Gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging
Through super-resolved imaging technology of platelet subcellular structures, gynecological tumors are identified using the distribution form of α particles, which solves the problems of poor diagnosis specificity and untimely results in the prior art, and achieves rapid and accurate identification and treatment evaluation of gynecological tumors.
Patent Information
- Application Number
- CN202310586833.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-24
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2043-05-24
AI Technical Summary
The existing gynecological tumor diagnosis technology has poor detection specificity, untimely diagnosis results and is prone to false negatives, especially for the early detection and recurrence monitoring of ovarian cancer, endometrial cancer and cervical cancer. biomarkers.
Based on the super-resolution imaging technology of platelet subcellular structure, the super-resolution image of platelet α particles is obtained, and the distribution form of α particles is classified and counted. The ratio of platelets with 'regularly distributed' is used as a biomarker to distinguish gynecology. The benign and malignant tumors are judged by the patient's tumor risk and evaluated for the treatment effect.
It realizes rapid and accurate identification of gynecological tumors, improves the sensitivity and specificity of diagnosis, and can promptly identify gynecological malignant tumors, helps to detect and treat early.
Smart Images

Figure CN119027360A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of gynecological malignant tumor diagnosis, and more specifically, relates to a gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging. Background Art
[0002] Gynecological tumors usually refer to benign gynecological tumors and malignant gynecological tumors. Benign gynecological tumors include ovarian cysts, endometrial hyperplasia, endometrial polyps, etc.; malignant gynecological tumors mainly include ovarian cancer, endometrial cancer, cervical cancer and other three categories. Today, the incidence and mortality of gynecological malignant tumors are increasing year by year, posing a huge threat to women's lives. Efficient, economical, and accurate diagnosis and stratified treatment play an important role in timely treatment of patients. Early and accurate classification of gynecological tumors has always been a hot topic of research.
[0003] At present, the commonly used methods for clinical detection of ovarian cancer include tumor markers (such as serum cancer antigen 125, human epididymis protein 4) combined with ultrasound, CT and other imaging examinations, but tissue biopsy is still the gold standard for diagnosing benign and malignant ovarian cancer, and tissue biopsy has the disadvantages of invasiveness, high cost, poor reproducibility and untimely diagnosis results. For the diagnosis of endometrial cancer, the focus is mainly on cytology and transvaginal ultrasound, but both have poor specificity and cannot meet clinical requirements. At present, histopathological examination is also the gold standard for diagnosing benign and malignant endometrial cancer, but due to the multifocality of endometrial lesions and the limitations of sampling methods, endometrial biopsy still has about 10% false negatives; moreover, there is no known sensitive tumor marker for the diagnosis and follow-up of endometrial cancer.
[0004] In addition, clinical screening for cervical cancer mostly uses HPV screening, exfoliative cytology and colposcopy. However, in terms of follow-up after treatment and early detection of recurrence, cervical cancer lacks highly specific and sensitive biomarkers, and the accuracy of diagnostic results is poor. It can be seen that the existing technology has poor detection and diagnostic specificity in the diagnosis and identification of benign and malignant tumors in gynecological tumors, and the diagnostic results are not timely, and even false negatives are prone to occur, resulting in inaccurate diagnostic results. To date, rapid diagnosis of benign and malignant gynecological tumors is still a difficult problem that needs to be solved in clinical practice.
[0005] In recent years, liquid biopsy has become a favorable tool for tumor diagnosis as an emerging disease diagnosis technology. Compared with traditional tissue pathological biopsy, liquid biopsy samples are widely available and can minimize errors caused by human manipulation and disease heterogeneity. Existing studies have shown that platelets have become a potentially valuable source of liquid biopsy, and platelet count, mean volume, distribution width, RNA and protein can be used as effective biomarkers for cancer screening, diagnosis, prognosis and treatment monitoring. However, platelet count, mean volume and distribution width are highly variable and also change in inflammatory patients, with poor specificity in diagnosing cancer. Platelet RNA and protein have the disadvantages of low content, complex analysis methods and poor sensitivity in diagnosing cancer. However, there are few existing studies on cancer-related studies at the subcellular level of platelets (including microtubules, α granules, mitochondria and dense granules). Therefore, it is of great significance to study a diagnostic system based on the subcellular structure of platelets to quickly and accurately identify gynecological tumors. Summary of the invention
[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, which aims to classify the platelets according to the "regular distribution" of α particles, the number of α particles "N<30", "N≥30" and "aggregated distribution" based on the super-resolution image of the platelet subcellular structure obtained by detecting the sample blood, and count the proportion of each type of platelets. It is found that the proportion of platelets with "regular distribution" of α particles in gynecological tumor patients is greater than that in healthy people, and the proportion of platelets with "regular distribution" of α particles in blood is greater than that in healthy people. The proportion of platelets can be used to distinguish between benign and malignant gynecological tumors. It has high sensitivity and good specificity, and can be used as a biomarker for quickly identifying benign and malignant gynecological tumors. The higher the proportion of platelets with "regular distribution" of α particles, the higher the risk of judging that the sample is a gynecological tumor. In particular, when the proportion of platelets with "regular distribution" of α particles is greater than the proportion corresponding to the Youden maximum, the sample is judged to be at high risk of gynecological malignant tumors, thereby solving the technical problem of the existing untimely judgment of benign and malignant tumors based on tissue biopsy results and poor specificity.
[0007] To achieve the above-mentioned object, according to one aspect of the present invention, a gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure is provided, which includes a super-resolution image acquisition module of platelet subcellular structure, a platelet classification and statistics module, and a gynecological tumor diagnosis module;
[0008] The super-resolution image acquisition module of the platelet subcellular structure is used to acquire multiple super-resolution images of platelet alpha particles composed of fluorescent signal pixels and non-fluorescent signal pixels of the sample to be diagnosed, and submit them to the platelet classification and statistics module;
[0009] The platelet classification and statistics module counts the total number of platelets and the number of platelets with "regular distribution" of alpha particles based on all acquired alpha particle super-resolution images, calculates the proportion of "regularly distributed" platelets in the sample, and submits it to the gynecological tumor diagnosis module;
[0010] The gynecological tumor diagnosis module is used to judge that the higher the proportion of platelets with "regular distribution" of alpha particles, the greater the possibility that the sample is a gynecological tumor. The gynecological tumor includes benign gynecological tumors and malignant gynecological tumors.
[0011] Preferably, the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, and its gynecological tumor diagnosis module are used to judge that the sample is at high risk of gynecological malignant tumor based on the fact that the proportion of platelets with "regular distribution" of alpha particles is greater than a preset threshold; the preset threshold is less than or equal to the ratio corresponding to the Newden maximum value of the ROC curve between healthy people and patients with gynecological malignant tumors.
[0012] Preferably, in the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, the preset threshold is the ratio of the Youden maximum value corresponding to the ROC curve between healthy people and patients with gynecological malignancies.
[0013] Preferably, in the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, the ratio of the Youden maximum value corresponding to the ROC curve between healthy people and patients with gynecological malignancies is 7.75%, that is, when the proportion of platelets with "regular distribution" of α particles is greater than 7.75%, it is judged to be a gynecological malignancy.
[0014] Preferably, in the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, if the sample to be diagnosed comes from a gynecological tumor patient, the gynecological tumor diagnosis module is also used to compare the proportion of the obtained "regularly distributed" platelets with a threshold value to determine whether the gynecological tumor is benign or malignant. The specific determination method is as follows:
[0015] If the proportion of platelets with "regular distribution" of alpha particles in the patient is less than or equal to the threshold, the patient is judged to have a benign gynecological tumor;
[0016] If the proportion of platelets with "regular distribution" of alpha particles in the patient is greater than the threshold, the patient is judged to have gynecological malignancy;
[0017] The threshold is the ratio of the Youden maximum value corresponding to the ROC curve between patients with benign gynecological tumors and patients with malignant gynecological tumors.
[0018] Preferably, in the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, the ratio of the Youden maximum value corresponding to the ROC curve between patients with benign gynecological tumors and patients with malignant gynecological tumors is 5.66%.
[0019] Preferably, the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, the total number of platelets counted is the sum of the numbers of four types of platelets: α particles showing "regular distribution", α particles showing "N<30", "N≥30" and α particles showing "aggregated distribution".
[0020] Preferably, the gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging further includes a gynecological tumor treatment evaluation module;
[0021] The super-resolution image acquisition module of the platelet subcellular structure is used to respectively acquire the super-resolution images of platelet alpha particles composed of fluorescent signal pixels and non-fluorescent signal pixels of patients with gynecological malignancies before and after treatment, and submit them to the platelet classification and statistics module;
[0022] The platelet classification and statistics module classifies the individual platelets according to the distribution forms of the individual platelet alpha particles in the super-resolution images obtained before and after treatment according to the alpha particles presenting "regular distribution", the number of alpha particles "N<30", "N≥30" and the alpha particles presenting "aggregated distribution", and counts the percentage of each type of platelet in the total number of platelets, and submits the results to the gynecological tumor treatment evaluation module;
[0023] The gynecological tumor treatment evaluation module is used to judge whether the treatment is effective based on the comparison of the proportion of platelets with "regular distribution" of α particles, the number of α particles "N<30" and the "aggregated distribution" of α particles before and after treatment. The specific judgment method is as follows:
[0024] If the proportion of platelets with "regular distribution" of α particles decreases after treatment or the proportion of platelets with "N < 30" and / or "aggregated distribution" of α particles increases compared with before treatment, the treatment is considered to be effective.
[0025] Preferably, the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure is evaluated as having a good treatment effect if the proportion of platelets with "regular distribution" of alpha particles in the patient decreases significantly after treatment compared with before treatment.
[0026] Preferably, the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure is evaluated as having a good treatment effect if, compared with before treatment, the proportion of platelets with "regular distribution" of alpha particles in the patient after treatment is less than or equal to the proportion corresponding to the Youden maximum value of the ROC curve between the patient before and after the treatment of the gynecological malignancy.
[0027] Preferably, in the gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, the ratio of the Youden maximum value corresponding to the ROC curve between patients before and after treatment of gynecological malignant tumors is 17.71%.
[0028] In general, compared with the prior art, the above technical solution conceived by the present invention can achieve the following beneficial effects because the present invention provides a gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure:
[0029] The gynecological tumor diagnosis system provided by the present invention is based on super-resolution imaging of α particles of platelet subcellular structure, and platelets are classified according to α particles presenting "regular distribution", α particle number "N<30", α particle number "N≥30" and α particles presenting "aggregated distribution", and the total number of these four types of platelets is counted, and the percentage of platelets with α particles presenting "regular distribution" in the total number of platelets is calculated. The higher the proportion of platelets with α particles presenting "regular distribution" in the patient, the higher the risk of gynecological tumors in the patient is judged; in particular, the proportion of platelets with α particles presenting "regular distribution" is greater than the proportion corresponding to the Youden maximum, and the sample is judged to be a high-risk person for gynecological malignant tumors. The detection required by the gynecological tumor diagnosis system is less invasive, highly sensitive and specific, and can quickly and effectively distinguish between benign and malignant patients with gynecological tumors, and can timely and accurately identify patients with gynecological malignant tumors, which is conducive to the early treatment of patients with gynecological malignant tumors. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 It is the result of classifying platelets according to the distribution pattern of α particles;
[0031] Figure 2 It is the result of differential analysis of the proportion of different types of platelets between healthy people and patients with ovarian cancer, endometrial cancer, and cervical cancer based on the distribution of α particles;
[0032] Figure 3 It is an ROC curve analysis based on the proportion of platelets with "regular distribution" of α particles to identify healthy people and gynecological malignancies;
[0033] Figure 4 It is the result of classifying platelets according to their microtubule distribution;
[0034] Figure 5 It is the result of differential analysis of the proportion of different types of platelets between healthy people and patients with ovarian cancer, endometrial cancer, and cervical cancer based on microtubule distribution;
[0035] Figure 6 It is the result of differential analysis of the proportion of different types of platelets between healthy people and patients with benign and malignant gynecological tumors based on the distribution of α particles;
[0036] Figure 7 It is the result of differential analysis of the proportion of different types of platelets between healthy people and benign and malignant gynecological tumors based on microtubule distribution;
[0037] Figure 8 It is an ROC curve analysis based on the proportion of platelets with "regular distribution" of alpha particles to identify benign and malignant gynecological tumors;
[0038] Fig. 9 It is the result of differential analysis of the proportion of different types of platelets in patients with gynecological tumors before and after treatment based on the distribution of α particles;
[0039] Fig.10 It is an ROC curve analysis based on the proportion of platelets with "regular distribution" of α particles to identify gynecological tumors before and after treatment. DETAILED DESCRIPTION
[0040] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0041] Although some scholars have used electron microscopy to detect platelet subcellular structures (microtubules, mitochondria, etc.), they have found that ovarian cancer can cause changes in the morphology and quantity of platelet substructures, but it is still unknown whether these changes can be used to differentiate between benign and malignant gynecological tumors. Moreover, electron microscopy imaging is time-consuming in sample preparation and slow in image acquisition and analysis, which greatly limits the clinical application of platelet subcellular structure detection. With the development of super-resolution fluorescence microscopy technology, accurate detection of subcellular structures of tens of nanometers has been achieved, but there is no research on platelet subcellular structures in the diagnosis of gynecological tumors.
[0042] Based on the research of the previous patent CN115661074A on a platelet classification method and system based on super-resolution images of platelet α particles and the patent CN115908302A on a platelet microtubule classification method and classification system based on super-resolution images, the present invention further studies the differences in platelet subcellular structures (microtubules, α particles) between healthy people, gynecological benign tumors (ovarian cysts, endometrial hyperplasia and endometrial polyps) and gynecological malignant tumor patients (ovarian cancer, endometrial cancer and cervical cancer). The results show that there are obvious differences in the proportions of different types of platelets based on the distribution form of α particles between healthy people and gynecological malignant tumor patients (ovarian cancer, endometrial cancer and cervical cancer). Compared with healthy people, the proportion of platelets with "regular distribution" of α particles in patients with gynecological malignancies such as ovarian cancer, endometrial cancer and cervical cancer is higher, while the proportion of platelets with "N<30" of α particles and the proportion of platelets with "aggregated distribution" of α particles are lower.
[0043] Furthermore, statistical analysis revealed that there are mainly the following situations between healthy people and patients with benign gynecological tumors and malignant gynecological tumors (ovarian cancer, endometrial cancer, cervical cancer):
[0044] ① The percentage of platelets with "regular distribution" of α particles and platelets with α particle number "N<30" showed significant differences between healthy people and patients with gynecological malignancies (ovarian cancer, endometrial cancer and cervical cancer); while the percentage of platelets with α particle number "N≥30" showed no significant difference between healthy people and ovarian cancer patients, but showed significant differences between healthy people and patients with endometrial cancer and cervical cancer; the percentage of platelets with "aggregated distribution" of α particles also showed significant differences between healthy people and patients with ovarian cancer, endometrial cancer and cervical cancer.
[0045] ②There was no significant difference in the percentage of platelets with "regular distribution" of α granules and platelets with α granule number "N<30" between healthy people and patients with benign gynecological tumors, while there was a significant difference in the percentage of platelets with α granule number "N≥30" and platelets with "aggregated distribution" of α granules between healthy people and patients with benign gynecological tumors.
[0046] Although there was no significant difference in the proportion of platelets with "regular distribution" of α particles and the proportion of platelets with α particles "N<30" between healthy people and benign gynecological tumors, but there was a significant difference between healthy people and gynecological malignancies, further ROC curve analysis between patients with benign gynecological tumors and gynecological malignancies found that the proportion of platelets with "regular distribution" of α particles can well distinguish patients with benign gynecological tumors and gynecological malignancies, while the proportion of platelets with α particles "N<30" cannot distinguish patients with benign gynecological tumors and gynecological malignancies.
[0047] Although the present invention also found that the proportion of different types of platelets based on microtubule distribution is different between healthy people and patients with gynecological malignancies (endometrial cancer, cervical cancer), as follows:
[0048] The proportion of platelets with "diffuse distribution" microtubules was significantly different between healthy people and endometrial cancer patients, but there was no significant difference between healthy people and ovarian cancer and cervical cancer patients.
[0049] The proportion of platelets with "aggregated distribution" in microtubules was significantly different between healthy people and cervical cancer patients, but there was no significant difference between healthy people and ovarian cancer and endometrial cancer patients.
[0050] There was no significant difference between "regular distribution" and "irregular distribution" of microtubules in healthy people and ovarian cancer, endometrial cancer, and cervical cancer.
[0051] Statistical analysis between healthy people, patients with benign gynecological tumors and patients with malignant gynecological tumors found that only the proportion of platelets with "aggregated distribution" of microtubules was significantly different between healthy people and patients with malignant gynecological tumors, but there was no significant difference between healthy people and patients with benign gynecological tumors. There was no significant difference in the proportion of other types of platelets between healthy people, benign gynecological tumors and patients with malignant gynecological tumors.
[0052] However, ROC curve analysis between patients with benign gynecological tumors and patients with malignant gynecological tumors confirmed that the proportion of platelets with "aggregated distribution" of microtubules could not distinguish patients with benign gynecological tumors and patients with malignant gynecological tumors.
[0053] Based on the above findings, the present invention proposes a gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, which includes a super-resolution image acquisition module of platelet subcellular structure, a platelet classification and statistics module, and a gynecological tumor diagnosis module;
[0054] The super-resolution image acquisition module of the platelet subcellular structure is used to perform binarization to obtain a super-resolution image of platelet alpha particles composed of fluorescent signal pixels and non-fluorescent signal pixels, and submit it to the platelet classification and statistics module;
[0055] The platelet classification and statistics module, based on the acquired multiple platelet α granule super-resolution images, counts the total number of platelets in all images and the number of platelets in which individual platelets are "regularly distributed" according to α granules, calculates the percentage of "regularly distributed" platelets in the sample to the total number of platelets, and submits it to the gynecological tumor diagnosis module;
[0056] The platelets with "regular distribution" of α particles are searched for an ellipse that satisfies condition A and has the smallest area in the α particle image of the single platelet as the outer circle: if the area of the outer circle is above the preset threshold of the area of the regular distribution ellipse and the ratio of the minor axis to the major axis is within the preset range of the regular distribution ellipse, the platelets involved in the α particle distribution image of the single platelet are judged to be "regularly distributed"; the threshold of the area of the regular distribution ellipse is within 0.15 μm 2 -20.0μm 2 The range of the regular distribution ellipse is [0.2, 1];
[0057] The gynecological tumor diagnosis module is used to make a judgment based on the proportion of platelets with "regular distribution" of the acquired alpha particles, as follows:
[0058] The higher the proportion of platelets with "regular distribution" of alpha particles, the greater the possibility of judging the sample as a gynecological tumor; the gynecological tumors include benign gynecological tumors and malignant gynecological tumors, among which benign gynecological tumors include ovarian cysts, endometrial hyperplasia, and endometrial polyps; malignant gynecological tumors include ovarian cancer, endometrial cancer, and cervical cancer.
[0059] Preferably, the proportion of platelets with "regular distribution" of alpha particles is greater than a preset threshold, and the sample is judged to be at high risk of gynecological malignancies; the preset threshold is less than or equal to the ratio corresponding to the Youden maximum value of the ROC curve between healthy people and patients with gynecological malignancies.
[0060] More preferably, the proportion of platelets with "regular distribution" of α particles is greater than the proportion of the Youden maximum value corresponding to the ROC curve between healthy people and patients with gynecological malignancies, and the sample is judged to be derived from a person at high risk of gynecological malignancies; in some embodiments, the proportion of the Youden maximum value corresponding to the ROC curve between healthy people and patients with gynecological malignancies is 7.75%. When the proportion of platelets with "regular distribution" of α particles is greater than 7.75%, it is judged to be a gynecological malignancy.
[0061] Furthermore, if the sample comes from a gynecological tumor patient, the gynecological tumor diagnosis module is used to perform a difference analysis based on the proportion of platelets with "regular distribution" of alpha particles obtained and the threshold value, and judge the benign or malignant nature of the gynecological tumor based on the result of the difference analysis. The specific judgment method is as follows:
[0062] If the proportion of platelets with "regular distribution" of alpha particles is significantly different from the threshold, it is judged that the patient is more likely to have a malignant gynecological tumor;
[0063] If the proportion of platelets with "regular distribution" of alpha particles is not significantly different from the threshold, it is highly likely that the patient has a benign gynecological tumor;
[0064] The threshold value is the average value of the proportion of platelets with "regular distribution" of alpha particles in healthy people.
[0065] Preferably, the proportion of platelets with "regular distribution" of the obtained α particles is compared with the threshold value to judge whether the gynecological tumor is benign or malignant, as follows:
[0066] If the proportion of platelets with "regular distribution" of alpha particles in the patient is less than or equal to the threshold, the patient is judged to have a benign gynecological tumor;
[0067] If the proportion of platelets with "regular distribution" of alpha particles in the patient is greater than the threshold, the patient is judged to have gynecological malignancy;
[0068] The threshold is the ratio of the Youden maximum value corresponding to the ROC curve between patients with benign gynecological tumors and patients with malignant gynecological tumors.
[0069] In some embodiments, the proportion of platelets with "regular distribution" of α particles in patients with benign gynecological tumors is less than 5%, while the proportion in patients with malignant gynecological tumors is greater than 40%; through ROC curve analysis between patients with benign gynecological tumors and patients with malignant gynecological tumors, the results indicate that the proportion corresponding to the maximum value of 5.66% can be used as the critical value for distinguishing patients with benign gynecological tumors from patients with malignant gynecological tumors, among which the proportion of platelets with "regular distribution" of α particles is greater than 5.66%, which is judged as a gynecological malignant tumor, and the proportion of platelets with "regular distribution" of α particles is less than or equal to 5.66%, which is judged as a benign gynecological tumor.
[0070] In some embodiments, the total platelet count is the sum of the numbers of four types of platelets: α particles presenting "regular distribution", α particles presenting "N<30", "N≥30", and α particles presenting "aggregated distribution".
[0071] Furthermore, the gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging also includes a gynecological tumor treatment evaluation module;
[0072] The super-resolution image acquisition module of the platelet subcellular structure is used to respectively acquire the super-resolution images of platelet alpha particles composed of fluorescent signal pixels and non-fluorescent signal pixels of patients with gynecological malignancies before and after treatment, and submit them to the platelet classification and statistics module;
[0073] The platelet classification and statistics module classifies individual platelets according to the distribution forms of individual platelet alpha particles in the super-resolution images obtained before and after treatment according to the alpha particles presenting "regular distribution", the number of alpha particles "N<30", "N≥30" and the alpha particles presenting "aggregated distribution", and counts the percentage of each type of platelet in the total number of platelets, and submits the results to the gynecological tumor treatment evaluation module;
[0074] The gynecological tumor treatment evaluation module is used to judge whether the treatment is effective based on the comparison of the proportion of platelets with "regular distribution" of α particles, the number of α particles "N<30" and the "aggregated distribution" of α particles before and after treatment. The specific judgment method is as follows:
[0075] If the proportion of platelets with "regular distribution" of α particles decreases after treatment or the proportion of platelets with "N < 30" and / or "aggregated distribution" of α particles increases compared with before treatment, the treatment is considered to be effective.
[0076] Preferably, if the proportion of platelets with "regular distribution" of alpha particles in the patient decreases significantly after treatment compared with before treatment, the treatment effect is evaluated to be good.
[0077] More preferably, if the proportion of platelets with "regular distribution" of alpha particles in patients after treatment is less than or equal to the proportion corresponding to the Youden maximum value of the ROC curve between patients before and after treatment of gynecological malignancies, the treatment effect is evaluated to be good.
[0078] In some embodiments, the ratio of the Youden maximum value corresponding to the ROC curve between the patients before and after the treatment of the gynecological malignancy is 17.71%.
[0079] The following are examples:
[0080] Example 1 Differentiation of healthy people and gynecological malignancies based on the distribution of α-granules in platelet subcellular structures
[0081] This example classifies platelets according to the distribution of α particles, and analyzes the differences in the proportions of different types of platelets between healthy people and patients with ovarian cancer, endometrial cancer, and cervical cancer.
[0082] The blood of healthy people, ovarian cancer, endometrial cancer and cervical cancer patients was used as the test objects, and super-resolution microscopy technology was used to obtain super-resolution imaging of α particles in the subcellular structure of platelets, as follows:
[0083] (1) Super-resolution imaging of platelet subcellular structures α-granules
[0084] (1-1) Extract platelets from whole blood sample: 2 Place 2-4 mL of anticoagulated whole blood in a medical centrifuge and centrifuge at 200 g for 12 minutes at room temperature. Gently remove the blood and then gently aspirate the supernatant and place it in a centrifuge tube. Then add ACDT solution to the centrifuge tube containing the supernatant and place the centrifuge tube in a 37°C 5% CO 2 Incubate in an incubator for 2 h to recover.
[0085] (1-2) Fixation of platelets: Remove the centrifuge tube from the incubator, add an equal amount of fixative solution to the centrifuge tube, and let it stand for 30 minutes. Place the centrifuge tube in a horizontal centrifuge, centrifuge at 1500g for 3 minutes at room temperature, then gently remove it, add 1mL of PBS solution, pipette and mix, and centrifuge at 1500g for 3 minutes at room temperature. Repeat 3 times.
[0086] (1-3) Immunostaining of platelet subcellular structures:
[0087] ① Platelet plating: first dilute the platelet suspension with PBS, then pipette a small amount of the platelet suspension into the poly-lysine treated culture dish, let it stand for 1 hour, and then observe the platelet density under a microscope. If the density is too low, pipette out the solution in the dish and repeat the process; if it is too high, increase the dilution ratio and repeat the process.
[0088] ② Punching: Add 0.2 mL of 0.2% Triton X-100 solution to the culture dish containing platelets, let it stand at room temperature for 10 minutes, and then aspirate the solution.
[0089] ③ Blocking: Add 0.2 mL of blocking solution into the culture dish, let it stand at room temperature for 60 minutes, and then aspirate the solution.
[0090] ④Primary antibody labeling: dilute the primary antibody in blocking solution, with the microtubule antibody dilution ratio of 1:500 and the α-particle dilution ratio of 1:1000. Add a certain amount of primary antibody dilution solution to the culture dish and incubate at 4°C overnight.
[0091] ⑤Primary antibody rinsing: Aspirate the primary antibody dilution in the culture dish, add antibody washing solution, place it on a shaker and gently rinse at room temperature for 5 minutes, repeat 5 times.
[0092] ⑥ Secondary antibody labeling: dilute the secondary antibody in blocking solution, with the dilution ratio of microtubules and α particles being 1:500. Add a certain amount of secondary antibody dilution solution to the culture dish and incubate at room temperature for 1 hour.
[0093] ⑦ Secondary antibody rinsing: Aspirate the secondary antibody dilution in the culture dish, add antibody washing solution, place it on a shaker and gently rinse at room temperature for 5 minutes, repeat 5 times.
[0094] ⑧Re-fixation: Add a small amount of 4% PFA solution into the culture dish, let it stand at room temperature for 10 minutes, and then aspirate the solution.
[0095] ⑨ Rinse: Add a certain amount of PBS solution into the culture dish, place it on a shaker and rinse gently for 5 minutes at room temperature, repeat 3 times.
[0096] (1-4) Super-resolution imaging of platelet subcellular structures: Adjust the fluorescence intensity and exposure time of each sample during imaging to ensure that each reconstructed image has a high signal-to-noise ratio. Then use super-resolution microscopy imaging technology (SIM, STED, STORM, etc.) to image a large number of platelets, obtain 50 large super-resolution fluorescence images of platelet subcellular structures, and count the total number of platelets in all super-resolution images. The total number of platelets is greater than or equal to 500.
[0097] (2) Platelet classification and statistical analysis: The super-resolution fluorescence images were input into the ResUNet and ResNet-50 algorithm models, and platelets were classified according to the α particle distribution in patent CN115661074A. Figure 1 The difference in the percentage of each type of platelet between 28 healthy subjects and 34 patients with ovarian cancer, 29 patients with endometrial cancer, and 31 patients with cervical cancer was statistically analyzed. The results are shown in Figure 2 shown.
[0098] Figure 1 In order to classify platelets according to the distribution of α particles, they are divided into four categories: α particle number "N < 30", α particle number "N ≥ 30", "regular distribution" and "aggregated distribution".
[0099] Depend on Figure 2 It can be seen that the proportion of platelets with α particles "N<30", "regular distribution" and "aggregated distribution" are significantly different between healthy people and patients with ovarian cancer, endometrial cancer and cervical cancer. In addition, the proportion of platelets with α particles "N≥30" is also significantly different between healthy people and patients with endometrial cancer and cervical cancer, but there is no significant difference between healthy people and patients with ovarian cancer.
[0100] Furthermore, receiver operating characteristic curve analysis (ROC curve analysis) is mainly used to evaluate the effect of a certain indicator on the classification or diagnosis of two types of testers (such as patients and normal people), and to find the best indicator critical value, and then determine the critical value of this evaluation indicator.
[0101] The ROC curve analysis results between healthy people and patients with gynecological malignancies showed that the proportion of platelets with "regular distribution" of α particles can distinguish healthy people from patients with gynecological malignancies. Figure 3 As shown, the AUC area of the ROC curve is 0.915 (95% Cl 0.866-0.964), the significant p value is <0.05, and the Youden maximum corresponding to the proportion of platelets with "regular distribution" of α particles to distinguish healthy people from gynecological malignancies is 7.75%, which can be used as the critical value to distinguish healthy people from patients with gynecological malignancies. When the proportion of platelets with "regular distribution" of α particles exceeds 7.75%, gynecological tumors can be diagnosed as malignant, with a corresponding sensitivity of 81.9% and a specificity of 92.9%. The proportion of other types of platelets cannot distinguish healthy people from patients with gynecological malignancies.
[0102] The true positive rate (TPR) is also called sensitivity: the ratio of the number of samples that are actually positive and are correctly judged as positive to the number of samples that are actually positive.
[0103] Specificity refers to the proportion of people who are actually disease-free that can be correctly identified as non-patients by the screening method, where specificity is equal to 1-false positive probability;
[0104] False positive rate (FPR): The ratio of the number of samples that are actually negative but are mistakenly judged as positive to the number of samples that are actually negative.
[0105] Comparative Example 1 Differentiation of healthy people and gynecological malignancies based on platelet subcellular structure microtubules
[0106] In this case, platelets were classified according to their microtubule distribution, and the differences in the proportions of different types of platelets between healthy people and patients with ovarian cancer, endometrial cancer, and cervical cancer were analyzed.
[0107] The blood of healthy people, ovarian cancer, endometrial cancer and cervical cancer patients was used as the test objects, and super-resolution microscopic imaging technology was used to obtain super-resolution imaging of microtubules in the subcellular structure of platelets, as follows:
[0108] (1) Super-resolution imaging of microtubules in platelet subcellular structures: except for the different types of primary antibodies used for incubation, the primary antibody required for microtubule detection was used in this embodiment, and the rest was the same as in Example 1;
[0109] (2) Platelet classification and statistical analysis: The super-resolution fluorescence images were input into the ResUNet and ResNet-50 algorithm models, and platelets were classified according to the microtubule distribution in patent CN115908302A. The platelet classification was as follows: Figure 4 As shown, the percentage differences of each type of platelets between 24 healthy subjects and 25 ovarian cancer, 29 endometrial cancer and 22 cervical cancer patients were statistically analyzed, as shown in Figure 5 shown.
[0110] Figure 4 In order to classify platelets according to their microtubule distribution, they are divided into four categories: “regular distribution”, “diffuse distribution”, “aggregated distribution” and “irregular distribution”.
[0111] like Figure 5 As shown, there was no significant difference in the proportion of platelets with "regular distribution" of microtubules and that of platelets with "irregular distribution" of microtubules between healthy people and patients with ovarian cancer, endometrial cancer, and cervical cancer, while there was a significant difference in the proportion of platelets with "diffuse distribution" of microtubules between healthy people and patients with endometrial cancer, but no significant difference between healthy people and patients with ovarian cancer and cervical cancer; there was a significant difference in the proportion of platelets with "aggregated distribution" of microtubules between healthy people and patients with cervical cancer, but no significant difference between healthy people and patients with ovarian cancer and endometrial cancer.
[0112] Furthermore, the ROC curve analysis between healthy people and gynecological malignancies showed that the AUC of the proportion of platelets with "diffuse distribution" of microtubules for distinguishing healthy people from gynecological malignancies was 0.604 (95% Cl 0.489-0.720), and the significant p value was greater than 0.05. Therefore, the proportion of platelets with "diffuse distribution" of microtubules cannot distinguish healthy people from patients with gynecological malignancies.
[0113] At the same time, the results showed that the AUC of the proportion of platelets with microtubules in "aggregated distribution" for distinguishing healthy people from gynecological malignancies was 0.615 (95% Cl 0.487-0.743), and the significant p value was greater than 0.05. Therefore, the proportion of platelets with microtubules in "aggregated distribution" could not distinguish healthy people from patients with gynecological malignancies.
[0114] Example 2 Differentiation of healthy people, gynecological benign tumors and gynecological malignant tumors based on the distribution of platelet subcellular structure α particles
[0115] In this example, platelets were classified according to the distribution of α particles, and the differences in the proportions of different types of platelets among 28 healthy subjects, 30 patients with benign gynecological tumors, and 94 patients with malignant gynecological tumors were analyzed.
[0116] Among them, there were 30 patients with benign gynecological tumors, including 18 patients with ovarian cysts, 4 patients with endometrial hyperplasia, and 8 patients with endometrial polyps; there were 94 patients with malignant gynecological tumors, including 34 patients with ovarian cancer, 29 patients with endometrial cancer, and 31 patients with cervical cancer.
[0117] The blood of healthy people, patients with benign gynecological tumors and patients with malignant gynecological tumors were used as test objects, and super-resolution microscopy technology was used to obtain super-resolution imaging of α particles in the subcellular structure of platelets, as follows:
[0118] (1) Super-resolution imaging of platelet subcellular structure α particles: Same as Example 1.
[0119] (2) Platelet classification and statistical analysis: Platelet classification was the same as in Example 1. Statistical analysis was performed on platelets classified according to the distribution of α particles. The statistical results are as follows: Figure 6 shown.
[0120] Depend on Figure 6 It can be seen that the proportion of platelets with α granules "N≥30" and the proportion of platelets with "aggregated" α granules decrease successively among healthy people, patients with benign gynecological tumors and patients with malignant gynecological tumors; while the proportion of platelets with "regular distribution" of α granules increases successively, indicating that the higher the proportion of platelets with "regular distribution" of α granules, the greater the possibility of suffering from gynecological tumors, especially the risk of gynecological malignant tumors is higher.
[0121] However, there was no significant difference in the proportion of platelets with α granules "N<30" and "regular distribution" between healthy people and patients with benign gynecological tumors, but there was a significant difference between healthy people and patients with malignant gynecological tumors. It can be seen that the proportion of platelets with "regular distribution" of α granules and α granules "N<30" may be a biomarker for quickly identifying benign and malignant gynecological tumors.
[0122] Comparative Example 2 Differentiation of healthy people, gynecological benign tumors and gynecological malignant tumors based on the distribution of platelet subcellular microtubules
[0123] This example classifies platelets according to their microtubule distribution, and analyzes the differences in the proportions of different types of platelets among 24 healthy subjects, 19 patients with benign gynecological tumors, and 76 patients with malignant gynecological tumors.
[0124] Among them, there were 19 patients with benign gynecological tumors, including 13 patients with ovarian cysts, 3 patients with endometrial hyperplasia, and 3 patients with endometrial polyps; there were 76 patients with malignant gynecological tumors, including 25 patients with ovarian cancer, 29 patients with endometrial cancer, and 22 patients with cervical cancer.
[0125] The blood of healthy people, patients with benign gynecological tumors and patients with malignant gynecological tumors were used as test objects, and super-resolution microscopic imaging technology was used to obtain super-resolution imaging of microtubules in the subcellular structure of platelets, as follows:
[0126] (1) Super-resolution imaging of microtubules in platelet subcellular structures: same as comparative example 1.
[0127] (2) Platelet classification and statistical analysis: Platelet classification was the same as in Comparative Example 1. Statistical analysis of platelets after classification according to microtubule distribution was performed. The statistical results are as follows: Figure 7 shown.
[0128] Depend on Figure 7 It can be seen that the proportion of the four types of platelets distributed according to microtubules is significantly different between healthy people and patients with benign gynecological tumors, and there is no significant difference in other categories.
[0129] Further, the ROC curve analysis between healthy people and patients with benign gynecological tumors showed that the AUC of the proportion of platelets in the "aggregated distribution" of microtubules to distinguish healthy people from benign gynecological tumors was 0.712 (95% Cl 0.556-0.868), with a significant p value of <0.05, and the corresponding sensitivity was 84.2% and the specificity was 58.3%. When applied to distinguishing healthy people from benign gynecological tumors, the specificity is mainly referenced, and the higher the specificity, the better. Because the specificity is low, it can be seen that the proportion of platelets in the "aggregated distribution" of microtubules cannot distinguish healthy people from patients with benign gynecological tumors very well.
[0130] There was no significant difference between healthy people and patients with gynecological malignancies, indicating that the proportion of different types of platelets based on microtubule distribution cannot be used to distinguish healthy people from patients with gynecological malignancies.
[0131] Example 3 Specificity of distinguishing benign and malignant gynecological tumors based on the proportion of platelets with “regular distribution” of α particles and α particles with “N<30”
[0132] In this embodiment, the blood of patients with benign gynecological tumors and malignant gynecological tumors is used as the detection object, wherein sample group 1 is the blood samples of patients with benign gynecological tumors, and sample group 2 is the blood samples of patients with malignant gynecological tumors, as follows:
[0133] The α particles in the platelets are detected by using the super-resolution imaging technology as in Example 1, and the super-resolution imaging of the α particles of the platelets of the two groups of samples is obtained;
[0134] Platelet classification and statistics were performed according to the platelet classification in Example 1. The results were as follows:
[0135] Sample group 1: In patients with benign gynecological tumors, the proportion of platelets with alpha granules "N<30" was 89.77%±2.29%, the proportion of platelets with "N≥30" was 2.33%±1.46%, the proportion of platelets with "regular distribution" was 4.09%±1.31%, and the proportion of platelets with "aggregated distribution" was 3.81%±1.41%.
[0136] Sample group 2: In patients with gynecological malignancies, the proportion of platelets with alpha granules "N<30" was 54.78%±2.99%, the proportion of platelets with "N≥30" was 1.84%±0.58%, the proportion of platelets with "regular distribution" was 42.20%±3.08%, and the proportion of platelets with "aggregated distribution" was 1.18%±0.27%.
[0137] ROC curves were drawn for the different proportions of platelets with "regular distribution" of α particles and α particles with "N < 30" in the two groups of samples, such as Figure 8 As shown, the results showed that the AUC area of the ROC curve drawn with different proportions of platelets with "regular distribution" of α particles was 0.910 (95% Cl0.860-0.961), and the significant p value was <0.05, indicating that the different proportions of platelets with "regular distribution" of α particles can better distinguish patients with gynecological benign tumors and gynecological malignancies, and the diagnostic results are highly reliable.
[0138] The ROC curve between benign gynecological tumors and malignant gynecological tumors was drawn using different proportions of platelets with α particles "N<30". The results showed that the proportion of platelets with α particles "N<30" was difficult to distinguish between patients with benign gynecological tumors and malignant gynecological tumors, and could not be used for the diagnosis and judgment of benign and malignant gynecological tumors.
[0139] Youden Index, also known as the correct index, is a commonly used method when assuming that the harmfulness of false negatives (missed diagnosis rate) and false positives (misdiagnosis rate) is of equal significance. It reflects the total ability of real patients and non-patients. The Youden Index is the sum of sensitivity and specificity minus 1. The larger the Youden Index, the greater the authenticity. At the same time, the test variable value corresponding to the maximum value of the Youden Index is the diagnostic critical value of the method. Youden Index = Sensitivity + Specificity - 1.
[0140] Further analysis showed that the proportion of platelets with "regular distribution" of α particles corresponding to the Youden maximum value for distinguishing benign gynecological tumors from gynecological malignant tumors was 5.66%, which can be used as the critical value for distinguishing patients with benign gynecological tumors from gynecological malignant tumors. When the proportion of platelets with "regular distribution" of α particles exceeds 5.66%, the gynecological tumor can be diagnosed as malignant, with a corresponding sensitivity of 85.1% and a specificity of 83.3%.
[0141] Example 4 Evaluation of therapeutic effects on patients with malignant tumors based on the proportion of platelets with “regular distribution” of α particles
[0142] In this embodiment, blood samples of patients with gynecological malignant tumors before and after treatment are used as the detection objects, wherein sample group 1 is the blood samples of patients with gynecological malignant tumors before treatment, and sample group 2 is the blood samples of patients with gynecological malignant tumors after treatment, as follows:
[0143] The α particles in the platelets are detected by using the super-resolution imaging technology as in Example 1, and the super-resolution imaging of the α particles of the platelets of the two groups of samples is obtained;
[0144] Platelet classification and statistics, according to the platelet classification in Example 1, the statistical analysis results are as follows Fig. 9 As shown:
[0145] Depend on Fig. 9 It can be seen that the proportion of platelets with α granules "N<30", platelets with α granules "regular distribution" and platelets with α granules "aggregated distribution" were significantly different between patients with gynecological malignancies and healthy people before treatment, but there was no significant difference between patients with gynecological tumors and healthy people after treatment. Fig. 9 It can be seen that after treatment, the proportion of platelets with α granules "N<30" and platelets with α granules showing "aggregated distribution" in patients with gynecological tumors increased significantly, while the proportion of platelets with α granules showing "regular distribution" decreased significantly, which reflects that patients with gynecological tumors have improved after treatment, indirectly indicating that the treatment is effective.
[0146] The ROC curves between patients with gynecological malignancies before and after treatment were drawn for the different proportions of platelets with "regular distribution" of α particles in the two groups of samples, such as Fig.10 As shown:
[0147] Fig.10 The AUC area of the ROC curve was 0.891 (95% Cl 0.731-1.000), and the significant p value was <0.05, indicating that the proportion of platelets with "regular distribution" of α particles has the potential to distinguish patients with gynecological malignancies before and after treatment, and can be used to evaluate the effect of treatment in patients with gynecological malignancies.
[0148] Further analysis shows that the proportion of platelets with "regular distribution" of alpha particles that distinguish the Youden maximum before and after treatment of gynecological malignancies is 17.71%, which can be used as a critical value to judge whether the treatment of patients with gynecological malignancies is effective. When the proportion of platelets with "regular distribution" of alpha particles is lower than 17.71%, it can be judged that the treatment effect of patients with gynecological malignancies is better, and the corresponding sensitivity is 100%. When it is used to judge the treatment effect of patients with gynecological malignancies, the sensitivity is mainly used as a reference. The higher the sensitivity, the more accurate the assessment. It can be seen that the use of the proportion of platelets with "regular distribution" of alpha particles to assess whether the treatment of patients with gynecological malignancies is effective has a high assessment accuracy.
[0149] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A gynecological tumor diagnosis system based on super-resolution imaging of platelet subcellular structure, characterized in that: It includes a super-resolution image acquisition module for platelet subcellular structure, a platelet classification and statistics module, and a gynecological tumor diagnosis module; The super-resolution image acquisition module of the platelet subcellular structure is used to acquire multiple super-resolution images of platelet alpha particles composed of fluorescent signal pixels and non-fluorescent signal pixels of the sample to be diagnosed, and submit them to the platelet classification and statistics module; The platelet classification and statistics module counts the total number of platelets and the number of platelets with "regular distribution" of alpha particles based on all acquired alpha particle super-resolution images, calculates the proportion of "regularly distributed" platelets in the sample, and submits it to the gynecological tumor diagnosis module; The gynecological tumor diagnosis module is used to judge that the higher the proportion of platelets with "regular distribution" of alpha particles, the greater the possibility that the sample is a gynecological tumor. The gynecological tumor includes benign gynecological tumors and malignant gynecological tumors.
2. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 1, characterized in that: The gynecological tumor diagnosis module is used to judge that the sample is a high-risk person for gynecological malignant tumors based on the proportion of platelets with "regular distribution" of alpha particles being greater than a preset threshold; the preset threshold is less than or equal to the proportion corresponding to the Youden maximum value of the ROC curve between healthy people and patients with gynecological malignant tumors.
3. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 2, characterized in that: The preset threshold is the ratio of the Youden maximum value corresponding to the ROC curve between healthy people and patients with gynecological malignancies.
4. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 3, characterized in that: The proportion corresponding to the Youden maximum is 7.75%, that is, when the proportion of platelets with "regular distribution" of α particles is greater than 7.75%, it is judged to be a gynecological malignancy.
5. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 1, characterized in that: If the sample to be diagnosed is from a gynecological tumor patient, the gynecological tumor diagnosis module is also used to compare the proportion of the obtained "regularly distributed" platelets with the threshold value to determine whether the gynecological tumor is benign or malignant. The specific determination method is as follows: If the proportion of platelets with "regular distribution" of alpha particles in the patient is less than or equal to the threshold, the patient is judged to have a benign gynecological tumor; If the proportion of platelets with "regular distribution" of alpha particles in the patient is greater than the threshold, the patient is judged to have gynecological malignancy; The threshold is the ratio of the Youden maximum value corresponding to the ROC curve between patients with benign gynecological tumors and patients with malignant gynecological tumors.
6. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 5, characterized in that: The Youden maximum corresponds to a ratio of 5.66%.
7. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to any one of claims 1 to 6, characterized in that: Also included is a gynecologic oncology treatment assessment module; The super-resolution image acquisition module of the platelet subcellular structure is used to respectively acquire the super-resolution images of platelet alpha particles composed of fluorescent signal pixels and non-fluorescent signal pixels of patients with gynecological malignancies before and after treatment, and submit them to the platelet classification and statistics module; The platelet classification and statistics module classifies single platelets according to the distribution forms of single platelet alpha particles in super-resolution images obtained before and after treatment of patients with gynecological malignant tumors according to the "regular distribution" of alpha particles, the number of alpha particles "N<30", "N≥30" and the "aggregated distribution" of alpha particles, and counts the percentage of each type of platelet in the total number of platelets, and submits it to the gynecological tumor treatment evaluation module; The gynecological tumor treatment evaluation module is used to judge whether the treatment is effective based on the comparison of the proportion of platelets with "regular distribution" of α particles, the number of α particles "N<30" and the "aggregated distribution" of α particles before and after treatment. The specific judgment method is as follows: If the proportion of platelets with "regular distribution" of α particles decreases after treatment or the proportion of platelets with "N<30" and / or "aggregated distribution" of α particles increases after treatment compared with before treatment, the treatment is considered to be effective.
8. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 7, characterized in that: If the proportion of platelets with "regular distribution" of alpha particles in patients after treatment is significantly reduced compared with before treatment, the treatment effect is evaluated to be good.
9. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 8, characterized in that: If the proportion of platelets with "regular distribution" of alpha particles in patients after treatment is less than or equal to the proportion corresponding to the Youden maximum value of the ROC curve between patients before and after treatment of gynecological malignancies, the treatment effect is evaluated to be good.
10. The gynecological tumor diagnosis system based on platelet subcellular structure super-resolution imaging according to claim 9, characterized in that: The proportion corresponding to the Youden maximum is 17.71%.
Citation Information
Patent Citations
Model and system for predicting benign and malignant pulmonary nodules based on platelet parameters
CN113288110A
Platelet classification method and system based on platelet alpha particle super-resolution image
CN115661074A
Platelet microtubule classification method and system based on super-resolution image
CN115908302A
Platelet biomarkers in cancer diagnosis
WO2014116170A1
Cited By
System for evaluating ovarian cancer recurrence based on platelet subcellular structure super-resolution imaging
CN122177428A
Lung cancer early screening system based on platelet alpha particle super-resolution imaging
CN122199404A
