Tumor therapeutic drug screening method and system

Abstract

The invention belongs to the technical field of drug screening, and discloses a tumor therapeutic drug screening method and system.The tumor therapeutic drug screening method comprises the steps that an in-vivo tissue sample of a tumor patient is obtained, synchronous organoid culture is conducted, and an in-vitro organoid culture sample is obtained; performing general pathological evaluation and molecular pathological evaluation on the in-vivo tissue sample to obtain a plurality of basic evaluation results; performing an dry experiment on the in-vitro organoid culture sample by adopting a plurality of target treatment drugs, wherein the target treatment drugs are obtained by primarily screening the in-vivo tissue sample; performing general pathological evaluation, molecular pathological evaluation and in-vitro living cell pathological evaluation on the in-vitro organoid sample in an dry experiment process to obtain a plurality of experiment evaluation results; and analyzing the experimental evaluation result on the basis of the basic evaluation result to obtain a tumor therapeutic drug screening result. And the reliability of tumor therapeutic drug screening results can be improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of drug screening, and particularly relates to a tumor therapeutic drug screening method and system. BACKGROUND

[0002] The treatment of tumors is much more difficult than that of common diseases, and the core problem lies in the complexity and heterogeneity of malignant tumors. Even if the pathological diagnosis is lung adenocarcinoma, the gene mutation spectrum of the patient may still be significantly different: about 30% carries EGFR mutation, 10% has ALK fusion, and part of the patients belong to KRAS mutation or driver gene mutation subtype. This heterogeneity directly leads to a huge difference in treatment effect: the objective remission rate of patients carrying EGFR sensitive mutation using gefitinib can reach 70%, while the remission rate of patients without mutation is less than 10%. Similarly, in the treatment of breast cancer, the response rate of HER2 positive patients to trastuzumab is about 50%, but half of the patients still have primary drug resistance due to tumor heterogeneity.

[0003] At present, drug screening has been carried out on tumor patients before treatment by using organoid technology. The organoid is a three-dimensional structure formed by tumor cells in vitro culture, which can highly simulate the histological characteristics and microenvironment of in vivo tumor, for example, the organoid of colorectal cancer can reproduce the glandular structure and gene mutation mode of the primary tumor, and the organoid of pancreatic cancer can retain the interstitial fibrosis characteristics of the tumor. However, the evaluation system of the effect in the process of drug screening has significant defects: the current effect evaluation of tumor organoids after drug treatment mainly depends on the subjective judgment of pathologists on the pathological morphological changes of tumor cells. Taking breast cancer organoids as an example, after treatment with paclitaxel, the doctor needs to observe the proportion of apoptosis, the degree of tissue structure destruction and other indicators through a microscope, but different doctors may have a deviation of 20%-30% in the definition of "moderate apoptosis". In the screening of chemotherapy drugs for colorectal cancer organoids, there was a case that the consistency of recommended drugs was only 58% after the same batch of samples were evaluated by 3 pathologists. Moreover, the evaluation of organoids is often independent of the pathological data of each case of the scheme, which is disconnected with the direct treatment data in clinic, and the tumor patient sample in vivo and the sample after in vitro organoid culture lack correlation, and it is difficult to achieve consistent treatment effect in vivo.

[0004] Therefore, the reliability of the screening result needs to be improved. SUMMARY

[0005] The purpose of the present application is to provide a tumor therapeutic drug screening method and system for improving the reliability of tumor therapeutic drug screening results.

[0006] The first aspect of the present application discloses a tumor therapeutic drug screening method, comprising:

[0007] Obtain in vivo tissue samples from cancer patients and simultaneously culture organoids to obtain in vitro organoid culture samples;

[0008] The in vivo tissue samples were subjected to general pathological and molecular pathological evaluations to obtain several basic evaluation results.

[0009] An interventional experiment was conducted on the in vitro organoid culture samples using several targeted therapeutic drugs, wherein the targeted therapeutic drugs were initially screened from the in vivo tissue samples;

[0010] During the interventional experiments, the in vitro organoid samples were subjected to general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation to obtain several experimental evaluation results.

[0011] Based on the aforementioned fundamental evaluation results, the experimental evaluation results are analyzed to obtain the screening results for tumor therapeutic drugs.

[0012] In some implementations, after obtaining in vivo tissue samples from cancer patients, molecular testing and drug screening are performed on the in vivo tissue samples to determine the target therapeutic drug.

[0013] In some embodiments, the experimental evaluation results include adaptive parameters corresponding to each of the basic evaluation results and several drug sensitivity evaluations. The step of analyzing the experimental evaluation results based on the basic evaluation results to obtain tumor therapeutic drug screening results includes:

[0014] Based on the adaptive parameters and the corresponding basic evaluation results, calculate the adaptive parameter evaluation corresponding to each adaptive parameter;

[0015] The results of the tumor therapeutic drug screening were obtained based on all the aforementioned adaptation parameters and all the aforementioned drug sensitivity evaluations.

[0016] In some implementations, the adaptive parameter evaluation corresponding to each adaptive parameter is calculated based on the adaptive parameters and the corresponding basic evaluation results, including:

[0017] Calculate the difference between the adaptive parameter and the corresponding basic evaluation result, and divide the calculation result by the corresponding basic evaluation result to obtain the adaptive parameter evaluation.

[0018] In some embodiments, during the interventional experiment, the in vitro organoid samples undergo general pathological evaluation, molecular pathological evaluation, and in vitro live-cell pathological evaluation to obtain several experimental evaluation results, including:

[0019] During the intervention experiment, photos were taken at different time points to obtain several experimental images;

[0020] Based on general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation, a deep learning model was used to analyze the experimental images to obtain the experimental evaluation results.

[0021] In some embodiments, the experimental evaluation results include: tumor cell nucleus size, tumor cell nucleus uniformity, tumor cell nucleus near-roundness, tumor cell density, tumor cell mitotic figures, tumor cell necrosis rate, tumor cell Ki67 index, and tumor cell HER2 index.

[0022] In some embodiments, when performing interventional experiments on the in vitro organoid culture samples using several targeted therapeutic agents, the method further includes:

[0023] Immune cells from cancer patients were extracted and separated, made into cell suspensions, and cultured and proliferated to obtain mixed immune cell suspensions from cancer patients.

[0024] Interventional experiments were conducted by co-culturing mixed immune cell suspensions from cancer patients with tumor organoids.

[0025] In some implementations, in vitro live-cell pathological evaluation is performed, including:

[0026] The growth and basic morphology of tumor cells in the control group and drug group undergoing the intervention experiment were observed at preset time points to determine the adaptability of live cells in vitro under various experimental conditions.

[0027] A second aspect of this invention discloses a tumor therapeutic drug screening system, comprising:

[0028] The basic evaluation results module is used to perform general pathological and molecular pathological evaluations on in vivo tissue samples from cancer patients to obtain basic evaluation results.

[0029] The experimental evaluation results module is used to perform general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation on in vitro organoid samples during interventional experiments, and obtain several experimental evaluation results.

[0030] The screening module is used to analyze the experimental evaluation results based on the basic evaluation results to obtain screening results for tumor therapeutic drugs.

[0031] In some implementations, the system further includes an image-taking module and a deep learning model analysis module. The image-taking module is used to take photos at different time points during the interventional experiment to obtain a number of experimental images. The deep learning model analysis module is used to analyze the experimental images using a deep learning model based on general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation to obtain the experimental evaluation results; and to perform general pathological evaluation and molecular pathological evaluation on the in vivo tissue samples to obtain basic evaluation results.

[0032] The beneficial effects of this invention lie in its multi-dimensional evaluation system, which performs general and molecular pathological evaluations on in vivo tissue samples, and general, molecular, and in vitro live-cell pathological evaluations on in vitro organoid samples. This system achieves a deep integration of morphological observation and molecular analysis, making tumor drug screening more efficient, objective, and reliable. Furthermore, by using the general and molecular pathological evaluations of tumor cells in the patient's body as a basis for evaluating the therapeutic effects of organoid-cultured tumor cells, the consistency and correlation between the evaluation conclusions of in vitro organoids and the subsequent in vivo treatment effects are strengthened, improving the reliability of tumor therapeutic drug screening results. Attached Figure Description

[0033] The accompanying drawings illustrate specific examples of the technical solutions described in this invention and, together with the detailed embodiments, form part of the specification, serving to explain the technical solutions, principles, and effects of this invention.

[0034] Unless otherwise specified or defined, the same reference numerals in different figures represent the same or similar technical features, and different reference numerals may be used to represent the same or similar technical features.

[0035] Figure 1 This is a flowchart of an embodiment of a tumor therapeutic drug screening method according to an embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram of the culture medium grid according to an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram of the intervention experiment results of an embodiment of the present invention;

[0038] Figure 4 This is a schematic diagram of the tumor therapeutic drug screening system according to an embodiment of the present invention. Detailed Implementation

[0039] Unless otherwise specified or defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. When combined with the technical solutions of the invention in a real-world scenario, all technical and scientific terms used herein may also have meanings corresponding to the purpose of achieving the technical solutions of the invention. The terms "first," "second," etc., used herein are merely for distinguishing names and do not represent a specific number or order. The term "and / or," as used herein, includes any and all combinations of one or more of the associated listed items.

[0040] It should be noted that when a component is considered "fixed" to another component, it can be directly fixed to the other component or there can be an intervening component; when a component is considered "connected" to another component, it can be directly connected to the other component or there can be an intervening component; when a component is considered "mounted" on another component, it can be directly mounted on the other component or there can be an intervening component; when a component is considered "placed" on another component, it can be directly placed on the other component or there can be an intervening component.

[0041] Unless otherwise specified or defined, the terms "described" or "the" as used herein refer to the technical features or technical content mentioned or described prior to the relevant section, which may be the same as or similar to the technical features or technical content mentioned herein. Furthermore, the terms "comprising" and "having," and any variations thereof, as used herein, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0042] To facilitate understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0043] To improve the reliability of screening results for cancer therapeutic drugs, this embodiment evaluates tumor organoids from the perspectives of pathological morphology and molecular pathology in cancer patients, constructing a multi-dimensional evaluation system to achieve a deep integration of "morphological observation" and "molecular analysis." Furthermore, based on the general pathological and molecular pathological evaluation of tumor cells in the patient's body, the efficacy of organoid-cultured tumor cell therapeutic drugs is evaluated and screened. This makes the consistency and correlation between the evaluation conclusions of in vitro organoids and the effects of subsequent in vivo treatment in patients stronger, providing a more reliable in vitro evaluation basis for precision cancer diagnosis and treatment.

[0044] like Figure 1As shown, this embodiment specifically includes the following steps:

[0045] Step S100: Obtain in vivo tissue samples from tumor patients and perform simultaneous organoid culture to obtain in vitro organoid culture samples;

[0046] Clinicians obtain fresh in vivo tissue samples from cancer patients using various methods, including endoscopic biopsy, in vitro needle biopsy, and surgical resection. These samples are then promptly fixed in formalin solution and labeled as sample A0001. The remaining tissue should be at least 2mm thick. 3 The above fresh tumor samples were immediately subjected to simultaneous organoid culture in cell preservation solution and labeled as sample B0001, i.e., in vitro organoid culture sample.

[0047] For sample A0001, conduct pathological diagnosis: determine the presence of tumor cells, the number of cells, histological type classification, and whether there are enough samples for pathological quality control such as gene testing, ensuring that the in vivo tissue samples can be used for pathological diagnosis and molecular testing, and ensuring the feasibility of subsequent experiments.

[0048] Then, molecular testing and drug screening are performed on in vivo tissue samples to determine target therapeutic drugs. Specifically, for cases that pass pathological quality control, corresponding molecular testing and drug screening are conducted. For example, for gastric cancer, it is recommended to perform immunohistochemistry for HER2 and Claudin18.2 to screen for anti-tumor drugs; for lung cancer, it is recommended to perform testing for genes such as EGFR and ALK to select effective targeted drugs. Finally, based on clinical guidelines, such as CSCO and NCCN guidelines, several classes of drugs that can be used to treat the disease are screened. Taking HER2-positive gastric cancer as an example, CSCO recommends the following treatment regimen: pembrolizumab (anti-PD-1) + trastuzumab (anti-HER2) + chemotherapy (such as XELOX or FLOT). The following medications may be effective for this patient: trastuzumab, HLX22 (recombinant humanized anti-HER2 monoclonal antibody), Hanquyou® (trastuzumab biosimilar), trastuzumab Deruxtecan (T-DXd), Disitamab Vedotin (RC48), Sintilimab, Pembrolizumab, Cadonilimab (AK104), Capecitabine, Oxaliplatin, Paclitaxel, and Irinotecan. Patients can choose from these medications to obtain a targeted treatment.

[0049] Step S200: Perform general pathological and molecular pathological evaluations on in vivo tissue samples to obtain several basic evaluation results;

[0050] The tumor cells in the pathological section of sample A0001 are referred to as "primary tissue cells". Sample A0001 is prepared into pathological sections, stained with hematoxylin and eosin (HE), and subjected to common immunohistochemical staining (CK, Ki67, HER2, Claudin 18.2, PD-L1, CD4, CD8, CD20, etc.). General pathological evaluation and molecular pathological evaluation are then performed. General pathological evaluation focuses on observing tissue cell morphology, while molecular pathological evaluation focuses on changes at the molecular level, such as genes and proteins. The evaluation results are collectively referred to as basic evaluation results, used as the basis for comparison with subsequent experimental results.

[0051] The general pathological evaluation includes: biopsy pathological specimen evaluation indicators, routine immunohistochemical evaluation indicators (I) and routine immunohistochemical evaluation indicators (II).

[0052] Among them, the evaluation indicators for biopsy pathological specimens include: tumor type (squamous cell carcinoma, adenocarcinoma, clear cell carcinoma, etc.), degree of differentiation (well differentiated, moderately differentiated, poorly differentiated, undifferentiated), mitotic index, average nuclear size, nuclear variability, nuclear-cytoplasmic ratio, and associated necrosis rate.

[0053] Routine immunohistochemical evaluation indicators (I) include: CK, HER2, Claudin18.2, PD-L1, CD4, CD8, CD20, etc.

[0054] Routine immunohistochemical evaluation indicators (II) include: cell proliferation activity—Ki-67, PCNA, etc.; stem cell characteristics—CD133, SOX2, Oct4, etc.; heterogeneity—CD44 / CD24, EpCAM, etc.; apoptosis—Cleaved caspase-3, Bax, Bcl-2, etc.; pyroptosis—GSDMD, NLRP3, etc.; necrosis—HMGB1, RIPK3, etc.

[0055] Molecular pathological evaluation involves detecting common gene mutations in relevant tumors using molecular detection techniques such as PCR or NGS. Examples include: lung cancer EGFR mutations (e.g., exon 19 deletion, L858R), ALK fusions (e.g., EML4-ALK), KRAS mutations, ROS1 fusions, BRAF mutations, etc.; breast cancer ER / PR, HER2 amplification, BRCA1 / 2 mutations, PIK3CA mutations, etc.; gastric cancer TP53 mutations, ARID1A mutations, CDH1 mutations, ERBB2 amplifications, etc.; colorectal cancer APC mutations, KRAS mutations, BRAF mutations, TP53 mutations, MSI; glioma IDH1 / 2 mutations, TERT promoter mutations, 1p / 19q co-deletion, EGFR amplification, TP53 mutations, etc.

[0056] Step S300: Conduct interventional experiments on in vitro organoid culture samples using several targeted therapeutic drugs;

[0057] The target therapeutic drug is obtained in step S100 by molecular testing and drug screening based on in vivo tissue samples. In this embodiment, the target therapeutic drugs are: trastuzumab, HLX22, Hanquyou®, detrastuzumab, vedicetuzumab, sintilimab, and pembrolizumab.

[0058] The specific process of an interventional experiment is as follows:

[0059] Eight organoid samples, from samples B00011 to B00018, were isolated from sample B0001 and used to form a blank control group and seven other treatment groups with different drugs. The drugs used in the treatment groups were, in order: trastuzumab, HLX22, Hanquyou®, detrastuzumab, vedicetuzumab, sintilimab, and pembrolizumab.

[0060] After in vitro tumor cell culture and expansion, sample B0001 was evenly distributed into a 4x8 culture medium. A separator was then placed over the medium. The corresponding target therapeutic drug was then added to the medium according to the column. For example... Figure 2 As shown, tumors were evenly distributed in each square of the culture medium and reacted with each column of different intervention drugs.

[0061] Currently, autoimmune cells play an important role in most patients, but they are not currently used for joint evaluation. Therefore, this embodiment also extracts and isolates immune cells from tumor patients, prepares cell suspensions, and culture and proliferates the immune cells to obtain a mixed immune cell suspension from tumor patients. This mixed immune cell suspension from tumor patients is then co-cultured with tumor organoids for interventional experiments to achieve joint evaluation.

[0062] Specifically, immune cells are extracted from areas of lymphatic richness in cancer patients, such as the tonsils in the oral cavity and superficial lymph nodes. This method is simple and easy to perform clinically, with minimal harm to the patient. After extracting the immune cells from the biopsy area, a cell suspension is prepared in vitro, and the immune cells are cultured and proliferated. The immune cells mainly include neutrophils, macrophages, dendritic cells, NK cells, eosinophils, basophils, mast cells, as well as adaptive T lymphocytes (cytotoxic, helper, and regulatory), B lymphocytes, plasma cells, etc. The suspension is then expanded in vitro to obtain a mixed immune cell suspension C0001 from the cancer patient.

[0063] Step S400: During the interventional experiment, the in vitro organoid samples are subjected to general pathological evaluation, molecular pathological evaluation and in vitro live cell pathological evaluation to obtain several experimental evaluation results;

[0064] During interventional experiments, after a certain period of time, the growth and basic morphology of tumor cells are observed according to the time of each row of data. General pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation are performed. The evaluation results are collectively referred to as experimental evaluation results.

[0065] Specifically: Evaluation is conducted in the form of time-critical nodes. On the corresponding days 0, 1, 7, and 14, tumor cells cultured in vitro with different drug interventions are co-cultured, fixed with fixatives such as formalin, and then pathological sections are prepared. Pathological evaluation is performed using techniques such as HE, IHC, and IF, or general pathological and molecular pathological evaluation is performed using techniques such as PCR and NGS. The specific content of general and molecular pathological evaluation can be referred to step S200, and will not be repeated here.

[0066] Under co-culture conditions, the growth and basic morphology of tumor cells were observed, and drug sensitivity was evaluated, such as... Figure 3 As shown, the following situations may occur:

[0067] First column: Blank group, serving as the control group, only tumor cells were added, without any other drugs. On the first day, the tumor cells grew slowly as they adapted to the new environment. They were observed concurrently for 14 days.

[0068] The second group: the drug group. After 14 days of observation following drug administration, the drug did not inhibit or kill tumor cells, and there was no significant difference compared with the control group.

[0069] The third group (drug group) showed that tumor cell growth was inhibited on day 7 after medication, and tumor cell apoptosis and death began on day 14. The drug's therapeutic effect on the tumor was slow to take effect.

[0070] Column 4: Drug group. On day 7 after medication, tumor cell growth was significantly inhibited, and necrosis occurred. On day 14, the tumor cells were basically completely controlled and eliminated. The drug produced a therapeutic effect on the tumor with a relatively rapid onset of action.

[0071] Fifth column: Drug group. On the 7th day after medication, the tumor cells were basically completely controlled and eliminated. The drug produced a therapeutic effect on the tumor and took effect the fastest.

[0072] Column 6: Drug group. On day 7 after drug administration, tumor cell growth was significantly inhibited, and subclonal tumor cell lines appeared. On day 14, the tumor cells screened for the drug, and the tumors developed drug resistance. Tumor cells with strong drug sensitivity were eliminated, while tumor cells with strong drug resistance proliferated actively.

[0073] Column 7: Drug group. On days 7 and 14 after medication, tumor cell growth was inhibited compared to the control group, but the inhibitory effect was limited. The drug produced a limited therapeutic effect on the tumor.

[0074] Column 8: Drug group. On the 7th and 14th days after medication, tumor cell growth was not inhibited. On the contrary, the tumor cell proliferation rate was faster compared with the blank group.

[0075] This embodiment also includes in vitro live-cell pathological evaluation of organoid samples: the growth and basic morphology of tumor cells in the control and drug groups undergoing interventional experiments were observed at preset time points to determine the adaptability of live cells in various experimental environments. Specifically, evaluation can be conducted at key time points or dynamically in real time; the density and particle size of tumor cells in the culture medium can be evaluated using light scattering, inverted microscope analysis systems, dynamic observation with image video microscopes, flow cytometry, etc.; and live-cell fluorescent staining reagents can be selected for tumor labeling, such as Hoechst 33342, SYTO 9, Calcein AM, LysoTracker, ER-Tracker, SiR-Actin, DiO, Fluo-4, CellEvent caspase-3 / 7, CY5-astragaloside A, pHrodo GreeniFL antibody labeling reagent, etc.

[0076] In this interventional experiment, a mixed immune cell suspension (C0001) from tumor patients was added for co-culture, and tumor cell growth was observed on days 0, 1, 7, and 14. The results were compared with the group without the C0001 suspension. It was found that in groups 7 and 8, tumor cells initially showed poor response to drug treatment, but the therapeutic effect was significantly inhibited after the addition of C0001. This indicates that this type of drug has a synergistic effect with the immune cells within the patient's tumor during treatment.

[0077] Current organoid evaluation methods are highly subjective, neglecting molecular-level responses and failing to align with clinical treatment needs. For example, a study at a top-tier hospital showed that among gastric cancer organoids treated with oxaliplatin, 17% of samples deemed "ineffective" by morphological evaluation showed abnormal expression of mismatch repair proteins in subsequent molecular testing. These patients may actually be sensitive to immunotherapy. Similarly, when treating melanoma organoids with BRAF inhibitors, some samples showed no significant morphological changes, but molecular testing revealed a significant decrease in MEK phosphorylation levels downstream of the BRAF pathway. This potential therapeutic signal is often missed by traditional evaluation methods. Therefore, this embodiment combines general pathological evaluation with molecular pathological evaluation, supplementing molecular evidence with molecular-level information, addressing the inability of morphology to distinguish between different organoids, and improving the reliability of screening results.

[0078] Furthermore, traditional evaluation methods lack quantitative standards. For example, in drug screening for liver cancer organoids, doctors typically use qualitative descriptions such as "partial necrosis" and "significant inhibition," which cannot provide precise numerical references like blood routine tests, significantly reducing the match between organoids and clinical treatment. This lag in the evaluation system hinders the full realization of the potential of organoid technology, often using it only as a research tool rather than a core basis for clinical decision-making. Therefore, in this embodiment, during the interventional experiment, photos are taken at different time points to obtain several experimental images. Then, based on general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation, a deep learning model is used to analyze the experimental images to obtain the experimental evaluation results. The deep learning model has been pre-trained using a training dataset. The specific structure of the deep learning model is not limited; existing convolutional neural network models can be used, or a vertical domain algorithm model can be built based on existing large-scale model algorithms constructed from tumor-related knowledge bases.

[0079] The experimental evaluation results included: tumor cell nucleus size, tumor cell nucleus uniformity, tumor cell nucleus near-roundness, tumor cell density, tumor cell mitotic figures, tumor cell necrosis rate, tumor cell Ki67 index, and tumor cell HER2 index.

[0080] The specific process is as follows: The prepared glass slide is placed on the scanner stage. After the device is started, the high-precision autofocus system first quickly determines multiple focal planes to obtain the optimal focal length. Subsequently, the scanner, through a high-resolution optical lens and CMOS sensor, moves at high speed along the X and Y axes, capturing images field by field and line by line, automatically capturing every local area of ​​the slide. The computer then seamlessly stitches and fuses these massive local image sequences in real time, ultimately integrating them into a single full-view digital image (WSI file) with a multi-dimensional hierarchical structure.

[0081] Then, basic parameters are constructed on the generated full-view digital image. For example, algorithms such as PathoSAM and U-Net, or methods using self-built annotations to construct algorithm models, are used for tumor cell nucleus identification and segmentation. Exemplarily, the experimental evaluation results specifically include:

[0082] Basic parameter Ca-vivo-1: Size of tumor cell nuclei. Within a unit area (1 mm²) 2 The average area of ​​cell nuclei after counting and segmentation. The larger the parameter, the higher the malignancy of the tumor cells and the worse the prognosis.

[0083] Basic parameter Ca-vivo-2: Uniformity of tumor cell nuclei. Within a unit area (1 mm) 2 Count the cell nuclei after segmentation. Nuclear area consistency: Calculate the coefficient of variation (CV) of the area (Area) of all nuclei; the lower the value, the more consistent the size. CV_area = (Standard deviation of Area / Mean of Area) × 100%. Nuclear shape consistency: Evaluated using the standard deviation of circularity; the lower the value, the more similar the morphology. Circularity = 4π × Area / (Perimeter)^2, Ca-vivo-2 = (CV_area + Circularity) / 2, where Perimeter is the perimeter. A larger parameter indicates a higher degree of malignancy in the tumor cells and a worse prognosis.

[0084] Basic parameter Ca-vivo-3: the near-roundness of tumor cell nuclei. Within a unit area (1 mm) 2 The cell nuclei were counted after segmentation. Circularity is an indicator that quantifies the near-circularity of the cell nucleus. The calculation formula is: C-value (Circularity) = 4π × Area / (Perimeter)^2.

[0085] Ca-vivo-3=

[0086] Basic parameter Ca-vivo-4: tumor cell density. Within a unit area (1 mm²) 2 Count the cell nuclei after segmentation. The number of cells obtained per unit area is n / mm². 2 This is Ca-vivo-4. The higher the parameter, the higher the malignancy of the tumor cells and the worse the prognosis.

[0087] Basic parameter Ca-vivo-5: mitotic count of tumor cells. Within a unit area (1 mm²) 2 Count the segmented cell nuclei. The number of mitotic figures per unit area is m / mm. 2 This is Ca-vivo-5. The higher the parameter, the higher the malignancy of the tumor cells and the worse the prognosis.

[0088] Basic parameter Ca-vivo-6: the percentage of necrotic tumor cells. Within a unit area (1 mm²) 2 Count the cell nuclei after segmentation. The ratio of necrotic cell nuclei to (necrotic cell nuclei + surviving cell nuclei) × 100% = Ca - vivo - 6. A higher parameter indicates a higher degree of malignancy in the tumor cells and a worse prognosis.

[0089] Basic parameter Ca-vivo-7: Ki67 index of tumor cells. Immunohistochemical staining of pathological sections yields Ki67 immunohistochemical pathological sections. Within a unit area (1 mm²) 2 Count the segmented cell nuclei. The ratio of Ki67-positive tumor cells to the total number of tumor cells × 100% = Ca-vivo-7. A higher parameter indicates higher malignancy of the tumor cells and a worse prognosis.

[0090] Basic parameter Ca-vivo-8: HER2 index of tumor cells. Immunohistochemical staining of pathological sections yields HER2 immunohistochemical pathological sections. Within a unit area (1 mm²) 2 Count the cell membranes after segmentation. The ratio of HER2-positive tumor cells to the total number of tumor cells × 100% = Ca-vivo-8. A higher parameter suggests a more significant potential response to HER2-targeted therapy.

[0091] The pathological evaluation of organoids involves multiple parameters and is complex. Relying solely on the doctor's personal evaluation is severely affected by subjectivity and personal experience. By using a constructed deep learning model for pathological evaluation, an efficient, objective, and reliable evaluation of treatment effects can be formed.

[0092] Step S500: Analyze the experimental evaluation results based on the basic evaluation results to obtain the screening results for tumor therapeutic drugs.

[0093] In this embodiment, the experimental evaluation results include adaptive parameters corresponding to each basic evaluation result and several drug sensitivity evaluations. First, based on the adaptive parameters and the corresponding basic evaluation results, the adaptive parameter evaluations corresponding to each adaptive parameter are calculated. Then, based on all the adaptive parameter evaluations and all the drug sensitivity evaluations, the screening results for tumor therapeutic drugs are obtained.

[0094] Specifically, the fitness parameters for in vitro organoid tumor samples are Ca-vitro-1 to Ca-vitro-8, corresponding to Ca-vivo-1 to Ca-vivo-8 in the basic evaluation results.

[0095] The formula for calculating the adaptability parameter Adapt is: Adapt Ca-vitro-1 = (Ca-vitro-1 - Ca-vivo-1) / Ca-vivo-1. …Adapt Ca-vitro-8 = (Ca-vitro-8 - Ca-vivo-8) / Ca-vivo-8. The adaptation parameter, Adapt, is evaluated based on values ​​between -1 and 1. An Adapt value < 0 indicates that tumor cells have migrated from in vivo to outside the body, potentially indicating poor adaptation. The further the Adapt value is from 0, the worse the adaptation ability. An Adapt value > 0 indicates that tumor cells have migrated from in vivo to outside the body, demonstrating strong adaptation ability. The further the Adapt value is from 0, the stronger the adaptation ability.

[0096] Drug sensitivity evaluation of in vitro organoid tumor samples is represented as Ca-drug1-d1. drug1 to drug10 represent 10 different drugs for treating tumors. d1 to d14 represent days 1 to 14 of antitumor drug administration.

[0097] Currently, most live-cell pathological evaluation methods are used in laboratory evaluations for clinical research. However, in clinical practice, these methods often fail to reflect the patient's in vivo pathological data, making it difficult to achieve consistent therapeutic effects in vivo. This invention compares the results of drug-based experimental evaluations with corresponding baseline evaluations for different drugs, dosage regimens, and time periods. By combining adaptability parameter evaluation and drug sensitivity evaluation, it can determine which drugs and dosage regimens are most effective for tumors in vivo while minimizing side effects on normal non-tumor organs. Ultimately, the optimal treatment regimen is recommended under organoid experiments with different drugs and dosage regimens. For example, this embodiment uses in vivo biopsy baseline pathological data as a basis to compare the therapeutic response of tumor cells to relevant drugs on days 0, 1, 7, and 14 of in vitro organoid culture, enabling early drug sensitivity screening for subsequent treatment of cancer patients and selecting more advantageous drugs for clinical recommendation.

[0098] In summary, this embodiment, based on the general pathological and molecular pathological parameters of tumor cells in the patient's body, conducts drug efficacy and screening using organoid cultured tumor cells. This improves the repeatability and consistency of tumor drug screening, making the evaluation more efficient, objective, and reliable. Furthermore, the evaluation of live cells, in vivo samples after fixation, and the combined evaluation with in vitro organoids strengthen the correlation between the evaluation conclusions of in vitro organoids and the subsequent in vivo treatment effects in patients. Moreover, the combination of in vivo immune cell culture with organoids more closely resembles the patient's subsequent in vivo treatment and can elucidate whether the effectiveness of therapeutic drugs depends on the adjuvant effect of in vivo immune cells.

[0099] like Figure 4 As shown, based on the above-described method for screening therapeutic drugs for tumors, this embodiment of the invention discloses a system for screening therapeutic drugs for tumors, comprising:

[0100] The basic evaluation results module 600 is used to perform general pathological and molecular pathological evaluations on in vivo tissue samples from cancer patients to obtain basic evaluation results.

[0101] The experimental evaluation results module 610 is used to perform general pathological evaluation, molecular pathological evaluation and in vitro live cell pathological evaluation on in vitro organoid samples during interventional experiments, and obtain several experimental evaluation results.

[0102] The screening module 620 is used to analyze the experimental evaluation results based on the basic evaluation results to obtain screening results for tumor therapeutic drugs.

[0103] In some implementations, the system further includes an image-taking module and a deep learning model analysis module. The image-taking module is used to take photos at different time points during the interventional experiment to obtain a number of experimental images. The deep learning model analysis module is used to analyze the experimental images using a deep learning model based on general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation to obtain the experimental evaluation results; and to perform general pathological evaluation and molecular pathological evaluation on the in vivo tissue samples to obtain basic evaluation results.

[0104] The purpose of the above embodiments is to reproduce and derive the technical solution of the present invention by way of example, and to fully describe the technical solution, purpose and effect of the present invention. The purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosure of the present invention, and not to limit the scope of protection of the present invention.

[0105] The above embodiments are not an exhaustive list based on the present invention, and there may be many other embodiments not listed. Any substitutions and improvements made without departing from the concept of the present invention are within the protection scope of the present invention.

Claims

1. A method for screening therapeutic drugs for tumors, characterized in that, include: Obtain in vivo tissue samples from cancer patients and simultaneously culture organoids to obtain in vitro organoid culture samples; The in vivo tissue samples were subjected to general pathological and molecular pathological evaluations to obtain several basic evaluation results. An interventional experiment was conducted on the in vitro organoid culture samples using several targeted therapeutic drugs, wherein the targeted therapeutic drugs were initially screened from the in vivo tissue samples; During the interventional experiments, the in vitro organoid samples were subjected to general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation to obtain several experimental evaluation results. Based on the aforementioned fundamental evaluation results, the experimental evaluation results are analyzed to obtain the screening results for tumor therapeutic drugs.

2. The method for screening therapeutic drugs for tumors as described in claim 1, characterized in that, After obtaining in vivo tissue samples from cancer patients, molecular detection and drug screening are performed on the in vivo tissue samples to determine the target therapeutic drug.

3. The method for screening therapeutic drugs for tumors as described in claim 1, characterized in that, The experimental evaluation results include adaptive parameters corresponding to each of the basic evaluation results and several drug sensitivity evaluations. The step of analyzing the experimental evaluation results based on the basic evaluation results to obtain the screening results for tumor therapeutic drugs includes: Based on the adaptive parameters and the corresponding basic evaluation results, calculate the adaptive parameter evaluation corresponding to each adaptive parameter; The results of the tumor therapeutic drug screening were obtained based on all the aforementioned adaptation parameters and all the aforementioned drug sensitivity evaluations.

4. The method for screening therapeutic drugs for tumors as described in claim 3, characterized in that, Based on the adaptive parameters and the corresponding basic evaluation results, calculate the adaptive parameter evaluation corresponding to each adaptive parameter, including: Calculate the difference between the adaptive parameter and the corresponding basic evaluation result, and divide the calculation result by the corresponding basic evaluation result to obtain the adaptive parameter evaluation.

5. The method for screening therapeutic drugs for tumors as described in claim 1, characterized in that, During the interventional experiments, the in vitro organoid samples underwent general pathological evaluation, molecular pathological evaluation, and in vitro live-cell pathological evaluation, yielding several experimental evaluation results, including: During the intervention experiment, photos were taken at different time points to obtain several experimental images; Based on general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation, a deep learning model was used to analyze the experimental images to obtain the experimental evaluation results.

6. The method for screening therapeutic drugs for tumors as described in claim 5, characterized in that, The experimental evaluation results include: tumor cell nucleus size, tumor cell nucleus uniformity, tumor cell nucleus near-roundness, tumor cell density, tumor cell mitotic figures, tumor cell necrosis rate, tumor cell Ki67 index, and tumor cell HER2 index.

7. The method for screening therapeutic drugs for tumors as described in claim 1, characterized in that, When conducting interventional experiments on the in vitro organoid culture samples using several targeted therapeutic agents, the method further includes: Immune cells from cancer patients were extracted and separated, made into cell suspensions, and cultured and proliferated to obtain mixed immune cell suspensions from cancer patients. Interventional experiments were conducted by co-culturing mixed immune cell suspensions from cancer patients with tumor organoids.

8. The method for screening therapeutic drugs for tumors as described in claim 1, characterized in that, Perform in vitro live-cell pathological evaluation, including: The growth and basic morphology of tumor cells in the control group and drug group undergoing the intervention experiment were observed at preset time points to determine the adaptability of live cells in vitro under various experimental conditions.

9. A tumor therapeutic drug screening system, characterized in that, include: The basic evaluation results module is used to perform general pathological and molecular pathological evaluations on in vivo tissue samples from cancer patients to obtain basic evaluation results. The experimental evaluation results module is used to perform general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation on in vitro organoid samples during interventional experiments, and obtain several experimental evaluation results. The screening module is used to analyze the experimental evaluation results based on the basic evaluation results to obtain screening results for tumor therapeutic drugs.

10. The tumor therapeutic drug screening system as described in claim 9, characterized in that, It also includes a photography module and a deep learning model analysis module. The photography module is used to take pictures at different time points during the intervention experiment to obtain a number of experimental images. The deep learning model analysis module is used to analyze the experimental images based on general pathological evaluation, molecular pathological evaluation, and in vitro live cell pathological evaluation, and to obtain the experimental evaluation results. It also performs general pathological evaluation and molecular pathological evaluation on the in vivo tissue samples to obtain basic evaluation results.

Images