Raman spectroscopy-based glioma IDH mutation detection method and device

Abstract

The present application relates to the field of Raman spectroscopy detection, and discloses a Raman spectroscopy-based glioma IDH mutation detection method and device. The method comprises: performing Raman spectroscopy scanning on a glioma tissue sample under test to obtain Raman spectroscopy data; preprocessing the Raman spectroscopy data to obtain normalized Raman spectroscopy data; extracting intensity values at characteristic shifts from the normalized Raman spectroscopy data; and inputting the intensity values at the characteristic shifts into a classification model to calculate a classification prediction value, wherein the classification model is a multivariate linear equation of the classification prediction value and the intensity values at the characteristic shifts, and the classification prediction value is used for assisting in determining whether the glioma tissue sample under test is of an IDH-mutant type. The present application allows for rapid and accurate detection of the IDH mutation status in gliomas.

Description

A Raman spectroscopy-based method and device for detecting IDH mutations in gliomas

[0001] This application claims priority to Chinese Patent Application No. 202411523305.0, filed on October 30, 2024, entitled "A Method and Apparatus for Detecting Glioma IDH Mutations Based on Raman Spectroscopy", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of Raman spectroscopy detection, and in particular to a method and apparatus for detecting IDH mutations in gliomas based on Raman spectroscopy. Background Technology

[0003] Gliomas are common central nervous system tumors, and accurate molecular testing is crucial for guiding treatment and prognostic assessment. Among these, isocitrate dehydrogenase (IDH) gene mutations are one of the most common molecular variations in gliomas, closely related to their occurrence, development, and prognosis. IDH gene mutations are an active molecular alteration in gliomas, and their clinical relevance is mainly reflected in the fact that patients with IDH-mutant gliomas have a better prognosis and increased sensitivity to chemotherapy and radiotherapy compared to those with wild-type IDH. IDH mutations lead to the production of the abnormal metabolite D-2-hydroxyglutarate (D-2HG), which can interfere with DNA and histone methylation patterns, thereby affecting the epigenetic state of tumor cells and making them more sensitive to treatment. For IDH-mutant gliomas, IDH inhibitors have shown potential in clinical trials. These drugs may inhibit tumor growth by suppressing the abnormal activity of mutant IDH and reducing the production of D-2HG. IDH mutations can also alter the immune microenvironment of gliomas, regulating immune checkpoint gene expression and chemokine secretion, and affecting immune cell infiltration and function. Therefore, immunotherapy may be a novel treatment strategy for patients with IDH-mutant gliomas. Furthermore, IDH mutation status is crucial for guiding surgical resection. For example, when patients are under 45 years old and have a KPS score of less than 80, extended resection can improve the survival prognosis of patients with low-grade IDH-mutant astrocytomas. Therefore, rapid detection of the IDH mutation status of gliomas is essential for guiding surgical strategies and postoperative adjuvant therapy.

[0004] Currently, conventional methods for detecting IDH mutations require lengthy procedures and complex experimental operations, lacking efficient, convenient, and rapid detection methods. Traditional intraoperative pathological examination methods include intraoperative frozen sections, rapid immunohistochemistry, and intraoperative cytology. Although these pathological diagnostic methods have relatively high accuracy, they are time-consuming and detrimental to the overall surgical process. For example, intraoperative frozen sections, the most widely used method, require approximately 30–40 minutes. Summary of the Invention

[0005] The purpose of this application is to provide a method and device for detecting IDH mutations in gliomas based on Raman spectroscopy, so as to achieve rapid and accurate detection of IDH mutation status in gliomas.

[0006] To achieve the above objectives, this application provides the following solution.

[0007] In a first aspect, this application provides a Raman spectroscopy-based method for detecting IDH mutations in gliomas, comprising: performing Raman spectroscopy scanning on a glioma tissue sample to be tested to obtain Raman spectral data; preprocessing the Raman spectral data to obtain normalized Raman spectral data; and extracting intensity values ​​at characteristic shifts from the normalized Raman spectral data; wherein the characteristic shifts include a Raman shift of 1161 cm⁻¹. -1 1200cm -1 1412cm -1 1518cm -1 1524cm -1 1592cm -1 2839cm -1 2916cm -1 2958cm -1 2971cm -1 3176cm -1 3180cm -1 and 3184cm -1 The intensity value at the characteristic displacement is input into the classification model to calculate the classification prediction value. The classification model is a multivariate linear equation relating the classification prediction value and the intensity value at the characteristic displacement. The classification prediction value is used to assist in determining whether the glioma tissue sample to be tested is an IDH-mutant glioma. If the absolute value of the classification prediction value is greater than or equal to a predetermined threshold, it is determined to be an IDH-mutant glioma. If the absolute value of the classification prediction value is less than the predetermined threshold, it is determined to be an IDH-wild-type glioma.

[0008] In one exemplary embodiment, preprocessing the Raman spectral data to obtain normalized Raman spectral data includes: removing fluorescence background from the Raman spectral data to obtain fluorescence-removed Raman spectral data; smoothing the fluorescence-removed Raman spectral data to obtain smoothed Raman spectral data; and normalizing the smoothed Raman spectral data to obtain normalized Raman spectral data.

[0009] In an exemplary embodiment, the classification model is determined based on the LASSO regression algorithm. The process of determining the classification model includes: acquiring several Raman spectral samples labeled with the IDH mutation status of gliomas, preprocessing them, and extracting feature spectral information to construct a sample dataset; the sample dataset includes feature spectral information corresponding to several normalized Raman spectral samples and the IDH mutation status of gliomas; the feature spectral information includes intensity values ​​at several Raman shifts; the IDH mutation status of gliomas includes 1 and 0, where 1 represents IDH-mutant gliomas and 0 represents IDH-wild-type gliomas; using the IDH mutation status of gliomas as the target variable and the feature spectral information as the feature variable, a linear regression model is constructed; based on the sample dataset, 5-fold cross-validation is used to determine the optimal regularization parameter value, and based on the optimal regularization parameter value, the LASSO regression algorithm is used to train the linear regression model, gradually reducing the coefficients of irrelevant Raman shifts in the linear regression model to zero, thereby obtaining the feature shifts and the classification model.

[0010] In an exemplary embodiment, the expression for the classification model is: y = 0.7273 + (-0.3157 × I 1161 )+0.2600×I 1200 +0.1042×I 1412 +(-0.1198×I 1518 )+(-0.5139×I 1524 )+(-0.1682×I 1592 )+0.0769×I 2839 +0.1626×I 2916 +0.0212×I 2958 +0.1187×I 2971 +(-0.2708×I 3176 )+(-0.2196×I 3180 )+(-0.0287×I 3184 ); where y represents the classification prediction value. When |y|≥0.5, it is classified as IDH-mutant glioma; when |y|<0.5, it is classified as IDH-wild-type glioma; I 1161 This indicates a Raman displacement of 1161 cm. -1 Intensity value at; I1200 This indicates a Raman displacement of 1200 cm. -1 Intensity value at; I 1412 This indicates a Raman displacement of 1412 cm. -1 Intensity value at; I 1518 This indicates a Raman displacement of 1518 cm. -1 Intensity value at; I 1524 This indicates a Raman displacement of 1524 cm. -1 Intensity value at; I 1592 This indicates a Raman displacement of 1592 cm. -1 Intensity value at; I 2839 This indicates a Raman displacement of 2839 cm. -1 Intensity value at; I 2916 This indicates a Raman displacement of 2916 cm. -1 Intensity value at; I 2958 This indicates a Raman displacement of 2958 cm. -1 Intensity value at; I 2971 This indicates a Raman displacement of 2971 cm. -1 Intensity value at; I 3176 This indicates a Raman displacement of 3176 cm. -1 Intensity value at; I 3180 This indicates a Raman displacement of 3180 cm. -1 Intensity value at; I 3184 This indicates a Raman displacement of 3184 cm. -1 The intensity value at that location.

[0011] In one exemplary embodiment, removing the fluorescence background from the Raman spectral data to obtain Raman spectral data with the fluorescence background removed includes: using the background removal function built into the RamPy library of Python to remove the fluorescence background from the Raman spectral data to obtain Raman spectral data with the fluorescence background removed.

[0012] In one exemplary embodiment, the Raman spectral data with the fluorescence background removed is subjected to spectral smoothing to obtain smoothed Raman spectral data, including: using the Savitzky-Golay smoothing algorithm to perform spectral smoothing on the Raman spectral data with the fluorescence background removed to obtain smoothed Raman spectral data.

[0013] In one exemplary embodiment, normalizing the smoothed Raman spectral data to obtain normalized Raman spectral data includes: normalizing the smoothed Raman spectral data using a max-min normalization algorithm to obtain normalized Raman spectral data.

[0014] Secondly, this application provides a Raman spectroscopy-based glioma IDH mutation detection device, employing the aforementioned Raman spectroscopy-based glioma IDH mutation detection method, comprising: a laser for emitting laser light onto a glioma tissue sample to be tested; a spectrometer for collecting the Raman light scattered by the glioma tissue sample to obtain Raman spectral data; and a computer connected to the spectrometer for preprocessing the Raman spectral data to obtain normalized Raman spectral data, extracting intensity values ​​at characteristic shifts from the normalized Raman spectral data, and inputting the intensity values ​​at characteristic shifts into a classification model to calculate a classification prediction value; wherein if the absolute value of the classification prediction value is greater than or equal to a predetermined threshold, it is determined to be an IDH-mutant glioma; and if the absolute value of the classification prediction value is less than the predetermined threshold, it is determined to be an IDH wild-type glioma.

[0015] In an exemplary embodiment, the glioma IDH mutation detection device based on Raman spectroscopy further includes: an optical fiber probe, connected to the laser and the spectrometer respectively, for transmitting the laser emitted by the laser to the surface of the glioma tissue sample to be tested, and transmitting the Raman light scattered from the surface of the glioma tissue sample to be tested to the spectrometer.

[0016] In an exemplary embodiment, the Raman spectroscopy-based glioma IDH mutation detection device further includes: a display connected to the computer for displaying the classification prediction value and the auxiliary determination result; the auxiliary determination result is determined based on the classification prediction value.

[0017] In an exemplary embodiment, the Raman spectroscopy-based glioma IDH mutation detection device further includes: a movable slide for placing the glioma tissue sample to be tested, and for adjusting the position and height of the glioma tissue sample to be tested.

[0018] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method and apparatus for detecting IDH mutations in gliomas based on Raman spectroscopy. First, Raman spectroscopy is performed on the glioma tissue sample to be tested to obtain Raman spectral data. Then, the Raman spectral data is preprocessed and features are extracted to obtain the intensity values ​​at characteristic shifts. Finally, the intensity values ​​at the characteristic shifts are input into a pre-determined classification model to calculate a classification prediction value, which is used to assist in determining whether the glioma tissue sample to be tested is an IDH-mutant glioma. Compared with the prior art, this application uses Raman spectroscopy technology, which eliminates the need for complex preprocessing and preparation of the glioma tissue sample to be tested. The operation is simple, the detection time is short, and the results are obtained rapidly. Furthermore, this application utilizes a classification model to calculate the classification prediction value based on the intensity values ​​at Raman shifts that are highly correlated with the IDH mutation state, enabling accurate identification of the IDH mutation state in gliomas. Attached Figure Description

[0019] 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.

[0020] Figure 1 is a flowchart of the Raman spectroscopy-based method for detecting IDH mutations in gliomas provided in this application.

[0021] Figure 2 shows the average Raman spectra of IDH mutant glioma and IDH wild-type glioma provided in this application.

[0022] Figure 3 is a curve showing the predictive performance of the classification model provided in this application.

[0023] Figure 4 is a structural diagram of the glioma IDH mutation detection device based on Raman spectroscopy provided in this application.

[0024] Figure labels: Laser-1, Spectrometer-2, Computer-3, Monitor-4. Detailed Implementation

[0025] 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.

[0026] The purpose of this application is to provide a method and device for detecting IDH mutations in gliomas based on Raman spectroscopy. By utilizing Raman spectroscopy technology to analyze glioma tissue samples, the mutation status of the IDH gene can be identified, thereby enabling rapid diagnosis and treatment planning for gliomas. This application provides a simple, efficient, and accurate method and device for detecting IDH mutations in gliomas, offering a new technical means for the field of clinical medical diagnosis and treatment.

[0027] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] In one exemplary embodiment, this application provides a Raman spectroscopy-based method for detecting IDH mutations in gliomas. This method is executed by a computer device, specifically a terminal or server, or both. As shown in FIG1, in this embodiment, the Raman spectroscopy-based method for detecting IDH mutations in gliomas includes the following steps.

[0029] Step S1: Perform Raman spectroscopy scanning on the glioma tissue sample to be tested to obtain Raman spectral data.

[0030] The glioma tissue sample to be tested can be collected directly during the operation without any sectioning. Simply take a suitable size (2–20 mm in length) and place it on a glass slide. Furthermore, the integration time for Raman spectroscopy scanning is controlled to within 5 seconds.

[0031] Step S2: Preprocess the Raman spectral data to obtain normalized Raman spectral data.

[0032] Specifically, the Raman spectral data is first processed to remove the fluorescence background, resulting in Raman spectral data with the fluorescence background removed; then, the Raman spectral data with the fluorescence background removed is smoothed, resulting in smoothed Raman spectral data; finally, the smoothed Raman spectral data is normalized, resulting in normalized Raman spectral data.

[0033] Preferably, the background removal process uses the built-in background removal function in Python's RamPy library. Smoothing is performed using the Savitzky-Golay smoothing algorithm, with the Python function name being `savgol_filter`. Normalization is performed using the min-max normalization algorithm, with the formula: Where x' is the normalized Raman spectral data, x is the smoothed Raman spectral data, min(x) is the minimum value of the smoothed Raman spectral data, and max(x) is the maximum value of the smoothed Raman spectral data.

[0034] Step S3: Extract the intensity values ​​at characteristic shifts from the normalized Raman spectral data. Specifically, the characteristic shifts include the Raman shift at 1161 cm⁻¹. -1 1200cm -1 1412cm -1 1518cm -1 1524cm -1 1592cm -1 2839cm -1 2916cm -1 2958cm -1 2971cm -1 3176cm-1 3180cm -1 and 3184cm -1 These Raman shifts are highly correlated with IDH mutation status, which facilitates accurate identification of IDH mutation status in gliomas.

[0035] Step S4: Input the intensity value at the feature displacement into the classification model to calculate the classification prediction value. This classification model is determined based on machine learning or pattern recognition algorithms, specifically a multivariate linear equation relating the classification prediction value and the intensity value at the feature displacement. This classification prediction value is used to assist in determining whether the glioma tissue sample to be tested is an IDH-mutant glioma (or an IDH-wild-type glioma). If the absolute value of the classification prediction value is greater than or equal to a predetermined threshold, it is determined to be an IDH-mutant glioma; if the absolute value of the classification prediction value is less than the predetermined threshold, it is determined to be an IDH-wild-type glioma.

[0036] Preferably, this application determines the classification model based on the Least Absolute Shrinkage and Selection Operator (LASSO) regression algorithm. Specific steps include: acquiring several Raman spectral samples labeled with glioma IDH mutation status, preprocessing them, and extracting feature spectral information to construct a sample dataset; the sample dataset includes feature spectral information corresponding to several normalized Raman spectral samples and glioma IDH mutation status; the feature spectral information includes intensity values ​​at several Raman shifts; the glioma IDH mutation status includes 1 and 0, where 1 represents IDH-mutant glioma and 0 represents IDH-wild-type glioma; using the glioma IDH mutation status as the target variable and the feature spectral information as the feature variable, a linear regression model is constructed; based on the sample dataset, 5-fold cross-validation is used to determine the optimal regularization parameter value, and based on the optimal regularization parameter value, the LASSO regression algorithm is used to train the linear regression model, gradually reducing the coefficients of irrelevant Raman shifts in the linear regression model to zero, thus obtaining the feature shifts and the classification model.

[0037] In one specific embodiment, this application constructs a sample dataset based on spectral data from 2393 retrospectively included 620 patients for training. The LASSO regression algorithm is used for 5-fold cross-validation. The optimal regularization parameter λ value (λ = 0.0046) is selected to gradually reduce the coefficients of irrelevant Raman shifts to zero. Finally, 13 feature shifts are selected to generate a classification model for predicting IDH mutation status.

[0038] When using the LASSO regression algorithm, its cost function expression is first defined as follows:

[0039] Where n is the number of samples, p is the number of features, and yi Let x be the observation value of the i-th sample. ij Let β be the j-th feature of the i-th sample, and β be the regression coefficient. j Let be the regression coefficient of the j-th feature, β0 be the initial value of the regression coefficient, and λ be the regularization parameter used to control the strength of regularization. This process minimizes the cost function while obtaining a set of regression coefficients corresponding to each feature, making the predicted value closest to the actual observed value.

[0040] The specific algorithm steps are as follows.

[0041] Data preparation: Spectral data from 2393 patients were divided into training and testing sets.

[0042] Standardization (preprocessing): Standardize the spectral data to ensure that different features have the same scale.

[0043] 5-fold cross-validation: The training data is randomly divided into 5 parts. Each time, 4 parts are used for training and 1 part is used for validation. This process is repeated 5 times.

[0044] Model training: The model is trained using the LASSO regression algorithm in each cross-validation, and the feature selection and model complexity are controlled by adjusting the parameter λ.

[0045] Choosing the optimal λ value: Through cross-validation, select the λ value that minimizes the prediction error on the validation set (here, λ = 0.0046).

[0046] Feature selection: The model was trained using the optimal λ value, and the coefficients of the unrelated Raman displacements were gradually reduced to zero, ultimately selecting 13 feature displacements.

[0047] Model generation: Generate the final classification model based on the selected feature shifts.

[0048] The classification model constructed using the above method demonstrates excellent performance on the validation set. The average Raman spectra of IDH mutant gliomas and IDH wild-type gliomas are shown in Figure 2, and the predictive power curves of the classification model are shown in Figure 3. The area under the curve (AUC) of the classification model reaches a maximum of 94.6%, and the sensitivity reaches 89.6%.

[0049] The 13 selected characteristic displacements can be divided into the following 8 characteristic peaks.

[0050] 1161cm -1It is formed by the C-C and CN bonds of β-carotene. It can reduce lipid peroxidation. Its antioxidant properties are mainly manifested in its ability to scavenge free radicals and prevent the chain reaction of free radicals, thereby reducing the damage of free radicals to cells.

[0051] 1200cm -1 It is formed by the mixing of lipids and nucleotides.

[0052] 1412cm -1 Formed by the combined action of pyruvate and lipids, with a molecular weight of 1200 cm. -1 With similar vibrational patterns, pyruvate is an important intermediate in the metabolism of sugars in all biological cells and in the interconversion of various substances in the body.

[0053] 1518~1524cm -1 : with 1161cm -1 The peaks exhibit the same vibrational modes and proportional signal intensities, and the pure β-carotene spectrum also shows a second peak here.

[0054] 1592cm -1 This peak position may be related to the Amide I band, primarily due to the C=O stretching vibration. It may also correspond to characteristic vibrations of aromatic compounds, such as tyrosine and tryptophan. Tryptophan is a precursor for the synthesis of many bioactive molecules, such as pigments, hormones, and neurotransmitters.

[0055] 2839cm -1 The Raman peak of the methyl group is caused by the stretching vibration of the CH bond in the methyl group and is related to the protein content.

[0056] 2916~2971cm -1 The characteristic peak of methyl bond CH3 is related to lipid content.

[0057] 3176~3184cm -1 These peaks are typically associated with Amide B vibrations in proteins, involving NH stretching. Vibrations in this region may characterize the protein's secondary structure.

[0058] The final classification model is expressed as follows: y = 0.7273 + (-0.3157 × I 1161 )+0.2600×I 1200 +0.1042×I 1412 +(-0.1198×I 1518 ) +(-0.5139×I 1524 )+(-0.1682×I 1592 )+0.0769×I 2839+0.1626×I 2916 +0.0212×I 2958 +0.1187×I 2971 +(-0.2708×I 3176 )+(-0.2196×I 3180 )+(-0.0287×I 3184 ).

[0059] Where y represents the classification prediction value; when |y|≥0.5, it is classified as IDH-mutant glioma, and when |y|<0.5, it is classified as IDH-wild-type glioma; 1161 This indicates a Raman displacement of 1161 cm. -1 Intensity value at; I 1200 This indicates a Raman displacement of 1200 cm. -1 Intensity value at; I 1412 This indicates a Raman displacement of 1412 cm. -1 Intensity value at; I 1518 This indicates a Raman displacement of 1518 cm. -1 Intensity value at; I 1524 This indicates a Raman displacement of 1524 cm. -1 Intensity value at; I 1592 This indicates a Raman displacement of 1592 cm. -1 Intensity value at; I 2839 This indicates a Raman displacement of 2839 cm. -1 Intensity value at; I 2916 This indicates a Raman displacement of 2916 cm. -1 Intensity value at; I 2958 This indicates a Raman displacement of 2958 cm. -1 Intensity value at; I 2971 This indicates a Raman displacement of 2971 cm. -1 Intensity value at; I 3176 This indicates a Raman displacement of 3176 cm. -1 Intensity value at; I 3180 This indicates a Raman displacement of 3180 cm. -1 Intensity value at; I 3184 This indicates a Raman displacement of 3184 cm. -1 The intensity value at that location.

[0060] In an exemplary embodiment, this application provides a Raman spectroscopy-based glioma IDH mutation detection device. As shown in FIG4, the Raman spectroscopy-based glioma IDH mutation detection device provided in this application includes a laser 1, a spectrometer 2, a computer 3, and a display 4. The laser 1 emits a laser beam towards the glioma tissue sample to be tested. The spectrometer 2 collects the Raman light scattered by the glioma tissue sample to obtain Raman spectral data. The computer 3 is connected to the spectrometer 2 and is used to preprocess the Raman spectral data to obtain normalized Raman spectral data, extract the intensity values ​​at characteristic shifts from the normalized Raman spectral data, and input the intensity values ​​at characteristic shifts into a classification model to calculate a classification prediction value. The display 4 is connected to the computer 3 and is used to display the classification prediction value and auxiliary judgment results determined based on the classification prediction value. If the absolute value of the classification prediction value is greater than or equal to a predetermined threshold, it is determined to be an IDH-mutant glioma; if the absolute value of the classification prediction value is less than the predetermined threshold, it is determined to be an IDH wild-type glioma.

[0061] Furthermore, the aforementioned device also includes an optical fiber probe. This optical fiber probe is connected to the laser 1 and the spectrometer 2, respectively, and is used to transmit the laser emitted by the laser 1 to the surface of the glioma tissue sample to be tested, and to transmit the Raman light scattered from the surface of the glioma tissue sample to the spectrometer 2.

[0062] Furthermore, the aforementioned device also includes a movable slide. This movable slide is used to place the glioma tissue sample to be tested, and to adjust the position and height of the glioma tissue sample.

[0063] The Raman spectroscopy-based method and apparatus for detecting IDH mutations in gliomas provided in this application have the following advantages.

[0064] 1. Fast: Utilizing Raman spectroscopy, the detection time is short and results are obtained quickly.

[0065] 2. Accuracy: By utilizing characteristic spectral information for analysis, the mutation status of the IDH gene can be accurately identified.

[0066] 3. Non-destructive: No additional processing or staining of tissue samples is required, thus maintaining the integrity of the samples.

[0067] 4. Simple: It is easy to operate and does not require complicated experimental conditions or professional skills.

[0068] In summary, this application provides a method and device for detecting IDH mutations in gliomas based on Raman spectroscopy, which has the advantages of being rapid, accurate, and non-destructive, and is suitable for clinical medical diagnosis and scientific research.

[0069] 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.

[0070] 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 detecting IDH mutations in gliomas based on Raman spectroscopy, characterized in that, include: Raman spectroscopy was performed on the glioma tissue sample to be tested to obtain Raman spectral data; The Raman spectral data are preprocessed to obtain normalized Raman spectral data; Intensity values ​​at characteristic shifts are extracted from the normalized Raman spectral data; the characteristic shifts include a Raman shift of 1161 cm⁻¹. -1 1200cm -1 1412cm -1 1518cm -1 1524cm -1 1592cm -1 2839cm -1 2916cm -1 2958cm -1 2971cm -1 3176cm -1 3180cm -1 and 3184cm -1 ; The intensity value at the characteristic displacement is input into the classification model to calculate the classification prediction value; the classification model is a multivariate linear equation of the classification prediction value and the intensity value at the characteristic displacement; the classification prediction value is used to assist in determining whether the glioma tissue sample to be tested is an IDH mutant glioma; If the absolute value of the classification prediction value is greater than or equal to a predetermined threshold, it is determined to be an IDH mutant glioma; and if the absolute value of the classification prediction value is less than the predetermined threshold, it is determined to be an IDH wild-type glioma.

2. The method for detecting glioma IDH mutations based on Raman spectroscopy according to claim 1, characterized in that, The Raman spectral data is preprocessed to obtain normalized Raman spectral data, including: The Raman spectral data are subjected to fluorescence background removal processing to obtain Raman spectral data with fluorescence background removed; The Raman spectral data with the fluorescence background removed are subjected to spectral smoothing to obtain smoothed Raman spectral data; The smoothed Raman spectral data are then normalized to obtain normalized Raman spectral data.

3. The method for detecting glioma IDH mutations based on Raman spectroscopy according to claim 1, characterized in that, The classification model is determined based on the LASSO regression algorithm; the process of determining the classification model includes: A number of Raman spectral samples labeled with the IDH mutation status of gliomas were obtained, and preprocessed and feature spectral information was extracted to construct a sample dataset. The sample dataset includes feature spectral information and glioma IDH mutation status corresponding to several normalized Raman spectral samples. The feature spectral information includes intensity values ​​at several Raman shifts. The glioma IDH mutation status includes 1 and 0, where 1 represents IDH-mutant glioma and 0 represents IDH-wild-type glioma. A linear regression model was constructed using the glioma IDH mutation status as the target variable and the characteristic spectral information as the characteristic variable. Based on the sample dataset, the optimal regularization parameter value is determined using 5-fold cross-validation. Based on the optimal regularization parameter value, the linear regression model is trained using the LASSO regression algorithm. The coefficients of the unrelated Raman shifts in the linear regression model are gradually reduced to zero to obtain the feature shifts and classification model.

4. The method for detecting glioma IDH mutations based on Raman spectroscopy according to claim 1, characterized in that, The expression for the classification model is: y = 0.7273 + (-0.3157 × I) 1161 )+0.2600×I 1200 +0.1042×I 1412 +(-0.1198×I 1518 ) +(-0.5139×I 1524 )+(-0.1682×I 1592 )+0.0769×I 2839 +0.1626×I 2916 +0.0212×I 2958 +0.1187×I 2971 +(-0.2708×I 3176 )+(-0.2196×I 3180 )+(-0.0287×I 3184 ); Where y represents the classification prediction value; when |y|≥0.5, it is classified as IDH-mutant glioma, and when |y|<0.5, it is classified as IDH-wild-type glioma; 1161 This indicates a Raman displacement of 1161 cm. -1 Intensity value at; I 1200 This indicates a Raman displacement of 1200 cm. -1 Intensity value at; I 1412 This indicates a Raman displacement of 1412 cm. -1 Intensity value at; I 1518 This indicates a Raman displacement of 1518 cm. -1 Intensity value at; I 1524 This indicates a Raman displacement of 1524 cm. -1 Intensity value at; I 1592 This indicates a Raman displacement of 1592 cm. -1 Intensity value at; I 2839 This indicates a Raman displacement of 2839 cm. -1 Intensity value at; I 2916 This indicates a Raman displacement of 2916 cm. -1 Intensity value at; I 2958 This indicates a Raman displacement of 2958 cm. -1 Intensity value at; I 2971 This indicates a Raman displacement of 2971 cm. -1 Intensity value at; I 3176 This indicates a Raman displacement of 3176 cm. -1 Intensity value at; I 3180 This indicates a Raman displacement of 3180 cm. -1 Intensity value at; I 3184 This indicates a Raman displacement of 3184 cm. -1 The intensity value at that location.

5. The method for detecting glioma IDH mutations based on Raman spectroscopy according to claim 2, characterized in that, The Raman spectral data with removed fluorescence background is subjected to spectral smoothing to obtain smoothed Raman spectral data, including: The Raman spectral data with removed fluorescence background was smoothed using the Savitzky-Golay smoothing algorithm to obtain smoothed Raman spectral data.

6. The method for detecting glioma IDH mutations based on Raman spectroscopy according to claim 2, characterized in that, The smoothed Raman spectral data are normalized to obtain normalized Raman spectral data, including: The smoothed Raman spectral data are normalized using the max-min normalization algorithm to obtain normalized Raman spectral data.

7. A Raman spectroscopy-based glioma IDH mutation detection device, employing the Raman spectroscopy-based glioma IDH mutation detection method as described in claim 1, characterized in that, include: A laser used to emit laser light onto a glioma tissue sample to be tested; A spectrometer is used to collect the Raman light scattered by the glioma tissue sample to be tested, and to obtain Raman spectral data; A computer, connected to the spectrometer, is used to preprocess the Raman spectral data to obtain normalized Raman spectral data, extract the intensity values ​​at characteristic shifts from the normalized Raman spectral data, and input the intensity values ​​at characteristic shifts into a classification model to calculate the classification prediction value. If the absolute value of the classification prediction value is greater than or equal to a predetermined threshold, it is determined to be an IDH mutant glioma; and if the absolute value of the classification prediction value is less than the predetermined threshold, it is determined to be an IDH wild-type glioma.

8. The Raman spectroscopy-based glioma IDH mutation detection device according to claim 7, characterized in that, Also includes: An optical fiber probe is connected to the laser and the spectrometer, respectively, for transmitting the laser emitted by the laser to the surface of the glioma tissue sample to be tested, and for transmitting the Raman light scattered from the surface of the glioma tissue sample to the spectrometer.

9. The Raman spectroscopy-based glioma IDH mutation detection device according to claim 7, characterized in that, Also includes: A display, connected to the computer, is used to display the classification prediction values ​​and auxiliary judgment results; The auxiliary determination result is determined based on the classification prediction value.

10. The Raman spectroscopy-based glioma IDH mutation detection device according to claim 7, characterized in that, Also includes: A movable slide is used to place the glioma tissue sample to be tested and to adjust the position and height of the glioma tissue sample to be tested.

Images