Recognition method and device for renal cyst and hydronephrosis, equipment and storage medium

Abstract

The invention discloses a renal cyst and hydronephrosis identification method and device, equipment and a storage medium, and relates to the technical field of medical image processing, and the method comprises the steps: obtaining clinical data and DECT images of different patients; dECT parameters are determined according to the DECT images; constructing a radiation scoring model according to the DECT parameters; determining clinical symptoms of each patient according to the clinical data; constructing a column graph model according to the radiation scoring model and the clinical symptoms; and identifying whether each DECT image is renal cyst or hydronephrosis according to the column graph model. According to the method, the column graph model with relatively high identification capability is established based on the clinical symptoms and the radiation scoring model, and the hydronephrosis and the renal cyst are identified by utilizing the independent risk factors determined by multivariate analysis of the column graph model, so that the identification accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical image processing technology, and in particular to a method, device, equipment and storage medium for identifying renal cysts and hydronephrosis. Background Art

[0002] Renal cysts are common renal lesions with typical clear fluid. Hydronephrosis is a disease in which the renal pelvis dilates due to urine retention. Ultrasound examination may misdiagnose perinephric cysts as hydronephrosis and vice versa. Currently, the diagnosis of renal cysts mainly relies on enhanced CT imaging by evaluating their morphology and enhancement characteristics. However, existing CT images make it difficult to distinguish between hydronephrosis and renal cysts. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a method, device, equipment and storage medium for identifying renal cysts and hydronephrosis, so as to improve the recognition accuracy of hydronephrosis and renal cysts.

[0004] To achieve the above object, one aspect of an embodiment of the present application provides a method for identifying renal cysts and hydronephrosis, the method comprising the following steps:

[0005] Obtain clinical data and DECT images of different patients;

[0006] Determining DECT parameters according to each of the DECT images;

[0007] constructing a radiomic scoring model according to the DECT parameters;

[0008] Determining the clinical symptoms of each of the patients according to the clinical data;

[0009] Constructing a nomogram model according to the radiological scoring model and the clinical symptoms;

[0010] According to the nomogram model, it is identified whether each of the DECT images is a renal cyst or hydronephrosis.

[0011] In some embodiments, the determining of DECT parameters according to each of the DECT images comprises the following steps:

[0012] Reconstructing virtual monochrome images of different energies according to each of the DECT images;

[0013] Determining an effective atomic number based on each of the DECT images;

[0014] determining different material pair images according to each of the DECT images;

[0015] Calculating the DECT index of each of the virtual monochrome images according to each of the DECT images;

[0016] The virtual monochrome image, the effective atomic number, the material pair image and the DECT index serve as the DECT parameters.

[0017] In some embodiments, reconstructing virtual monochrome images of different energies according to each of the DECT images comprises the following steps:

[0018] The virtual monochrome images with energy ranging from 40keV to 140keV and intervals of 10keV are reconstructed according to the DECT images.

[0019] In some embodiments, determining different material pair images according to each of the DECT images comprises the following steps:

[0020] The substance pair images reconstructed according to each of the DECT images include: creatinine-iodine, creatinine-water, creatinine-glucose, water-iodine, water-creatinine, water-glucose, iodine-water, iodine-creatinine, iodine-glucose, glucose-iodine, glucose-water and glucose-creatinine.

[0021] In some embodiments, the step of calculating the DECT index of each of the virtual monochrome images according to each of the DECT images comprises the following steps:

[0022] Calculate the dual energy index, dual energy ratio, dual energy difference and Lambda of each of the virtual monochrome images according to each of the DECT images as the DECT index;

[0023] The calculation formula of the dual energy index is:

[0024] DEI = HU40kev / HU140kev;

[0025] Wherein, DEI represents the dual energy index; HU represents the CT attenuation value; kev represents the energy unit;

[0026] The calculation formula of the dual energy ratio is:

[0027] DER=(HU40kev-HU140kev) / (HU40kev+HU140kev+2000);

[0028] Wherein, DER represents the dual energy ratio;

[0029] The calculation formula of the dual energy difference is:

[0030] DED = HU80kev - HU140kev;

[0031] Wherein, DED represents the dual energy difference;

[0032] The calculation formula of Lambda is:

[0033] Lamda=(HU40kev-HU70kev) / 30;

[0034] Herein, Lamda represents the Lambda.

[0035] In some embodiments, constructing a radiological scoring model according to the DECT parameters comprises the following steps:

[0036] The radiological scoring model was constructed according to the DECT parameters as follows:

[0037] 0.249+0.373*iodine-creatinine+0.361*DER+1.911*MONO70;

[0038] Among them, DER means dual energy ratio; MONO70 means the CT value of dual energy CT at 70kev.

[0039] In some embodiments, constructing a nomogram model according to the radiological scoring model and the clinical symptoms comprises the following steps:

[0040] Performing univariate logistic regression analysis on the radiological scoring model and the clinical symptoms, thereby identifying several variables with probability values ​​less than a set threshold;

[0041] Performing multivariate logistic regression analysis on each of the variables, thereby identifying predictors with probability values ​​less than the set threshold;

[0042] The nomogram model is constructed according to the predictive factors.

[0043] To achieve the above object, another aspect of the embodiment of the present application provides a device for identifying renal cysts and hydronephrosis, the device comprising:

[0044] A data acquisition unit, used for acquiring clinical data and DECT images of different patients;

[0045] a parameter determination unit, configured to determine a DECT parameter according to each of the DECT images;

[0046] A first model building unit, configured to build a radiological scoring model according to the DECT parameters;

[0047] a symptom determination unit, configured to determine clinical symptoms of each of the patients according to the clinical data;

[0048] A second model building unit is used to build a nomogram model according to the radiological scoring model and the clinical symptoms;

[0049] The identification unit is used to identify whether each of the DECT images is a renal cyst or hydronephrosis according to the nomogram model.

[0050] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above method when executing the computer program.

[0051] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0052] The embodiments of the present application include at least the following beneficial effects:

[0053] The present application can obtain clinical data and DECT images of different patients; determine DECT parameters according to each DECT image; construct a radiological scoring model according to the DECT parameters; determine the clinical symptoms of each patient according to the clinical data; construct a nomogram model according to the radiological scoring model and clinical symptoms; and identify whether each DECT image is a renal cyst or hydronephrosis according to the nomogram model. The present application establishes a nomogram model with high discrimination ability based on clinical symptoms and radiological scoring models, and uses the independent risk factors determined by multivariate analysis of the nomogram model to identify hydronephrosis and renal cysts, which can improve the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 A schematic diagram of a flow chart of a method for identifying renal cysts and hydronephrosis provided in an embodiment of the present application;

[0056] Figure 2 ROI schematic diagram of renal cyst and hydronephrosis provided in the embodiment of the present application;

[0057] Figure 3 An example flowchart of the participant screening process and research steps provided for the embodiments of the present application;

[0058] Figure 4 A schematic diagram of variable selection using LASSO regression analysis and 10-fold cross validation provided in an embodiment of the present application;

[0059] Figure 5Schematic diagram of ROC curves of the RS model and nomogram model provided in the embodiments of the present application in the training set and the validation set respectively;

[0060] Figure 6 An example diagram of a nomogram model provided in an embodiment of the present application;

[0061] Figure 7 A schematic diagram of the calibration curve of the nomogram model in the training set and the validation set provided in the embodiment of the present application;

[0062] Figure 8 A schematic diagram of the decision curve of RS and its related nomogram model in the training set and validation set provided in the embodiment of the present application;

[0063] Fig. 9 A schematic diagram of the structure of a device for identifying renal cysts and hydronephrosis provided in an embodiment of the present application;

[0064] Fig.10 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0066] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0067] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0068] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0069] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations:

[0070] Dual-Energy CT (DECT) is a method that uses X-rays at different energy levels to evaluate tissue absorption of radiation. By acquiring images at two energy levels, DECT helps to break down materials, making it easier to distinguish similar substances, thereby improving image clarity and accuracy. Iodine water images can evaluate blood vessels and tumor blood flow, helping to distinguish tumors. Calcium water images help clarify cardiovascular problems by reducing soft tissue confusion. Uric acid water images can identify uric acid crystals in joints and assist in the diagnosis of gout. DECT can generate multiple parameters, such as monochrome CT values, spectral curve slopes, and material pair images to reflect differences in imaging characteristics.

[0071] The embodiments of the present application provide a method, device, equipment and storage medium for identifying renal cysts and hydronephrosis. The technical solution of the present application includes: acquiring clinical data and DECT images of different patients; determining DECT parameters according to each DECT image; constructing a radiological scoring model according to the DECT parameters; determining the clinical symptoms of each patient according to the clinical data; constructing a nomogram model according to the radiological scoring model and clinical symptoms; and identifying whether each DECT image is a renal cyst or hydronephrosis according to the nomogram model. The present application establishes a nomogram model with high discrimination ability based on clinical symptoms and radiological scoring models, and uses the independent risk factors determined by multivariate analysis of the nomogram model to identify hydronephrosis and renal cysts, which can improve the recognition accuracy.

[0072] The embodiments of the present application provide a method, device, equipment and storage medium for identifying renal cysts and hydronephrosis, and relate to the field of medical image processing technology. The method, device, equipment and storage medium for identifying renal cysts and hydronephrosis provided in the embodiments of the present application can be applied to a terminal, a server, or a software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but are not limited to this; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements a knowledge extraction method, etc., but is not limited to the above forms.

[0073] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0074] Reference Figure 1 The present application embodiment provides a method for identifying renal cysts and hydronephrosis. The method may include but is not limited to S100 to S150, as follows:

[0075] S100: Acquire clinical data and DECT images of different patients.

[0076] S110: Determine DECT parameters according to each of the DECT images.

[0077] Further, S110 may include the following steps S111 to S114:

[0078] S111: reconstructing virtual monochrome images of different energies according to the DECT images.

[0079] More specifically, S111 may include the following steps:

[0080] The virtual monochrome images with energy ranging from 40keV to 140keV and intervals of 10keV are reconstructed according to the DECT images.

[0081] S112: Determine the effective atomic number according to each of the DECT images.

[0082] S113: Determine different material pair images according to each of the DECT images.

[0083] More specifically, S113 may include the following steps:

[0084] The substance pair images reconstructed according to each of the DECT images include: creatinine-iodine, creatinine-water, creatinine-glucose, water-iodine, water-creatinine, water-glucose, iodine-water, iodine-creatinine, iodine-glucose, glucose-iodine, glucose-water and glucose-creatinine.

[0085] S114: Calculating a DECT index of each of the virtual monochrome images according to each of the DECT images.

[0086] More specifically, S114 may include the following steps:

[0087] Calculate the dual energy index, dual energy ratio, dual energy difference and Lambda of each of the virtual monochrome images according to each of the DECT images as the DECT index;

[0088] The calculation formula of the dual energy index is:

[0089] DEI = HU40kev / HU140kev;

[0090] Wherein, DEI represents the dual energy index; HU represents the CT attenuation value; kev represents the energy unit;

[0091] The calculation formula of the dual energy ratio is:

[0092] DER=(HU40kev-HU140kev) / (HU40kev+HU140kev+2000);

[0093] Wherein, DER represents the dual energy ratio;

[0094] The calculation formula of the dual energy difference is:

[0095] DED = HU80kev - HU140kev;

[0096] Wherein, DED represents the dual energy difference;

[0097] The calculation formula of Lambda is:

[0098] Lamda=(HU40kev-HU70kev) / 30;

[0099] Herein, Lamda represents the Lambda.

[0100] The virtual monochrome image, the effective atomic number, the material pair image and the DECT index serve as the DECT parameters.

[0101] S120: constructing a radiological scoring model according to the DECT parameters.

[0102] Further, S120 may include the following steps:

[0103] The radiological scoring model was constructed according to the DECT parameters as follows:

[0104] 0.249+0.373*iodine-creatinine+0.361*DER+1.911*MONO70;

[0105] Among them, DER means dual energy ratio; MONO70 means the CT value of dual energy CT at 70kev.

[0106] S130: Determine the clinical symptoms of each of the patients according to the clinical data.

[0107] S140: constructing a nomogram model according to the radiological scoring model and the clinical symptoms.

[0108] Further, S140 may include the following steps S141 to S143:

[0109] S141: performing univariate logistic regression analysis on the radiological scoring model and the clinical symptoms, thereby identifying a number of variables with probability values ​​less than a set threshold;

[0110] S142: performing a multi-factor logistic regression analysis on each of the variables, thereby identifying a prediction factor having a probability value less than the set threshold;

[0111] S143: constructing the nomogram model according to the prediction factors.

[0112] S150: Identify whether each of the DECT images is a renal cyst or hydronephrosis according to the nomogram model.

[0113] Next, the solution of the embodiment of the present application will be introduced and explained in detail with reference to specific application examples.

[0114] This example included 146 patients with suspected renal cysts, all of whom underwent non-enhanced dual-energy CT scans. Clinical data and DECT parameters were recorded, including virtual monochrome images (VMI) from 40 to 140 keV (increments of 10 keV), effective atomic number (Zeff), 12 substance pair images based on iodine, water, creatinine and glucose, and VMI-derived measurements (DER, DEI, DED, lambda). Participants were divided into training and validation sets (7:3 ratio). Significant DECT parameters were selected by LASSO regression, an RS scoring model was constructed, and a nomogram model was developed based on RS scores and clinical data. According to the scores of RS (-7-7) and clinical symptoms (0 and 1), the probability of the corresponding model graph was used to infer the probability of renal cysts. Among them, clinical symptoms include urinary symptoms and low back pain.

[0115] Among the 146 patients, 78 were diagnosed with renal cysts and 68 with hydronephrosis. The formula of the RS score model was: 0.249+0.373*iodine (creatinine)+0.361*DER+1.911*MONO70. The area under the curve (AUC) of both the training set and the validation set was 0.883 (95% CI: 0.820, 0.946). The nomogram model found that RS (OR = 2.953, 95% CI: 1.784, 6.134) and symptoms (OR = 0.003, 95% CI: 0, 0.028) were significant predictors for distinguishing renal cysts from hydronephrosis. The AUC of the nomogram in the training set and validation set were 0.980 (95% CI: 0.956, 1.000) and 0.974 (95% CI: 0.937, 1.000), respectively. Therefore, the nomogram model based on RS score in this embodiment can improve the accuracy of identifying renal cysts and hydronephrosis.

[0116] Next, this embodiment will be described in more detail.

[0117] The subjects of this example study were recruited between January 2023 and January 2024, with a total of 200 patients, of whom 146 were ultimately included in the analysis.

[0118] 1. Inclusion criteria include:

[0119] Patients who underwent non-enhanced DECT examination;

[0120] Patients with complete clinical information and imaging data;

[0121] CT evaluation indicated Bosniak grade I or II, and postoperative pathological diagnosis was a benign renal cyst. Based on imaging examinations, hydronephrosis was assessed by the dilation of the renal pelvis and ureter.

[0122] Exclusion criteria include:

[0123] The presence of heterogeneous density or abnormal soft tissue within the lesion may indicate diseases such as renal abscess, hemorrhage within renal cyst, or renal cancer;

[0124] Cases with substandard image quality or severe artifacts;

[0125] Patients with severe organic diseases or combined systemic diseases.

[0126] The dataset was randomly divided into two groups: 70% for training set and 30% for validation set. A diagnostic nomogram model was developed based on the training set to distinguish benign renal cysts from hydronephrosis, and its performance was verified using the validation set.

[0127] 2. Clinical data collection.

[0128] The clinical data of each participant were obtained from the electronic medical record system. The clinical data included age, sex, affected side (left, right or bilateral), treatment history and clinical symptoms (such as low back pain, frequent urination, urgency and hematuria). In addition, laboratory venous blood test results were collected, including total protein, albumin, sodium, potassium, calcium, glucose, urea and creatinine.

[0129] 3. DECT scanning.

[0130] The patient was lying flat for non-enhanced scanning using an ultra-high-speed DECT system (GE HealthCare, RevolutionApex CT). Scanning settings included tube voltages of 80 kVp and 140 kVp, automatic tube current adjustment, and a noise index of 7 HU (GSIAssist, GE HealthCare). Image reconstruction used 60% intensity (ASiR-V, GE HealthCare), thickness and spacing of 1.25 mm, pitch of 0.992:1, and scanning speed of 0.8 seconds per revolution.

[0131] 4. DECT image reconstruction and analysis.

[0132] The data of all patients were transferred to the AW4.7 workstation, and 11 virtual monochrome images (VMIs) were reconstructed with an energy range of 40keV to 140keV and an interval of 10keV. At the same time, the effective atomic number (Zeff) of each patient was also reconstructed. Taking into account the differences in electrolyte, glucose and protein content between renal cyst fluid and hydronephrosis, 12 substance pair images based on iodine, creatinine, glucose and water were further reconstructed. The reconstructed base substance pairs include: creatinine (iodine), creatinine (water), creatinine (glucose), water (iodine), water (creatinine), water (glucose), iodine (water), iodine (creatinine), iodine (glucose), glucose (iodine), glucose (water) and glucose (creatinine).

[0133] Quantitative analysis of the images recorded attenuation values ​​of 11 unenhanced VMIs and corresponding material density measurements in mg / ml for 12 material pairs. All measurements were performed by placing circular or elliptical regions of interest (ROIs) to cover the fluid or cyst area as comprehensively as possible (mean ROI area was 5.9 cm 2 , range 2-9cm 2 During the measurement process, the ROI does not contain pixels outside the lesion (such as Figure 2 As shown, Figure 2 A and Figure 2 B are schematic diagrams of ROIs of renal cysts and hydronephrosis, respectively). From the VMIs, this embodiment calculates four DECT indices: dual energy index (DEI), dual energy ratio (DER), dual energy difference (DED) and Lambda, and uses a specific formula for calculation, as follows:

[0134] DEI = HU40kev / U140kev;

[0135] DER=(HU40kev-HU140kev) / (HU40kev+HU140kev+2000);

[0136] DED = HU80kev - HU140kev;

[0137] Lamda=(HU40kev-HU70kev) / 30.

[0138] 5. Statistical analysis.

[0139] Categorical variables were expressed as frequencies and percentages and compared using the chi-square test. Continuous variables were reported as mean ± standard deviation (SD) or median (1st quartile, 4th quartile) and compared using the Student's t test or Mann-Whitney U test, respectively, depending on the normality of the data distribution. Clinical data and DECT parameters in the training and validation sets were tested for differences.

[0140] 5.1RS build.

[0141] In order to solve the potential multicollinearity problem, this embodiment uses the least absolute shrinkage and selection operator (LASSO) regression analysis to identify the best variables with the highest predictive performance, thereby improving the simplicity and robustness of the model. Therefore, this embodiment constructs a RS scoring model of LASSO regression based on multiple DECT parameters. In order to evaluate the predictive performance and stability of the RS scoring model, this embodiment calculates the AUC values ​​of the training set and the validation set.

[0142] 5.2 Construction of nomogram prediction model.

[0143] In the training set, univariate logistic regression analysis was performed on the clinical data and RS of all patients to identify variables with a P value < 0.05. These variables were then included in multivariate logistic regression analysis to further identify the final predictors (clinical symptoms and RS with a P value < 0.05) for distinguishing renal cysts from hydronephrosis. Based on the above predictors, a nomogram model was constructed to infer the probability of cysts according to the scores obtained from the values ​​of the included variables. The predictive performance of the nomogram model was evaluated by ROC curve analysis, calibration curve (CC) analysis, and decision curve (DCA) analysis to assess the accuracy and clinical applicability of the model. To improve the robustness and wide applicability of the model, the nomogram model was also validated in a separate validation set. All statistical analyses were performed using R software (version 4.2.1), and P values ​​< 0.05 were considered statistically significant.

[0144] 6. Results.

[0145] 6.1 Study population and variables

[0146] A total of 146 patients were included in this example, of which 78 had renal cysts and 68 had hydronephrosis. According to a 7:3 ratio, 102 patients (70%; including 55 patients with renal cysts and 47 patients with hydronephrosis) were assigned to the training set, and 44 patients (30%; including 23 patients with renal cysts and 21 patients with hydronephrosis) were assigned to the validation set. Detailed instructions for participant screening process and study steps Figure 3 .

[0147] As shown in Table 1, there were no significant differences in baseline characteristics, DECT parameters, and laboratory test indicators between the training set and the validation set (P>0.05). The similarity of baseline data indicates that patients in the training set and validation set have the same distribution of key characteristics, which enhances the wide applicability of the model, improves the reliability of the evaluation results, and minimizes the impact of confounding factors.

[0148] Table 1 Comparison of variables in the training set and validation set

[0149]

[0150]

[0151]

[0152] Among them, MONO70-MONO140 represents the CT value (HU) at 40-140kev.

[0153] 6.2 Construction of RS model.

[0154] As shown in Table 2, the DECT parameters between the hydronephrosis group and the renal cyst group in the training set, including the monochromatic CT values ​​from 40keV to 140keV, the basic substance concentration, DER, DED, DEI, Lambda, and Zeff, all showed significant differences (all P values ​​< 0.001). In the ROC analysis, the CT values ​​of 60keV and 70keV showed the highest AUC values, both of which were 0.882, indicating that these DECT parameters have a high recognition potential in distinguishing hydronephrosis from renal cysts.

[0155] Table 2 Comparison of DECT parameters in the training set

[0156]

[0157]

[0158] The 28 variables were subjected to univariate logistic regression analysis, and variables with a P value less than 0.05 were included in the LASSO regression (e.g. Figure 4 Finally, three variables were identified: iodine (creatinine), DER and MONO70. The corresponding logistic regression model was established as follows Figure 4 shown. Figure 4 Variable selection was performed using LASSO regression analysis and 10-fold cross validation.

[0159] RS = 0.249 + 0.373 × Iodine (Creatinine) + 0.361 × DER + 1.911 × MONO70. The RS model is a reliable predictor in the training set ( Figure 5 A) and validation set ( Figure 5 In B), an AUC value of 0.883 was obtained, showing good prediction performance.

[0160] Figure 5 The instructions are as follows:

[0161] ROC curves of the RS model in the training set (A) and validation set (B), and ROC curves of the nomogram model in the training set (C) and validation set (D).

[0162] 6.3 Construction and verification of the nomogram model.

[0163] Table 3 shows the clinical data and DECT parameters of the two groups of patients. The mean age (p = 0.041), glucose (Glu) level (p = 0.008), and urea level (p = 0.039) in the renal cyst group were significantly higher than those in the hydronephrosis group. In contrast, the proportion of patients with symptoms in the hydronephrosis group was significantly higher (p < 0.001). In addition, there were significant differences between the two groups in the incidence of different renal sites (location: left, right, bilateral) (P = 0.029). Left-sided hydronephrosis was more common, while renal cysts more often affected both kidneys. Importantly, no significant differences were found in gender, blood protein concentration, sodium, potassium, and creatinine blood concentrations (p > 0.05).

[0164] Table 3 Clinical and hematological indicators of hydronephrosis and renal cysts in the training set

[0165]

[0166] The variables RS, age, location, symptoms, glucose, and urea were included in the univariate logistic regression analysis, and the variables with P < 0.05 were further included in the multivariate logistic regression analysis (Table 4). The analysis identified two indicators as independent predictors: symptoms (OR = 0.003, 95% CI: 0-0.028) and RS (OR = 2.953, 95% CI: 1.784-6.134). A nomogram model was established based on symptoms and RS, and the independent risk factors identified by multivariate analysis were used to identify hydronephrosis and renal cysts ( Figure 5 The model has high discrimination ability, with an AUC value of 0.980 (95% CI: 0.956-1.000) for the training set ( Figure 5 The AUC value of the validation set was 0.974 (95% CI: 0.937-1.000) ( Figure 5 D). The nomogram model is a graphical representation, such as Figure 6 As shown; calibration curve ( Figure 7 ) shows that the model has good accuracy and stability. In addition, Figure 8 Decision curves for the training and validation sets are shown separately, illustrating that the nomogram provides a superior net benefit.

[0167] Table 4 Univariate and multivariate logistic regression analysis

[0168]

[0169] The dual-energy CT (DECT) used in this embodiment has a significant advantage in recognition accuracy compared to traditional ultrasound and enhanced CT. Ultrasound often misdiagnoses perirenal cysts as hydronephrosis during diagnosis, with a false positive rate of between 11% and 26%. Related technology points out that traditional CT often ignores the subtle differences between these lesions due to the use of mixed energy imaging. For patients with renal insufficiency or iodine allergy, conventional CT or more expensive magnetic resonance imaging may be a viable option. DECT's non-enhanced scanning mode effectively replaces traditional ordinary scans, reduces radiation exposure and simplifies the examination process. DECT provides a range of parameters, such as virtual monochrome images (VMI), Zeff, Lambda, and material decomposition technology, making it a powerful alternative to enhanced CT.

[0170] VMI in DECT can reduce artifacts, solve the problem of CT value drift, provide accurate CT values, better image quality, and higher signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Research on related technologies has found that 70keV virtual monochrome images are similar to traditional 120kVp images, but with less noise and better clarity. Through LASSO regression, the 70keV monochrome CT value was determined to be an important parameter associated with distinguishing renal cysts from hydronephrosis. DECT can also generate measurements such as dual energy ratio (DER) to help analyze other lesions such as urinary stones. This example shows that DER is a key factor in distinguishing renal cysts from hydronephrosis, surpassing the analysis of a single CT value difference.

[0171] DECT's material decomposition technology can effectively characterize material density, perform high-precision identification, distinguish uric acid stones from other types of stones, and quantify liver iron reserves. Renal cysts usually contain clear fluid with low protein and electrolyte content, while hydronephrosis is caused by urinary tract obstruction, the fluid composition is more complex, the electrolyte content is higher, and it may be accompanied by infection. The study found that there were significant differences in electrolyte, glucose and protein content between renal cyst fluid and hydronephrosis fluid, which prompted this embodiment to select glucose, creatinine and water as basic materials for paired analysis. This embodiment also includes iodine as one of the basic materials because iodine is often used in DECT material decomposition images. Finally, the study of this embodiment found that iodine (creatinine) images, as an important parameter for distinguishing renal cysts from hydronephrosis, are different from the more commonly used iodine (water) images and may become a key parameter for identification using DECT image markers.

[0172] Most patients with renal cysts are discovered during physical examinations and usually have no obvious symptoms. However, in a few cases, cysts may compress adjacent structures, leading to problems such as obstruction of the ureteropelvic junction. Patients with hydronephrosis usually seek medical attention for low back pain or urinary tract symptoms caused by obstruction. In the two patient groups in this embodiment, multivariate logistic regression analysis was used to find that RS scores and clinical symptoms were significant variables (P<0.05). Although the relevant technology also noted the differences in urinary tract symptoms between the renal cyst and hydronephrosis groups, the confirmation of these findings was challenging due to the small sample size, and the symptoms were not included in the comprehensive analysis. Therefore, clinical symptoms including rib pain and urinary tract symptoms were considered in this embodiment to minimize potential errors. Among patients with renal cysts, approximately 19% of patients (15-78) showed symptoms, while 97% of patients with hydronephrosis (66-68) had symptoms.

[0173] This embodiment is a single-center retrospective analysis with a limited sample size. To improve the wide applicability of the model, multicenter data and a larger sample size can be included for external validation to enhance the robustness of the model. In addition, this embodiment can also integrate more complex machine learning algorithms to achieve a more efficient identification accuracy rate.

[0174] This embodiment constructs the RS model by 70keV, DER and iodine (creatinine). In addition, by combining the patient's symptom indicators, the AUC of the obtained nomogram model in the validation set reaches 0.97, so this embodiment improves the recognition accuracy of patients who cannot undergo iodine enhancement examination.

[0175] Reference Fig. 9 The embodiment of the present application also provides a device for identifying a renal cyst and hydronephrosis, which can implement the above-mentioned method for identifying a renal cyst and hydronephrosis. The device includes:

[0176] A data acquisition unit, used for acquiring clinical data and DECT images of different patients;

[0177] a parameter determination unit, configured to determine a DECT parameter according to each of the DECT images;

[0178] A first model building unit, configured to build a radiological scoring model according to the DECT parameters;

[0179] a symptom determination unit, configured to determine clinical symptoms of each of the patients according to the clinical data;

[0180] A second model building unit is used to build a nomogram model according to the radiological scoring model and the clinical symptoms;

[0181] The identification unit is used to identify whether each of the DECT images is a renal cyst or hydronephrosis according to the nomogram model.

[0182] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0183] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned method for identifying renal cysts and hydronephrosis when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0184] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0185] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0186] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0187] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes a method for identifying a renal cyst and hydronephrosis in the embodiments of this application;

[0188] Input / output interface 1003, used to implement information input and output;

[0189] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0190] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0191] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0192] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for identifying renal cysts and hydronephrosis.

[0193] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0194] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0195] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0196] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0197] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0198] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0199] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0200] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0201] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0202] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0203] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0204] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0205] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for identifying renal cysts and hydronephrosis, characterized in that: The method comprises the following steps: Obtain clinical data and DECT images of different patients; Determining DECT parameters according to each of the DECT images; constructing a radiomic scoring model according to the DECT parameters; Determining the clinical symptoms of each of the patients according to the clinical data; Constructing a nomogram model according to the radiological scoring model and the clinical symptoms; According to the nomogram model, it is identified whether each of the DECT images is a renal cyst or hydronephrosis.

2. A method for identifying renal cysts and hydronephrosis according to claim 1, characterized in that: Determining the DECT parameters according to each of the DECT images comprises the following steps: Reconstructing virtual monochrome images of different energies according to each of the DECT images; Determining an effective atomic number based on each of the DECT images; determining different material pair images according to each of the DECT images; Calculating the DECT index of each of the virtual monochrome images according to each of the DECT images; The virtual monochrome image, the effective atomic number, the material pair image and the DECT index serve as the DECT parameters.

3. A method for identifying renal cysts and hydronephrosis according to claim 2, characterized in that: The process of reconstructing virtual monochrome images of different energies according to the DECT images comprises the following steps: The virtual monochrome images with energy ranging from 40keV to 140keV and intervals of 10keV are reconstructed according to the DECT images.

4. A method for identifying renal cysts and hydronephrosis according to claim 2, characterized in that: Determining different material pair images according to each of the DECT images comprises the following steps: The substance pair images reconstructed according to each of the DECT images include: creatinine-iodine, creatinine-water, creatinine-glucose, water-iodine, water-creatinine, water-glucose, iodine-water, iodine-creatinine, iodine-glucose, glucose-iodine, glucose-water and glucose-creatinine.

5. A method for identifying renal cysts and hydronephrosis according to claim 2, characterized in that: The step of calculating the DECT index of each of the virtual monochrome images according to each of the DECT images comprises the following steps: Calculate the dual energy index, dual energy ratio, dual energy difference and Lambda of each of the virtual monochrome images according to each of the DECT images as the DECT index; The calculation formula of the dual energy index is: DEI = HU40kev / HU140kev; Wherein, DEI represents the dual energy index; HU represents the CT attenuation value; kev represents the energy unit; The calculation formula of the dual energy ratio is: DER=(HU40kev-HU140kev) / (HU40kev+HU140kev+2000); Wherein, DER represents the dual energy ratio; The calculation formula of the dual energy difference is: DED = HU80kev - HU140kev; Wherein, DED represents the dual energy difference; The calculation formula of Lambda is: Lamda=(HU40kev-HU70kev) / 30; Herein, Lamda represents the Lambda.

6. A method for identifying renal cysts and hydronephrosis according to claim 1, characterized in that: The method of constructing a radiological scoring model according to the DECT parameters comprises the following steps: The radiological scoring model was constructed according to the DECT parameters as follows: 0.249+0.373*iodine-creatinine+0.361*DER+1.911*MONO70; Among them, DER means dual energy ratio; MONO70 means the CT value of dual energy CT at 70kev.

7. A method for identifying renal cysts and hydronephrosis according to any one of claims 1 to 6, characterized in that: The method of constructing a nomogram model according to the radiological scoring model and the clinical symptoms comprises the following steps: Performing univariate logistic regression analysis on the radiological scoring model and the clinical symptoms, thereby identifying several variables with probability values ​​less than a set threshold; Performing multivariate logistic regression analysis on each of the variables, thereby identifying predictors with probability values ​​less than the set threshold; The nomogram model is constructed according to the predictive factors.

8. A device for identifying renal cysts and hydronephrosis, characterized in that: The device comprises: A data acquisition unit, used for acquiring clinical data and DECT images of different patients; a parameter determination unit, configured to determine a DECT parameter according to each of the DECT images; A first model building unit, configured to build a radiological scoring model according to the DECT parameters; a symptom determination unit, configured to determine clinical symptoms of each of the patients according to the clinical data; A second model building unit is used to build a nomogram model according to the radiological scoring model and the clinical symptoms; The identification unit is used to identify whether each of the DECT images is a renal cyst or hydronephrosis according to the nomogram model.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images