A method, device and system for dynamic monitoring of living cells

Abstract

The application discloses a kind of live cell dynamic monitoring method, comprising the following steps: obtaining the cell scanning picture group that live cell grown in culture vessel is photographed under specified condition, and the picture is preprocessed;Cell scanning picture group after pre-processing is input into trained cell identification model, and output cell growth state chart group;Cell growth state chart group is input into trained survival rate calculation model, and the survival rate of cell in each cell growth state chart is output;The cell survival rate numerical value obtained is drawn into cell survival rate-time curve chart;The cell survival rate-time curve chart generated is combined with nonlinear regression statistical method, and the half inhibitory concentration value of the efficacy of specified parameter calculation is selected.The growth state of cell under specified condition is monitored, and the survival rate of cell and the half inhibitory concentration value of the efficacy are calculated based on these data;It can significantly improve the efficiency and accuracy in the field of drug research and development, drug screening, treatment scheme effect, etc.

Description

Technical Field

[0001] This invention belongs to the field of cell detection technology, and in particular relates to a method, device and system for dynamic monitoring of live cells. Background Technology

[0002] The latest global cancer data from 2021 indicates that approximately 90% of cancer incidence is caused by solid tumors. Treatment for solid tumors generally involves surgery combined with postoperative chemotherapy (or radiotherapy). Currently, the techniques for sensitivity testing of treatment drugs after surgery are limited. Clinical testing does not utilize relevant in vitro diagnostic (IVD) products for chemotherapy drug sensitivity testing targeting the patient's own cells. The inability to obtain drug sensitivity test results immediately is a major obstacle to personalized and precision medicine. Summary of the Invention

[0003] The purpose of this invention is to address the problems existing in the prior art by providing a method, device, and system for dynamic monitoring of live cells. By continuously and visually monitoring the growth status of cells under the action of drugs, and calculating the cell survival rate and half-inhibitory concentration of various drugs at specific time periods, the effects of drug regimens on target cells can be quickly compared, providing data support for researchers to conduct subsequent studies and assisting in precise clinical treatment.

[0004] On one hand, the present invention provides a method for dynamic monitoring of live cells, comprising the following steps:

[0005] Acquire a set of cell scan images of live cells growing in a culture vessel under specified conditions, and preprocess the images;

[0006] The preprocessed cell scan images are input into the trained cell recognition model, which outputs a set of cell growth status images.

[0007] Input the cell growth status map set into the trained survival rate calculation model, and output the cell survival rate of each cell growth status map;

[0008] The obtained cell viability values ​​were plotted as a cell viability-time curve.

[0009] The generated cell survival-time curve is combined with a nonlinear regression statistical method, and the half-inhibitory concentration of the drug effect is calculated by selecting specified parameters.

[0010] The above-mentioned technical solutions, through cell identification and survival rate calculation models, can automatically and accurately calculate cell survival rate and drug efficacy, reduce human error, improve research efficiency, monitor cell growth status under specified conditions, and calculate cell survival rate and half-inhibitory concentration (WIC) values ​​of drug efficacy based on these data. This can significantly improve the efficiency and accuracy of drug development, cell biology research, and other fields, and has broad application prospects. For example, if the collected cells are primary cells derived from autologous surgery of cancer patients, they can represent individual genetic and pathological information, which is of great significance for the pre-screening of precision oncology treatment plans. The above methods can exclude ineffective drugs for newly diagnosed cancer patients with an accuracy of over 95%, avoiding economic waste and toxic side effects caused by ineffective treatment. Furthermore, it can help find usable drugs or treatment plans for patients with relapsed, drug-resistant, metastatic, or refractory cancers.

[0011] Furthermore, the specified conditions include drug type, drug concentration, cell type, start time of filming, and end time of filming. The explicitness of these conditions helps to ensure the reproducibility of the experiment and the reliability of the results, while also providing researchers with more flexibility in experimental design.

[0012] Furthermore, the training of the cell recognition model includes:

[0013] Construct a sample information set, including cell images and images of cell growth status; construct a convolutional neural network model, with cell images as input and cell growth status images as output;

[0014] The convolutional neural network model is trained using the constructed sample information set, outputting the trained cell recognition model. This step is fundamental to subsequent cell viability calculations, and its accuracy directly affects the reliability of the final result.

[0015] Furthermore, the training of the survival rate calculation model includes:

[0016] Construct a sample dataset of cell growth status diagrams and corresponding cell viability under different experimental conditions;

[0017] Annotate the cell growth state diagrams in the sample dataset;

[0018] Construct a convolutional neural network model whose input is an annotated image and whose output is the survival rate of cells in the image;

[0019] A convolutional neural network model is trained using a loss function, outputting a trained survival rate calculation model. This process ensures that the survival rate calculation model can accurately calculate cell survival rates, providing strong support for drug efficacy evaluation.

[0020] Furthermore, the cell growth status of each image is labeled, including marking the living or dead cells in each image. This labeling makes it easier for the convolutional neural network model to identify living or dead cells and thus calculate the cell survival rate of the image.

[0021] On the one hand, a live cell dynamic monitoring device is provided, comprising: a first main module, used to acquire a group of cell scan images of live cells growing in a culture container under specified conditions, and to preprocess the images;

[0022] The second main module is used to input the preprocessed cell scan image set into the trained cell recognition model and output the cell growth state image set.

[0023] The third main module is used to input the cell growth status map group into the trained survival rate calculation model and output the cell survival rate of each cell growth status map.

[0024] The fourth main module is used to plot the obtained cell viability values ​​as a cell viability-time curve.

[0025] The fifth main module is used to combine the generated cell survival rate-time curve with nonlinear regression statistical methods and select specified parameters to calculate the half-inhibitory concentration of the drug effect.

[0026] On the one hand, the present invention provides a live cell dynamic monitoring system, including a culture medium module, an imaging module, and a main control module;

[0027] The culture carrier module is configured to carry cell culture carrier containers;

[0028] The imaging module is configured to acquire images of live cells growing in a culture container;

[0029] The main control module is configured to implement the red blood cell dynamic monitoring method.

[0030] Furthermore, the imaging module includes an LED cold light source, an objective lens module, and a camera module, with the objective lens module located between the object being observed and the camera;

[0031] The LED cold light source includes, from top to bottom, an LED light source, a light-collecting lens group, a color filter, a field lens group, an aperture grating, a field grating, and a color filter.

[0032] Through precise power design and optical path control, the LED cold light source ensures that only the imaging area and its vicinity receive sufficient illumination, while other non-imaging areas remain almost unaffected. This ability to precisely control the illumination range not only improves the clarity and quality of the image but also significantly reduces phototoxic effects on non-imaging areas. This structural design helps provide stable and uniform illumination conditions, reduces light interference with cell growth, and improves the accuracy of monitoring results. It not only provides sufficient illumination to meet imaging requirements but also effectively reduces phototoxic effects on non-imaging areas, protecting the safety of the observed sensitive biological samples.

[0033] Furthermore, it also includes a communication module, a storage module, and a display module, which are used for data transmission, data storage, and result display, respectively.

[0034] Compared with existing technologies, the beneficial effects of this invention are: 1. Monitoring cell growth status under specified conditions and calculating cell survival rate and half-inhibitory concentration (WIC) of drug efficacy based on these data. This technical solution can significantly improve the efficiency and accuracy of drug development, cell biology research, and other fields, and has broad application prospects; 2. The collected cells are all derived from primary cells from the cancer patients themselves, which can represent individual genetic and pathological information, and are of great significance for precision oncology; 3. The above method can exclude ineffective drugs for newly diagnosed cancer patients with an accuracy of over 95%, avoiding economic waste and toxic side effects caused by ineffective treatment; 4. It can help find available drugs or treatments for patients with relapsed, drug-resistant, metastatic, or refractory cancers. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of a live cell dynamic monitoring method according to an embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram of a live cell dynamic monitoring system according to an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram showing the before and after comparison of cell image preprocessing under a live cell dynamic monitoring system in an embodiment of the present invention;

[0038] Figure 4 This is a schematic diagram of various cancer cells selected in a live cell dynamic monitoring method according to an embodiment of the present invention;

[0039] Figure 5 This is a schematic diagram of growth curves for different cell areas in an embodiment of the present invention;

[0040] Figure 6 This is a schematic diagram showing the state of liver cancer cells before drug administration in an experimental example of the present invention;

[0041] Figure 7This is a schematic diagram showing the state of liver cancer cells at 24 hours, 48 ​​hours, and 72 hours after the addition of 50 μM drug in the experimental example of this invention.

[0042] Figure 8 This is a schematic diagram showing the state of liver cancer cells at 24 hours, 48 ​​hours and 72 hours after the addition of 10 μM drug in the experimental example of the present invention.

[0043] Figure 9 This is a schematic diagram showing the state of liver cancer cells at 24 hours, 48 ​​hours and 72 hours after the addition of 2 μM drug in the experimental example of the present invention.

[0044] Figure 10 This is a schematic diagram showing the state of liver cancer cells 24 hours, 48 ​​hours, and 72 hours after the addition of 0.4 μM drug in the experimental examples of this invention;

[0045] Figure 11 This is a schematic diagram showing the state of liver cancer cells 24 hours, 48 ​​hours, and 72 hours after the addition of 0.08 μM drug in the experimental examples of this invention.

[0046] Figure 12 This is a schematic diagram showing the state of liver cancer cells 24 hours, 48 ​​hours and 72 hours after the addition of 0.016 μM drug in the experimental examples of the present invention;

[0047] Figure 13 This is a schematic diagram showing the positive status of the liver cancer cell control group at 24 hours, 48 ​​hours, and 72 hours in the experimental examples of this invention.

[0048] Figure 14 This is a schematic diagram showing the negative status of the liver cancer cell control group at 24, 48, and 72 hours in the experimental examples of this invention.

[0049] Figure 15 This is a schematic diagram showing the state of liver cancer cells at 24 hours, 48 ​​hours, and 72 hours after no drug was added in the experimental example of this invention.

[0050] Figure 16 This is a schematic diagram of the analysis results of liver cancer cells in the experimental examples of this invention;

[0051] Figure 17 This is a schematic diagram showing the state of prostate cancer cells before drug administration in an experimental example of the present invention;

[0052] Figure 18 This is a schematic diagram showing the state of prostate cancer cells 24 hours, 48 ​​hours and 72 hours after the addition of 50 μM drug in the experimental example of the present invention.

[0053] Figure 19This is a schematic diagram showing the state of prostate cancer cells at 24 hours, 48 ​​hours, and 72 hours after the addition of 10 μM drug in an experimental example of the present invention.

[0054] Figure 20 This is a schematic diagram showing the state of prostate cancer cells at 24 hours, 48 ​​hours, and 72 hours after the addition of 2 μM drug in the experimental example of this invention.

[0055] Figure 21 This is a schematic diagram showing the state of prostate cancer cells 24 hours, 48 ​​hours, and 72 hours after the addition of 0.4 μM drug in the experimental examples of this invention;

[0056] Figure 22 This is a schematic diagram showing the state of prostate cancer cells 24 hours, 48 ​​hours, and 72 hours after the addition of 0.08 μM drug in the experimental examples of this invention.

[0057] Figure 23 This is a schematic diagram showing the state of prostate cancer cells 24 hours, 48 ​​hours, and 72 hours after the addition of 0.016 μM drug in the experimental examples of this invention.

[0058] Figure 24 This is a schematic diagram showing the positive status of the prostate cancer cell control group at 24 hours, 48 ​​hours, and 72 hours in the experimental examples of this invention.

[0059] Figure 25 This is a schematic diagram showing the negative status of the prostate cancer cell control group at 24, 48, and 72 hours in the experimental examples of this invention.

[0060] Figure 26 This is a schematic diagram showing the state of prostate cancer cells at 24 hours, 48 ​​hours, and 72 hours after no drug was added in the experimental examples of this invention.

[0061] Figure 27 This is a schematic diagram of the analysis results of prostate cancer cells in the experimental examples of this invention;

[0062] Figure 28 This is a schematic diagram of the structure of a live cell dynamic monitoring device according to an embodiment of the present invention;

[0063] Figure 29 This is a schematic diagram of the LED cold light source structure in a live cell dynamic monitoring device according to an embodiment of the present invention.

[0064] In the diagram: 1. Outer shell; 2. LED cold light source; 3. Cell stage; 4. Objective lens module; 5. Camera module; 6. Main control module. Detailed Implementation

[0065] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] In the description of this invention, it should be noted that the terms "middle", "upper", "lower", "left", "right", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0067] like Figure 1 , Figure 3 , Figure 4 , Figure 5 As shown, in one aspect, the present invention provides a method for dynamic monitoring of live cells, comprising the following steps:

[0068] Acquire a set of cell scan images of live cells growing in a culture vessel under specified conditions, and preprocess the images;

[0069] The preprocessed cell scan images are input into the trained cell recognition model, which outputs a set of cell growth status images.

[0070] Input the cell growth status map set into the trained survival rate calculation model, and output the cell survival rate of each cell growth status map;

[0071] The obtained cell viability values ​​were plotted as a cell viability-time curve.

[0072] The generated cell survival-time curve is combined with a nonlinear regression statistical method, and the half-inhibitory concentration of the drug effect is calculated by selecting specified parameters.

[0073] The above technical solutions, through cell recognition models and survival rate calculation models, can automatically and accurately calculate cell survival rate and drug efficacy, reduce human error, and improve research efficiency.

[0074] In this embodiment, the half-inhibitory concentration (WIC) of the drug effect is calculated using a nonlinear regression statistical method and implemented with existing software.

[0075] Specifically: After obtaining the cell survival rate-time curve, import the graph directly into Graphpad Prism software. Then, in the Nonlinear regression (Curve fit) function under the analyzes section of the software, select the Dose-response-Inhibition parameter to calculate the half-inhibitory concentration (IC50 value) of the drug.

[0076] The detection results of this invention output the IC50 value of the drug efficacy for the corresponding cells and compare it with the reference IC50 value in the literature. It automatically judges the strength of the drug efficacy, especially the experimental results of drugs that are obviously insensitive, and provides data support and reference standards for doctors' clinical drug use.

[0077] Preprocessing operations include denoising, contrast enhancement, and normalization of images. These operations help improve image quality, providing a more favorable data foundation for subsequent identification and thus improving the overall accuracy of monitoring.

[0078] Specifying conditions includes drug type, drug concentration, cell type, start time of filming, and end time of filming. The clarity of these conditions helps to ensure the reproducibility of the experiment and the reliability of the results, while also providing researchers with more flexibility in experimental design.

[0079] Training the cell recognition model includes:

[0080] A sample information set is constructed, including ordinary cell image data; a convolutional neural network model is constructed, specifically, in this embodiment, the Mask R-CNN model is used. The input of Mask R-CNN is a clear cell image, and the output is an image of cell growth status.

[0081] The Mask R-CNN model is trained using the constructed sample information set, and the trained cell recognition model is output.

[0082] By constructing a Mask R-CNN model and training it using a sample information set, a cell recognition model capable of outputting cell image data was obtained. This step is fundamental to subsequent cell viability calculations, and its accuracy directly affects the reliability of the final result.

[0083] The Mask R-CNN model is an existing network model. The algorithm steps of the Mask R-CNN model are as follows:

[0084] First, input an image you want to process, then perform the corresponding preprocessing operations, or the preprocessed image;

[0085] Then, it is input into a pre-trained neural network (such as ResNeXt) to obtain the corresponding feature map;

[0086] Next, a predetermined number of ROIs are set for each point in this feature map, thereby obtaining multiple candidate ROIs;

[0087] Next, these candidate ROIs are fed into the RPN network for binary classification (foreground or background) and BB regression to filter out some candidate ROIs.

[0088] Next, perform the ROIAlign operation on these remaining ROIs (that is, first match the pixels of the original image with those of the feature map, and then match the feature map with the fixed features).

[0089] Finally, these ROIs are classified (N-class classification), BB regression is performed, and MASK is generated (FCN operation is performed in each ROI).

[0090] The Mask R-CNN model consists of three main modules: Faster R-CNN, ROIAlign, and FCN.

[0091] Faster R-CNN (Region Convolutional Neural Network) is a widely used deep learning model for object detection tasks. It combines the advantages of both RPN (Region Proposal Network) and Fast R-CNN. The following is the main structure and working principle of Faster R-CNN:

[0092] Base network: Typically, a pre-trained convolutional neural network (such as VGG, ResNet, etc.) is used to extract image features.

[0093] Region Proposal Network (RPN): This is a small, parallel-running convolutional network that generates a set of candidate object regions (called "RoIs") from an input image. The RPN predicts whether each candidate region contains an object and its category probability.

[0094] RoI Pooling: For each candidate region, features are sampled from the original feature map through a fixed-size window of the RoI pooling layer. This step ensures that all RoIs have the same size for further processing.

[0095] ROIAlign or RoIPooling: A replacement for earlier versions of RoIPooling, it handles the position information of bounding boxes more accurately and reduces accuracy loss.

[0096] Classification and Regression: The features of the RoI are passed to the fully connected layer to determine whether the region contains an object (binary classification problem) and to determine the precise location of the object (boundary coordinate regression).

[0097] Non-Maximum Suppression (NMS): In order to remove highly similar region proposals, the candidate region with the highest confidence is retained as the final result.

[0098] The key to Faster R-CNN lies in its end-to-end design, which can simultaneously complete the two steps of region proposal and object recognition, significantly improving the speed and accuracy of object detection.

[0099] Secondly, ROIAlign (Region of Interest Alignment) is a technique in Faster R-CNN. It is an improvement over the earlier RoIPooling and is mainly used to handle the region proposal (RoI, Regions of Interest) operation in object detection tasks in convolutional neural networks. The core idea of ​​ROIAlign is to perform pixel-level interpolation according to the bounding box of each RoI before performing feature pooling, so as to ensure that each pixel of the output feature map is a linear transformation of the corresponding real position on the original image.

[0100] Finally, the FCN algorithm is a classic semantic segmentation algorithm that can accurately segment objects in images. Its overall architecture, as shown in the figure above, is an end-to-end network. The main modules include convolution and deconvolution. First, convolution and pooling are performed on the image to continuously reduce the size of its feature map; then, deconvolution, or interpolation, is performed to continuously increase the feature map size; finally, each pixel value is classified. This achieves accurate segmentation of the input image.

[0101] Training the survival rate calculation model includes:

[0102] Construct a sample dataset of cell growth status diagrams and corresponding cell viability under different experimental conditions (such as cells under different drugs, different drug concentrations, different placement times, etc.);

[0103] Annotate the cell growth state diagrams in the sample dataset;

[0104] Construct a convolutional neural network model whose input is an annotated image and whose output is the survival rate of cells in the image;

[0105] A convolutional neural network model is trained using a loss function, outputting a trained survival rate calculation model. This process ensures that the survival rate calculation model can accurately calculate cell survival rates, providing strong support for drug efficacy evaluation.

[0106] The process of labeling each image includes identifying whether a cell is alive or dead. This labeling helps the convolutional neural network model recognize live or dead cells and calculate the cell survival rate for that image.

[0107] In this embodiment, the survival rate calculation model simultaneously identifies the number of surviving cells and the total number of cells in the image. Then, the survival rate calculation model substitutes the two parameters, the number of surviving cells and the total number of cells, into formula (1) to obtain the cell survival rate of the image.

[0108] Formula (1): Cell viability = (Number of surviving cells / Total number of cells) * 100%

[0109] Experimental Example 1: Using liver cancer cells as the original cells for drug administration and monitoring.

[0110] Culture system: 96-well flat-bottomed plates, liver cancer cell culture medium, seeding density 8 × 10⁶. 3 One hole / hole.

[0111] Experimental procedure: 24 hours after inoculation, the corresponding compound was added according to the experimental design, and the cells were observed for 72 hours.

[0112] The working concentrations of the drugs are shown in Table 1:

[0113] Table 1. Statistical Table of Liver Cancer Cell Monitoring

[0114] .

[0115] Cell images such as Figure 6-15 As shown:

[0116] Specifically, before adding the drug (to healthy cells) (Group 1), as follows: Figure 6 As shown; Test results: After drug administration (6 groups) as follows Figure 7-15 Determination of lethality:

[0117] The recommended therapeutic dose for (5-fluorouracil) patients with good hematopoietic function and nutritional status is 12 mg / kg intravenously daily, with a maximum daily dose of 800 mg. If no toxicity is observed after 4 days of injection, the dose should be reduced to 6 mg / kg every other day for a total of 4 doses. The literature recommends an experimental dose of 1 μM.

[0118] The test results are analyzed in Table 2:

[0119] Table 2. Statistical table of survival rate of liver cancer cells.

[0120] .

[0121] like Figure 17 As shown, the report output results are: half-inhibition concentration test value 0.7686μM, half-inhibition concentration reference value 0.8μM.

[0122] Experimental Example 2: Prostate cancer cells were used as the primary cells for drug administration and monitoring.

[0123] Culture system: 96-well flat-bottomed plates, prostate cancer cell culture medium, seeding density 5 × 10⁶. 3 One hole / hole.

[0124] Experimental procedure: 24 hours after inoculation, the corresponding compound was added according to the experimental design, and the cells were observed for 72 hours.

[0125] The working concentrations of the drugs are shown in Table 3:

[0126] Table 3. Statistical Table of Prostate Cancer Cell Monitoring

[0127] .

[0128] Images of prostate cancer cells, such as Figure 17-26 As shown:

[0129] Specifically, before adding the drug (to healthy cells) (Group 1), as follows: Figure 17 As shown; Test results: After drug administration (6 groups) as follows Figure 18-26 Determination of lethality.

[0130] Determination of lethality:

[0131] (Etoposide) Therapeutic dose according to the product information is 60-100 mg / m² daily. 2 (On the body surface), for 3-5 consecutive days, repeat every 3-4 weeks. The literature recommends an experimental dose of 1-100 μM.

[0132] The test results are analyzed in Table 4:

[0133] Table 4. Statistical table of prostate cancer cell survival rate

[0134] .

[0135] like Figure 27 As shown, the report output results are: half-inhibition concentration test value 4.351μM, IC50 reference value 3.56μM.

[0136] Compared to traditional tumor cell line cultures, which lack individual patient variability, the cells collected in this application are all primary cells derived from the cancer patients themselves, representing individual genetic and pathological information. This is of great significance for precision oncology. Furthermore, this method can exclude ineffective drugs for newly diagnosed cancer patients with an accuracy rate exceeding 95%, avoiding economic waste and toxic side effects from ineffective treatment. Secondly, it can help identify usable drugs or treatment plans for patients with relapsed, drug-resistant, metastatic, or refractory cancers. It also provides scientific evidence for off-label drug use, such as the multiple uses of targeted therapies, and offers high-throughput in vitro drug sensitivity testing for patients lacking guideline-approved effective treatments, including FDA-approved drug libraries, allowing for the screening of hundreds of drugs and treatment plans in about two weeks.

[0137] In addition, this application can utilize primary cells to establish pharmacogenomics databases for different tumors, providing support for the development of new drugs and target discovery for related cancers.

[0138] like Figure 28 As shown, based on the same technical concept as the above embodiments, a live cell dynamic monitoring device is provided, the first main module being used to acquire a group of cell scan images of live cells growing in a culture container under specified conditions, and to preprocess the images;

[0139] The second main module is used to input the preprocessed cell scan image set into the trained cell recognition model and output the cell growth state image set.

[0140] The third main module is used to input the cell growth status map group into the trained survival rate calculation model and output the cell survival rate of each cell growth status map.

[0141] The fourth main module is used to plot the obtained cell viability values ​​as a cell viability-time curve.

[0142] The fifth main module is used to combine the generated cell survival rate-time curve with nonlinear regression statistical methods and select specified parameters to calculate the half-inhibitory concentration of the drug effect.

[0143] Based on the same technical concept as the above embodiments, a live cell dynamic monitoring system is provided, comprising a material carrier module, an imaging module, and a main control module;

[0144] The culture carrier module is configured to carry cell culture carrier containers;

[0145] The imaging module is configured to acquire images of live cells growing in a culture container;

[0146] The main control module is configured to scan the cell image group captured by the imaging unit, and sequentially identify the cell image group, calculate the cell viability, generate cell viability and time curves, and calculate the half-maximum inhibitory concentration (WMC) value of the corresponding drug.

[0147] The loading module is located at the center of the top of the outer shell 1. The loading module includes a cell loading stage 2 and live cells growing in a culture container.

[0148] like Figure 28 As shown, the imaging module includes an LED cold light source 2, an objective lens module 4, and a camera module 5;

[0149] The LED cold light source 2 is positioned above the cell stage 3, while the objective lens module 4 and the camera module 5 are positioned below the cell stage 3 from top to bottom.

[0150] like Figure 29 As shown, the LED cold light source includes, from top to bottom, an LED light source, a light-collecting lens group, a color filter, a field lens group, an aperture grating, a field grating, and a color filter.

[0151] Through precise power design and optical path control, the LED cold light source 2 ensures that only the imaging area and its vicinity receive sufficient illumination, while other non-imaging areas remain almost unaffected. This ability to precisely control the illumination range not only improves the clarity and quality of the image but also significantly reduces the phototoxic effects on non-imaging areas. This structural design helps provide stable and uniform illumination conditions, reduces light interference with cell growth, and improves the accuracy of monitoring results. It not only provides sufficient illumination to meet imaging requirements but also effectively reduces the phototoxic effects on non-imaging areas, protecting the safety of the observed sensitive biological samples.

[0152] It is important to note that in continuous observation of live cells, the culture area is much larger than the imaging area of ​​a single field of view. Traditional imaging sampling methods utilize multi-image stitching to capture the entire culture area. While this technology is mature, it suffers from excessive data throughput, high equipment requirements, and excessive redundant data. This not only unnecessarily interferes with data interpretation but also wastes data processing and storage resources, adding unnecessary burdens to clinical treatment and research, hindering technology implementation and widespread adoption. Therefore, in this embodiment, the objective lens module and camera module are integrated and can be moved along the x and y axes of a single plane via a drive structure such as an electric slide rail. During imaging sampling, a single-well multi-field sampling method is adopted, referencing the classic hemocytometer counting method. Its advantages are as follows:

[0153] (1) Comprehensiveness: By sampling the entire culture area from multiple fields of view, the comprehensiveness and representativeness of the data can be ensured, and the bias caused by local sampling can be reduced.

[0154] (2) Accuracy: Multi-field sampling can capture more information about the state and distribution of cells, thereby improving the accuracy of counting. At the same time, by sampling multiple times and calculating the average value, random errors can be further reduced.

[0155] (3) Reliability: This method avoids the randomness that may exist in single field sampling, making the counting results more reliable and stable.

[0156] Single-well multi-field sampling collects data from the entire culture area, effectively avoiding random field-of-view errors.

[0157] In this embodiment, the live cell dynamic monitoring device also includes a communication module, a storage module, and a display module, used for data transmission, data storage, and result display, respectively. The main control module interacts with both the storage and display units to achieve data storage and result display. All data is automatically uploaded to the cloud periodically via the communication module, reducing hardware storage pressure and enabling the integration and sharing of data from different sources for convenient viewing and analysis by users. Data export and report generation functions are provided, allowing users to share results with clinicians or other researchers.

[0158] The aforementioned equipment, combined with the monitoring methods described above, fully supports high-throughput chemotherapy drug sensitivity testing technology, enabling the selection of precise medication regimens for clinical oncology patients. Fresh tumor samples, such as intraoperative tissue, pleural and peritoneal fluid, puncture samples, and biopsy tissue obtained during clinical diagnosis and treatment, are rapidly expanded and enriched using novel conditional reprogrammed cell (CRC) technology within 72 hours. While preserving the genetic, pathological, and other biological characteristics of the primary cells and original tissues, over 100 drugs or combination regimens are rapidly screened within 1-2 weeks. This helps patients exclude drugs that have become resistant or ineffective (with a concordance rate of over 90%), providing medication references for patients with advanced-stage, drug-resistant, or relapsed cancer, and those lacking guideline-based medication recommendations. This allows for the development of precise treatment plans, further reducing the incidence of ineffective treatment and improving the success rate of medication administration in clinical oncology patients.

[0159] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for dynamic monitoring of live cells, characterized in that: Drug sensitivity testing for primary tumor cells includes the following steps: Acquire a set of cell scan images of live cells growing in a culture vessel under specified conditions, and preprocess the images; The preprocessed cell scan images are input into the trained cell recognition model, which outputs a set of cell growth status images. The cell growth status images are input into the trained survival rate calculation model, which outputs the cell survival rate of each cell growth status image. The survival rate calculation model simultaneously identifies the number of surviving cells and the total number of cells in the image, and calculates the cell survival rate of the image according to the formula: cell survival rate = number of surviving cells / total number of cells * 100%. The obtained cell viability values ​​were plotted as a cell viability-time curve. The generated cell survival-time curve is combined with a nonlinear regression statistical method, and the half-inhibitory concentration of the drug effect is calculated by selecting specified parameters.

2. The method for dynamic monitoring of live cells according to claim 1, characterized in that: The specified conditions include drug type, drug concentration, cell type, start time of shooting, and end time of shooting.

3. The method for dynamic monitoring of live cells according to claim 1, characterized in that: The training of the cell recognition model includes: Construct a sample information set, including cell images and images of cell growth status; construct a convolutional neural network model, with cell images as input and cell growth status images as output; The convolutional neural network model is trained using the constructed sample information set, and the trained cell recognition model is output.

4. The method for dynamic monitoring of live cells according to claim 1, characterized in that: The training of the survival rate calculation model includes: Construct a sample dataset of cell growth status diagrams and corresponding cell viability under different experimental conditions; Annotate the cell growth state diagrams in the sample dataset; Construct a convolutional neural network model whose input is an annotated image and whose output is the survival rate of cells in the image; The convolutional neural network model is trained using a loss function, and the survival rate calculation model after training is output.

5. The method for dynamic monitoring of live cells according to claim 4, characterized in that: Each cell growth status image is labeled, including marking the living or dead cells in each image.

6. A live cell dynamic monitoring device, characterized in that: Drug sensitivity testing for primary tumor cells includes: The first main module is used to acquire a set of cell scan images of live cells growing in a culture container under specified conditions, and to preprocess the images. The second main module is used to input the preprocessed cell scan image set into the trained cell recognition model and output the cell growth state image set. The third main module is used to input the cell growth status image group into the trained survival rate calculation model and output the cell survival rate of each cell growth status image. The survival rate calculation model simultaneously identifies the number of surviving cells and the total number of cells in the image, and calculates the cell survival rate of the image according to the formula: cell survival rate = number of surviving cells / total number of cells * 100%. The fourth main module is used to plot the obtained cell viability values ​​as a cell viability-time curve. The fifth main module is used to combine the generated cell survival rate-time curve with nonlinear regression statistical methods and select specified parameters to calculate the half-inhibitory concentration of the drug effect.

7. A live cell dynamic monitoring system, characterized in that: It includes a culture medium module, an imaging module, and a main control module; The culture carrier module is configured to carry cell culture carrier containers; The imaging module is configured to acquire images of live cells growing in a culture container; The main control module is configured to implement the method described in any one of claims 1 to 5.

8. A live cell dynamic monitoring system according to claim 7, characterized in that: The imaging module includes an LED cold light source, an objective lens module, and a camera module, with the objective lens module located between the object being observed and the camera; The LED cold light source includes, from top to bottom, an LED light source, a light-collecting lens group, a color filter, a field lens group, an aperture grating, a field grating, and a color filter.

9. A live cell dynamic monitoring system according to claim 7, characterized in that: It also includes a communication module, a storage module, and a display module, which are used for data transmission, data storage, and result display, respectively.

Images