Lymphoma cell classification system

Abstract

The invention provides a lymphoma cell classification system, and relates to the technical field of biomedical detection. Comprising an injection pump, an optical scattering imaging subsystem, an electrochemical detection subsystem and a data analysis subsystem, the injection pump and the data analysis subsystem are connected with the optical scattering imaging subsystem and the electrochemical detection subsystem; the injection pump is used for introducing a to-be-detected sample into the optical scattering imaging subsystem and the electrochemical detection subsystem, the optical scattering imaging subsystem is used for acquiring feature image data of the to-be-detected sample, and the electrochemical detection subsystem is used for acquiring an electrochemical signal of the to-be-detected sample; and the data analysis subsystem is used for performing data fusion and classification on the feature image data and the electrochemical signal by using a machine learning algorithm to obtain a classification result. The problem of low classification accuracy of lymphoma cells in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of biomedical detection technology, and in particular to a lymphoma cell classification system. Background Technology

[0002] Lymphoma, a malignant tumor originating from the lymphatic system, has become one of the top ten cancers with the highest incidence rate worldwide, and its incidence continues to rise, posing a significant challenge to public health. Based on molecular characteristics, cellular origin, and clinical features, lymphoma is mainly divided into Hodgkin lymphoma (HL) and non-Hodgkin lymphoma (NHL), with NHL accounting for over 90%. Early and accurate diagnosis is crucial for effective treatment of lymphoma, but existing diagnostic methods have significant limitations: imaging examinations, blood tests, and biomarker detection have limited accuracy, while tissue biopsy, although the "gold standard" for diagnosis, is invasive and may cause complications such as bleeding and infection. Therefore, there is an urgent need to develop non-invasive, highly accurate alternative diagnostic technologies.

[0003] With advancements in imaging technology, particularly two-dimensional light scattering (BLS), detailed, high-resolution information at the single-cell level is provided. This method can reveal complex details of cell structure, providing insights into physical characteristics such as cell size, shape, and internal distribution, and holds promise as an ideal tool for lymphoma cell analysis. However, scattering images alone are often complex, requiring advanced statistical methods such as deep learning to fully interpret the data and extract meaningful patterns. Previous studies have shown that combining light scattering with machine learning can achieve more robust statistical analysis and improve classification accuracy. For example, Su et al. used a label-free cell technique combining anisotropic cytometers and machine learning to classify single ovarian cancer cells and normal cell lines with an accuracy of 92.84%. Electrochemical methods are also gaining increasing attention due to their ability to provide supplemental functional data. These techniques, based on electrochemical reaction principles, can detect cellular metabolites through electrical signals such as current and potential, enabling rapid and direct analysis. Electrochemical sensors based on principles such as cyclic voltammetry (CV) and electrochemical ionization (it) can reflect cellular functional status by detecting cellular metabolic markers (such as hydrogen peroxide H2O2), offering advantages such as high real-time performance and rapid response. For example, the application of novel composite material electrodes such as graphene and MXene has enabled highly sensitive detection of multiple target metabolites such as uric acid and dopamine. However, relying solely on electrochemical signals cannot reflect cell morphological characteristics and makes it difficult to directly distinguish cell types.

[0004] Currently, relying solely on light scattering technology combined with machine learning can achieve binary classification of tumor cells and normal cells, but the multi-classification effect for different subtypes of lymphoma cells and normal cells is poor, making it difficult to distinguish between different subtypes of lymphoma cells; electrochemical technology can detect metabolic markers of cells in real time and rapidly to reflect the functional state of cells, but relying solely on electrochemical signals cannot reflect cell morphological characteristics, making it difficult to directly distinguish cell types. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, the purpose of this invention is to provide a lymphoma cell classification system, which solves the problem of low accuracy in lymphoma cell classification in the prior art.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A lymphoma cell classification system, comprising:

[0008] Injection pump, optical scattering imaging subsystem, electrochemical detection subsystem, and data analysis subsystem;

[0009] The syringe pump and the data analysis subsystem are both connected to the optical scattering imaging subsystem and the electrochemical detection subsystem.

[0010] The syringe pump is used to introduce the sample to be tested into the optical scattering imaging subsystem and the electrochemical detection subsystem. The optical scattering imaging subsystem is used to acquire the feature image data of the sample to be tested. The electrochemical detection subsystem is used to acquire the electrochemical signal of the sample to be tested. The data analysis subsystem is used to use machine learning algorithms to perform data fusion and classification on the feature image data and the electrochemical signal to obtain a classification result.

[0011] Preferably, the optical scattering imaging subsystem includes:

[0012] The laser, neutral density filter, first objective lens, fiber optic coupling module, optical excitation cell, second objective lens, and CMOS sensor are connected in sequence.

[0013] The optical excitation cell is connected to the injection pump, and the CMOS sensor is connected to the data analysis subsystem;

[0014] The laser is used to emit laser light, the neutral density filter is used to attenuate and adjust the power of the laser light, the first objective lens is used to focus the adjusted laser light, the fiber optic coupling module is used to transmit the focused laser light to the optical excitation cell using an optical fiber, the optical excitation cell is used to store the sample to be tested and receive the focused laser light to excite cells and generate scattered light, the second objective lens is used to acquire the scattered light and transmit it to the CMOS sensor, the CMOS sensor is used to perform imaging based on the scattered light, obtain feature image data and transmit it to the data analysis subsystem.

[0015] Preferably, the wavelength of the laser is 532nm and the power of the laser is 50mW.

[0016] Preferably, the optical excitation cell comprises:

[0017] Bottom glass substrate, top glass sheet, and two spacers;

[0018] The two gaskets are located at the two ends of the bottom glass substrate and the top glass interlayer, respectively, to form a micro excitation cell. The micro excitation cell has a size of 24mm × 10mm and a thickness of 0.15mm.

[0019] Preferably, the numerical aperture of the second objective lens is 0.25.

[0020] Preferably, the electrochemical detection subsystem includes:

[0021] Three-electrode module, electrochemical active reaction cell and electrochemical workstation;

[0022] The electrochemical active reaction cell is connected to the injection pump, and the electrochemical workstation is connected to the data analysis subsystem;

[0023] The three-electrode module is used to perform electrochemical detection on the sample to be tested in the electrochemically active reaction cell to obtain an electrochemical signal. The electrochemical workstation is used to receive the electrochemical signal and transmit it to the data analysis subsystem.

[0024] Preferably, the three-electrode module includes:

[0025] Working electrode, counter electrode, and reference electrode.

[0026] The present invention discloses the following technical effects:

[0027] This invention provides a lymphoma cell classification system, comprising: an injection pump, an optical scattering imaging subsystem, an electrochemical detection subsystem, and a data analysis subsystem; the injection pump and the data analysis subsystem are both connected to the optical scattering imaging subsystem and the electrochemical detection subsystem; the injection pump is used to introduce the sample to be tested into the optical scattering imaging subsystem and the electrochemical detection subsystem; the optical scattering imaging subsystem is used to acquire feature image data of the sample to be tested; the electrochemical detection subsystem is used to acquire the electrochemical signal of the sample to be tested; and the data analysis subsystem is used to perform data fusion and classification on the feature image data and the electrochemical signal using a machine learning algorithm to obtain a classification result. This invention acquires cell morphological characteristics through two-dimensional light scattering label-free imaging, combines it with real-time electrochemical detection of metabolic signals, and integrates these signals through machine learning algorithms to overcome the limitations of single-modality cell differentiation among multiple cell types. Relying on label-free light scattering imaging technology, it eliminates the need for fluorescent or antibody labeling, avoiding interference with cell viability. Electrochemical detection uses a composite electrode to collect metabolic signals non-contactly, minimizing cell damage throughout the process, making it suitable for early clinical screening and reducing patient risk. The integration of data through machine learning ensures detection efficiency while maintaining the integrity of morphological and metabolic information, overcoming the problem of incomplete information from single technologies. The integrated system design lowers the operational threshold, and the high accuracy and subtype identification capabilities reduce reliance on invasive biopsies, making it suitable for early screening, recurrence monitoring, and other scenarios, providing a practical tool for the precise diagnosis of lymphoma. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram of a lymphoma cell classification system provided in an embodiment of the present invention;

[0030] Figure 2 A detailed schematic diagram of a lymphoma cell classification system provided in an embodiment of the present invention;

[0031] Figure 3 This is a diagram showing the results of optical scattering imaging and electrochemical detection of different cells using a lymphoma cell classification system, provided in an embodiment of the present invention. Figure 3 (A) is a representative scattering map of different cell types (HDLM-2, Daudi, HMy2.CIR) detected by the optical scattering imaging subsystem; Figure 3(B) is a schematic diagram of the current response curves of different cell types (HDLM-2, Daudi, HMy2.CIR) detected by the electrochemical detection subsystem after the addition of the stimulant fMLP;

[0032] Figure 4 This invention provides a lymphoma cell classification system that utilizes a support vector machine (SVM) classification model during five-fold cross-validation. The diagram illustrates the receiver operating characteristic (ROC) curves for different cell types (HMy2.CIR, Daudi, HDLM-2). Figure 4 (A) is a first schematic diagram illustrating the relationship between cell type sensitivity and 1-specificity; Figure 4 (B) is a second schematic diagram showing the relationship between cell type sensitivity and 1-specificity; Figure 4 (C) is the third schematic diagram showing the relationship between cell type sensitivity and 1-specificity; Figure 4 (D) is the fourth schematic diagram showing the relationship between cell type sensitivity and 1-specificity; Figure 4 (E) is the fifth schematic diagram showing the relationship between cell type sensitivity and 1-specificity;

[0033] Figure 5 A schematic diagram of the confusion matrix for classifying different cell types (HMy2.CIR, Daudi, HDLM-2) using a support vector machine (SVM) classification model in the lymphoma cell classification system provided in this embodiment of the invention during five-fold cross-validation. Figure 5 (A) is a schematic diagram of the first classification result; Figure 5 (B) is a schematic diagram of the second classification results; Figure 5 (C) is a schematic diagram of the third classification results; Figure 5 (D) is a schematic diagram of the fourth classification results; Figure 5 (E) is a schematic diagram of the fifth classification results.

[0034] Figure label:

[0035] 1-Injection pump, 2-Optical scattering imaging subsystem, 3-Electrochemical detection subsystem, 4-Data analysis subsystem. Detailed Implementation

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0037] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0038] like Figure 1 As shown, the present invention provides a lymphoma cell classification system, comprising:

[0039] Injection pump 1, optical scattering imaging subsystem 2, electrochemical detection subsystem 3, and data analysis subsystem 4;

[0040] The syringe pump 1 and the data analysis subsystem 4 are both connected to the optical scattering imaging subsystem 2 and the electrochemical detection subsystem 3.

[0041] The syringe pump 1 is used to introduce the sample to be tested into the optical scattering imaging subsystem 2 and the electrochemical detection subsystem 3. The optical scattering imaging subsystem 2 is used to acquire the feature image data of the sample to be tested. The electrochemical detection subsystem 3 is used to acquire the electrochemical signal of the sample to be tested. The data analysis subsystem 4 is used to use machine learning algorithms to perform data fusion and classification on the feature image data and the electrochemical signal to obtain a classification result.

[0042] Specifically, the syringe pump 1 controls the flow of cell samples and introduces the samples into the optical excitation cell and the electrochemical active reaction cell, ensuring that the cell samples stably enter the optical excitation cell and the electrochemical active reaction cell for detection in different modules; the syringe pump 1 simultaneously introduces cell samples into the optical excitation cell and the electrochemical active reaction cell through the pipeline, providing samples for the two detection systems.

[0043] Furthermore, the optical scattering imaging subsystem 2 includes:

[0044] The laser, neutral density filter, first objective lens, fiber optic coupling module, optical excitation cell, second objective lens, and CMOS sensor are connected in sequence.

[0045] The optical excitation cell is connected to the injection pump 1, and the CMOS sensor is connected to the data analysis subsystem 4;

[0046] The laser is used to emit laser light, the neutral density filter is used to attenuate and adjust the power of the laser light, the first objective lens is used to focus the adjusted laser light, the fiber optic coupling module is used to transmit the focused laser light to the optical excitation cell using an optical fiber, the optical excitation cell is used to store the sample to be tested and receive the focused laser light to excite cells and generate scattered light, the second objective lens is used to acquire the scattered light and transmit it to the CMOS sensor, the CMOS sensor is used to perform imaging based on the scattered light, obtain feature image data and transmit it to the data analysis subsystem 4.

[0047] Specifically, a diode-pumped solid-state laser (DPSSL) emits a 532nm wavelength laser to excite lymphoma cells. The laser power is 50mW. After emission from the DPSSL, the laser first passes through a neutral density filter (NDFilter) for power attenuation and adjustment to ensure the laser intensity is suitable for subsequent imaging. The adjusted laser is then focused by the first objective lens and transmitted via an optical fiber coupling module. The laser enters from one end of the fiber, while the other end is connected to the optical excitation cell, further guiding the laser into the cell for cell sample excitation and scattering imaging. Through this fiber optic transmission, the laser can be precisely transmitted to the optical excitation cell, ensuring the efficiency and stability of the excitation process.

[0048] Neutral density (ND) filters regulate the power output of the laser, ensuring that while maintaining the clarity of the scattered image, they protect living cells from damage caused by excessive laser irradiation. By appropriately attenuating the laser intensity, ND filters balance imaging accuracy and cell safety, ensuring the accuracy of experimental results and the physiological stability of cells; the ND filter is located between the laser beam and the objective lens, directly affecting the laser intensity.

[0049] Cell suspensions are injected into an optical excitation cell for light scattering excitation imaging. The optical excitation cell consists of a bottom glass substrate, a top glass plate, and two spacers located at opposite ends of the top plate and substrate layer, forming a miniature excitation cell in which the cell sample is suspended. The optical excitation cell measures 24 mm × 10 mm and has a thickness of 0.15 mm. Cells are excited by a laser within the cell, generating scattered light. This scattered light is captured and imaged by a second objective lens and a CMOS sensor, ultimately forming the cell's scattering imaging data.

[0050] The second objective lens captures the scattered light. With a numerical aperture of 0.25, the second objective lens effectively captures scattered light within the ranges of 75°≤θ≤105° and 75°≤φ≤105°, where θ is the polar angle, representing the angle between the incident light direction and the scattered light direction, and φ is the azimuth angle, referring to the angle between the incident light vibration surface and the scattered light surface. The second objective lens is connected to the optical excitation cell. The scattered light is captured through the second objective lens and transmitted to the CMOS sensor to complete the imaging process.

[0051] A CMOS sensor captures images of scattered light from cells. This sensor has a resolution of 1936×1460 pixels. The CMOS sensor is connected to a second objective lens, which is responsible for capturing the scattered light and transmitting it to the CMOS sensor for imaging. After imaging by the sensor, the scattered light image is transmitted to the data analysis subsystem 4 for subsequent data processing and analysis.

[0052] Furthermore, the electrochemical detection subsystem 3 includes:

[0053] Three-electrode module, electrochemical active reaction cell and electrochemical workstation;

[0054] The electrochemical active reaction cell is connected to the injection pump 1, and the electrochemical workstation is connected to the data analysis subsystem 4;

[0055] The three-electrode module is used to perform electrochemical detection on the sample to be tested in the electrochemical active reaction cell to obtain an electrochemical signal. The electrochemical workstation is used to receive the electrochemical signal and transmit it to the data analysis subsystem 4.

[0056] Furthermore, the three-electrode module includes:

[0057] Working electrode, counter electrode, and reference electrode.

[0058] Specifically, the 3D rGO-Ti3C2-MWCNTs electrode is used as the working electrode, the Pt electrode as the counter electrode, and the Ag / AgCl electrode as the reference electrode for electrochemical detection and recording of cell metabolites (such as H2O2).

[0059] The specific fabrication steps of the three-dimensional reduced graphene oxide-titanium carbide-multi-walled carbon nanotube (3D rGO-Ti3C2-MWCNTs) composite electrode include: injecting a mixed solution of graphene oxide (GO), titanium carbide (Ti3C2) and multi-walled carbon nanotubes (MWCNTs) into a polytetrafluoroethylene-lined autoclave and carrying out a hydrothermal reaction at 180°C for 4 hours, followed by air drying at room temperature to obtain the final electrode. These electrodes are installed in an electrochemically active reaction chamber to synergistically collect electrochemical signals.

[0060] The electrochemically active reaction cell employs a three-electrode system, using a platinum electrode as the counter electrode, an Ag / AgCl electrode as the reference electrode, and a 3D rGO-Ti3C2-MWCNTs electrode as the working electrode for electrochemical detection, monitoring the release of H2O2 to assess cellular metabolic activity. The electrochemically active reaction chamber is connected to the cell sample flow via a syringe pump 1. The system uses a three-electrode system (3D rGO-Ti3C2-MWCNTs composite electrode, Pt electrode, and Ag / AgCl electrode) to detect electrochemical signals.

[0061] The electrochemical workstation controls the potentiometer to record electrochemical signals, especially the amount of H2O2 released, for real-time monitoring of cell metabolism. The electrochemical workstation is connected to the electrochemical reaction chamber via the potentiometer to collect electrochemical signals and transmit them to the data analysis subsystem 4 for subsequent data processing and analysis.

[0062] More specifically, the electrochemical detection section employs a composite electrode for electrochemical detection. The electrode was prepared via a hydrothermal method, yielding a composite material with high electrocatalytic performance. The system uses a three-electrode setup: the working electrode is composed of a 3D rGO-Ti3C2-MWCNTs composite material, while the Pt and Ag / AgCl electrodes serve as the counting and reference electrodes, respectively. Electrochemical signals are measured using a potentiostat, and the release of H2O2 is tracked to provide real-time data on cellular metabolic activity. Simultaneously, a syringe pump 1 introduces cell samples into both the optical liquid-based chip and the electrochemical reaction chamber, enabling simultaneous detection by both methods. This allows for real-time integration of light scattering data and electrochemical signals, ensuring synchronization of the two measurement techniques.

[0063] Furthermore, the data analysis subsystem 4 is used to monitor, record, and process light scattering images and electrochemical signals obtained from the CMOS sensor and electrochemical workstation in real time, and to perform image processing, signal analysis, and data visualization. The data analysis subsystem 4 is connected to the CMOS sensor and the electrochemical workstation and is responsible for data processing and analysis.

[0064] Specifically, the light scattering section collected the scattered light from cells within the range of 75° to 105°, and obtained the characteristics of different subtypes of lymphocytes through two-dimensional light scattering images. The light scattering images were cropped, normalized, and adjusted to a standard size of 224×224 pixels. After image preprocessing, the following seven optical image features were extracted: number of speckles, average speckle area, total speckle area, average grayscale value, contrast, second angular moment, and image entropy.

[0065] In the electrochemical section, the cellular current response after the addition of the stimulant fMLP was recorded, particularly within the time window of 60.1 to 123.4 seconds, yielding 632 current response values. The difference between the current value at each time point and the baseline mean current was further calculated to obtain the current variation values.

[0066] To effectively combine optical image features with electrochemical data, linear interpolation was performed on the electrochemical data to maintain consistency with the light scattering data. Specifically, the current variation values ​​of different cell groups were expanded to the same number of data points: HMy2.CIR cells were expanded to 803 data points, Daudi cells to 800 data points, and HDLM-2 cells to 813 data points.

[0067] The processed electrochemical data was fused with the corresponding light scattering image features to form the input feature set for each cell. Ultimately, this method generated a total of 2,416 feature sets, which were then input into a Support Vector Machine (SVM) classification model. Five-fold cross-validation was used to evaluate the stability and generalization ability of the classification model, thereby ensuring the robustness and reliability of its classification results.

[0068] Furthermore, Figure 3 This image shows the results of optical scattering imaging and electrochemical detection of different cells using a lymphoma cell classification system. Figure 3 (A) are representative light scattering images of different cell types (HDLM-2, Daudi, HMy2.CIR) detected by the optical scattering imaging subsystem. The first row is a representative light scattering image of human B lymphocytes (HMy2.CIR cells), the second row is a representative light scattering image of human B lymphoma cells (Daudi cells), and the third row is a representative light scattering image of human Hodgkin lymphoma cells (HDLM-2 cells). Figure 3 (B) The current response curves of different cell types (HDLM-2, Daudi, HMy2.CIR) detected by the electrochemical detection subsystem after the addition of the stimulant fMLP are shown, illustrating the relationship between time (horizontal axis) and current (vertical axis) for each cell type. The current response curves for each cell type are represented by different colors: blue for HDLM-2 cells, red for Daudi cells, and black for HMy2.CIR cells. In each current response curve, the arrow indicates the time of addition of the stimulant fMLP, which is introduced at approximately 60 seconds.

[0069] Figure 4 Receiver operating characteristic (ROC) curves for different cell types (HMy2.CIR, Daudi, HDLM-2) in a five-fold cross-validation process using a Support Vector Machine (SVM) classification model for a lymphoma cell classification system. Each fold corresponds to a subplot (A to E), and each subplot shows the relationship between sensitivity and 1-specificity for each cell type at that fold. Cell types are represented by curves of different colors: HMy2.CIR is represented by a black line, Daudi by a red line, and HDLM-2 by a blue line. This demonstrates the performance stability and classification effectiveness of the classification model across different cell types.

[0070] Figure 5 This is a confusion matrix for classifying different cell types (HMy2.CIR, Daudi, HDLM-2) using a Support Vector Machine (SVM) model in a five-fold cross-validation process for a lymphoma cell classification system. Each subplot (A to E) shows the classification results at different folds. Rows in each confusion matrix represent the actual class, and columns represent the predicted class. Each number in the matrix represents the classification result for the corresponding class, where diagonal elements represent the number of correctly classified samples, and off-diagonal elements represent the number of misclassified samples.

[0071] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0072] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, 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 the present invention.

Claims

1. A lymphoma cell classification system, characterized in that, include: Injection pump, optical scattering imaging subsystem, electrochemical detection subsystem, and data analysis subsystem; The syringe pump and the data analysis subsystem are both connected to the optical scattering imaging subsystem and the electrochemical detection subsystem. The syringe pump is used to introduce the sample to be tested into the optical scattering imaging subsystem and the electrochemical detection subsystem. The optical scattering imaging subsystem is used to acquire the feature image data of the sample to be tested. The electrochemical detection subsystem is used to acquire the electrochemical signal of the sample to be tested. The data analysis subsystem is used to use machine learning algorithms to perform data fusion and classification on the feature image data and the electrochemical signal to obtain a classification result.

2. The lymphoma cell classification system according to claim 1, characterized in that, The optical scattering imaging subsystem includes: The laser, neutral density filter, first objective lens, fiber optic coupling module, optical excitation cell, second objective lens, and CMOS sensor are connected in sequence. The optical excitation cell is connected to the injection pump, and the CMOS sensor is connected to the data analysis subsystem; The laser is used to emit laser light, the neutral density filter is used to attenuate and adjust the power of the laser light, the first objective lens is used to focus the adjusted laser light, the fiber optic coupling module is used to transmit the focused laser light to the optical excitation cell using an optical fiber, the optical excitation cell is used to store the sample to be tested and receive the focused laser light to excite cells and generate scattered light, the second objective lens is used to acquire the scattered light and transmit it to the CMOS sensor, the CMOS sensor is used to perform imaging based on the scattered light, obtain feature image data and transmit it to the data analysis subsystem.

3. The lymphoma cell classification system according to claim 2, characterized in that, The wavelength of the laser is 532nm and the power of the laser is 50mW.

4. A lymphoma cell classification system according to claim 2, characterized in that, The optical excitation cell includes: Bottom glass substrate, top glass sheet, and two spacers; The two gaskets are located at the two ends of the bottom glass substrate and the top glass interlayer, respectively, to form a micro excitation cell. The micro excitation cell has a size of 24mm × 10mm and a thickness of 0.15mm.

5. A lymphoma cell classification system according to claim 2, characterized in that, The numerical aperture of the second objective lens is 0.

25.

6. A lymphoma cell classification system according to claim 2, characterized in that, The electrochemical detection subsystem includes: Three-electrode module, electrochemical active reaction cell and electrochemical workstation; The electrochemical active reaction cell is connected to the injection pump, and the electrochemical workstation is connected to the data analysis subsystem; The three-electrode module is used to perform electrochemical detection on the sample to be tested in the electrochemically active reaction cell to obtain an electrochemical signal. The electrochemical workstation is used to receive the electrochemical signal and transmit it to the data analysis subsystem.

7. A lymphoma cell classification system according to claim 6, characterized in that, The three-electrode module includes: Working electrode, counter electrode, and reference electrode.

Images