputting the neurodegenerative change assessment results to achieve the degree classification of neurodegenerative changes, such as mild, moderate, and severe.

[0098] The present application proposes a method and device for assessing neurodegenerative changes based on neuromelanin MRI, which has the following advantages.

[0099] (1) Non-invasive: This application is based on the evaluation of neuromelanin MRI signal, which does not require invasive operation, avoids harm to patients, is easy for patients to accept, and can be widely used in clinical screening and long-term disease monitoring.

[0100] (2) Accuracy: This application conducts in-depth analysis of the MRI signal characteristics of neuromelanin and establishes an assessment model for neurodegenerative changes by combining machine learning algorithms. It can accurately capture the changes of neuromelanin during the process of neurodegenerative changes, which is in line with the natural law of the close relationship between neuromelanin and neurodegenerative changes. The assessment method is more scientific and reasonable, and can improve the accuracy and objectivity of the assessment.

[0101] (3) Early diagnosis: This application can detect subtle changes in neuromelanin in the early stages of neurodegenerative diseases, which helps to achieve early detection of neurodegenerative diseases, provide a basis for timely intervention and treatment, and improve patient prognosis.

[0102] (4) Repeatability: MRI examination is performed in a standardized manner, and the image data is easy to store and analyze. It can be repeated multiple times, which facilitates dynamic monitoring of neurodegenerative changes in the same patient at different time points.

[0103] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores MRI image data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for assessing neurodegenerative changes based on neuromelanin MRI.

[0104] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0105] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0106] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0107] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0108] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0109] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for assessing neurodegenerative changes based on neuromelanin MRI, characterized in that, The neurodegenerative change assessment method based on neuromelanin MRI includes: Acquire MRI image data of the individual to be evaluated; the MRI image data includes multi-sequence MRI image data, including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging; The MRI image data is preprocessed to obtain preprocessed MRI image data; The region of interest is extracted from the preprocessed MRI image data to obtain the region of interest; MRI signal feature analysis was performed on the region of interest to obtain MRI signal features; The MRI signal features are input into the neurodegenerative change assessment model, and the neurodegenerative change assessment result of the individual to be assessed is output; the neurodegenerative change assessment model is a pre-trained model based on machine learning algorithm and used for neurodegenerative change assessment; the neurodegenerative change assessment result is a graded result of the degree of neurodegenerative change, which is used to represent the degree level of neurodegenerative change of the individual to be assessed.

2. The method for assessing neurodegenerative changes based on neuromelanin MRI according to claim 1, characterized in that, Obtain MRI image data of the individual to be evaluated, specifically including: Using an MRI device with a field strength greater than or equal to 3T, the brain of the individual to be evaluated was scanned with a neuromelanin-sensitive sequence to acquire MRI image data in multiple directions and with different scanning parameters.

3. The method for assessing neurodegenerative changes based on neuromelanin MRI according to claim 1, characterized in that, The MRI image data is preprocessed to obtain preprocessed MRI image data, specifically including: The MRI image data is denoised to obtain denoised MRI image data; Image registration technology is used to spatially align the denoised MRI image data to obtain spatially aligned MRI image data. The spatially aligned MRI image data is subjected to grayscale normalization to obtain preprocessed MRI image data.

4. The method for assessing neurodegenerative changes based on neuromelanin MRI according to claim 1, characterized in that, The region of interest (ROI) is extracted from the preprocessed MRI image data, specifically including: Based on brain anatomical atlases, image segmentation is used to manually or automatically delineate brain regions containing neuromelanin on the preprocessed MRI image data, and these brain regions containing neuromelanin are designated as regions of interest; the brain regions containing neuromelanin include: substantia nigra pars compacta and locus coeruleus.

5. The method for assessing neurodegenerative changes based on neuromelanin MRI according to claim 1, characterized in that, MRI signal feature analysis is performed on the region of interest to obtain MRI signal features, specifically including: Based on the region of interest, MRI signal characteristic parameters of neuronal melanin within the region of interest are calculated, and these MRI signal characteristic parameters are used as input MRI signal characteristics into the neurodegenerative change assessment model. The MRI signal characteristic parameters include: MRI signal intensity, signal homogeneity, T1 relaxation time, and T2 relaxation time. The signals in the MRI signal intensity and signal homogeneity include: T1-weighted imaging signal, T2-weighted imaging signal, and magnetization transfer imaging signal.

6. The method for assessing neurodegenerative changes based on neuromelanin MRI according to claim 1, characterized in that, The neurodegenerative change assessment model is either an SVM model or a CNN model.

7. A device for assessing neurodegenerative changes based on neuromelanin MRI, characterized in that, The neurodegenerative change assessment device based on neuromelanin MRI includes: The MRI image acquisition module is used to acquire MRI image data of the individual to be evaluated; the MRI image data includes multi-sequence MRI image data, including three-dimensional T1-weighted imaging, two-dimensional T2-weighted imaging, and magnetization transfer imaging. The image preprocessing module is used to preprocess the MRI image data to obtain preprocessed MRI image data; The region of interest extraction module is used to extract the region of interest from the preprocessed MRI image data to obtain the region of interest. The signal feature analysis module is used to perform MRI signal feature analysis on the region of interest to obtain MRI signal features; The neurodegenerative change assessment module is used to input the MRI signal features into the neurodegenerative change assessment model and output the neurodegenerative change assessment result of the individual to be assessed; the neurodegenerative change assessment model is a pre-trained model based on machine learning algorithm and used for neurodegenerative change assessment; the neurodegenerative change assessment result is a graded result of the degree of neurodegenerative change, used to represent the degree level of neurodegenerative change of the individual to be assessed.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the neurodegenerative change assessment method based on neuromelanin MRI as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the neurodegenerative change assessment method based on neuromelanin MRI as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the neurodegenerative change assessment method based on neuromelanin MRI as described in any one of claims 1-6.

Images