CN114266774A - Method, equipment and system for diagnosing pulmonary embolism based on flat-scan CT image - Google Patents
Method, equipment and system for diagnosing pulmonary embolism based on flat-scan CT image Download PDFInfo
- Publication number
- CN114266774A CN114266774A CN202210200366.8A CN202210200366A CN114266774A CN 114266774 A CN114266774 A CN 114266774A CN 202210200366 A CN202210200366 A CN 202210200366A CN 114266774 A CN114266774 A CN 114266774A
- Authority
- CN
- China
- Prior art keywords
- image
- flat
- scan
- pulmonary embolism
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention relates to a method, equipment and a system for diagnosing pulmonary embolism based on a flat-scan CT image. The method comprises the following steps: acquiring a flat scanning CT image of the lung of a patient to be diagnosed; performing three-dimensional reconstruction on the lung flat scanning CT image to obtain whole lung imaging; carrying out feature extraction on the whole lung imaging to obtain a feature vector; and inputting the characteristic vector into a trained machine learning model to obtain a pulmonary embolism diagnosis classification result of the patient to be diagnosed. The invention provides a novel non-invasive acute pulmonary embolism detection method for patients who do not have CTPA or have a contraindication of CTPA examination in clinic, and has important clinical application value.
Description
Technical Field
The invention relates to the technical field of intelligent medical treatment, in particular to a method, equipment, a system and a storage medium for diagnosing pulmonary embolism based on a flat-scan CT image.
Background
Acute pulmonary thromboembolism (APE) is a high incidence of cardiovascular disease, and severe cases can lead to acute right heart failure and even sudden death. Because of the non-specificity of clinical symptoms and signs, pulmonary artery CT angiography (CTPA) is a protocol for definitive diagnosis of APE, used to guide the diagnosis and severity assessment of APE. Although the method is a first-line noninvasive detection method for CTPA APE, not all people are suitable for CTPA examination, especially high risk group with unstable hemodynamics, patients with renal insufficiency or patients allergic to iodine contrast agent, and the like, and the CTPA cannot be used for diagnosing pulmonary embolism detection, thereby causing blindness of pulmonary embolism treatment. Compared with CTPA, contrast medium is not needed in chest flat-scan CT, but clinicians generally consider that APE cannot be effectively diagnosed in flat-scan CT and images of flat-scan CT do not have the value of APE diagnosis. At present, no good clinical solution is provided for patients who need noninvasive APE detection in clinical critical patients, contrast medium allergy patients and renal insufficiency patients.
Disclosure of Invention
In order to solve the problems, a flat-scan CT image which is discarded by a clinician and is considered to have no APE diagnostic value is adopted again, and imaging omics and machine learning algorithm modeling are combined to establish a method, equipment, a system and a storage medium for diagnosing pulmonary embolism based on the flat-scan CT image, so that a brand-new, rapid and noninvasive evaluation method is provided for patients who do not have CTPA detection conditions or have CTPA imaging contraindications clinically.
The application discloses a method for diagnosing pulmonary embolism based on flat scan CT image, comprising the following steps:
step 1: acquiring a flat scanning CT image of the lung of a patient to be diagnosed;
step 2: and carrying out three-dimensional reconstruction on the lung flat scanning CT image to obtain whole lung imaging. Preferably, each whole lung image is geometrically transformed into an image containing 36 subregions;
and step 3: carrying out feature extraction on the whole lung imaging to obtain a feature vector;
and 4, step 4: inputting the feature vector into a trained machine learning model
And obtaining the pulmonary embolism diagnosis classification result of the patient to be diagnosed.
Further, the method further includes performing ROI segmentation on the whole lung image to obtain a segmented whole lung image including N (N is a natural number, preferably, N is 36) sub-regions, and performing feature extraction on the N sub-regions in the whole lung image to obtain feature vectors;
optionally, the ROI segmentation on the whole lung imaging is automatically performed based on a deep learning segmentation method; preferably, the ROI segmentation for whole lung imaging is performed automatically by medical imaging software.
Further, the feature extraction is to perform feature extraction after filtering each sub-region in the whole lung imaging by adopting different filters respectively to obtain different types of image omics features as feature vectors;
optionally, the different categories of the imagery omics features include first-order statistics, 3D shape-based features, a gray level co-occurrence matrix, a gray level run length matrix, a gray level size region matrix, an adjacent gray level hue difference matrix, and a gray level dependency matrix.
Further, the method further comprises the steps of carrying out feature fusion on the obtained feature vectors, wherein the feature fusion is the feature fusion of each feature vector in N (preferably 36) sub-region feature vectors;
optionally, the feature fusion is a feature fusion in which 10 common statistics are selected from N (preferably 36) sub-region feature vectors for each feature vector;
optionally, the feature fusion is a feature fusion of the image omics features of different categories (preferably 7 categories) in N (preferably 36) sub-region feature vectors, and optionally, the feature fusion is a feature fusion of 10 common statistics selected from the N (preferably 36) sub-region feature vectors for the image omics features of different categories (preferably 7 categories).
Further, the step 3 further includes performing feature dimension reduction on the obtained feature vector, where the feature dimension reduction is performed according to a P value, a correlation coefficient, and a Least Absolute Shrinkage and Selection Operator (LASSO) regression; optionally, the feature dimensionality reduction is to perform feature sorting according to a P value, screen and retain features ranked in the top, calculate correlation coefficients between the screened features, delete features with larger P values in a feature group with larger correlation coefficients, and select features with nonzero coefficients from the retained features as feature vectors after dimensionality reduction by adopting LASSO regression.
Further, the lung flat-scan CT image adopts flat-scan CT to scan the head and the tail of the whole chest of a patient to be diagnosed from the lung tip to diaphragm muscle;
optionally, the lung flat-scan CT image is preprocessed, and preferably, the preprocessing includes performing any one or more of graying, geometric transformation, and image enhancement on the lung flat-scan CT image.
Further, the machine learning model is selected from one or more of the following machine learning model algorithms: logistic regression algorithm, naive Bayes classification, support vector machine, k neighbor, decision tree, random forest, xgboost, perception machine algorithm and logistic regression; preferably, the decision tree is a gradient boosting decision tree.
An object of the present application is to provide a system for diagnosing pulmonary embolism based on flat scan CT image, comprising:
the flat-scan CT image acquisition unit is used for acquiring a flat-scan CT image of the lung of a patient to be diagnosed;
the whole lung imaging unit is used for carrying out three-dimensional reconstruction on the lung flat scanning CT image to obtain whole lung imaging;
the characteristic extraction unit is used for carrying out characteristic extraction on the whole lung imaging to obtain a characteristic vector;
and the pulmonary embolism diagnosis unit is used for inputting the feature vector into a trained machine learning model to obtain a pulmonary embolism diagnosis classification result of the patient to be diagnosed.
An object of the present application is to provide an apparatus for diagnosing pulmonary embolism based on flat scan CT image, comprising: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke program instructions that, when executed, implement the pathological image classification method steps described above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method steps for diagnosing a pulmonary embolism based on a flat-scan CT image.
The application has the advantages that:
1. the method for diagnosing the pulmonary embolism based on the flat-scan CT image is established by adopting the flat-scan CT image which is considered by a clinician to have no APE diagnostic value and combining the image omics characteristics of the pulmonary image and machine learning algorithm modeling;
2. the application creatively provides a novel noninvasive detection method for patients without CTPA detection conditions clinically, the method can be used for diagnosing APE (acute respiratory syndrome) under the real emergency condition by using chest CT (computed tomography) flat scan assistance, and research results show that the method is obviously superior to the visual evaluation of radiologists with different clinical experiences.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart illustrating a method for diagnosing pulmonary embolism based on flat-scan CT image according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an apparatus for diagnosing pulmonary embolism based on flat-scan CT image according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a system for diagnosing pulmonary embolism based on flat-scan CT images according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of full lung imaging and sub-region segmentation based on flat-scan CT images according to an embodiment of the present invention;
fig. 5 is a schematic diagram of feature fusion provided by an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
In some of the flows described in the present specification and claims and in the above figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, with the order of the operations being indicated as 101, 102, etc. merely to distinguish between the various operations, and the order of the operations by themselves does not represent any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for diagnosing pulmonary embolism based on a flat-scan CT image, which includes the following steps:
101: acquiring a flat scanning CT image of the lung of a patient to be diagnosed;
in one embodiment, the acquired pathological image is preprocessed, and the preprocessing comprises any one or more of graying, geometric transformation, resizing and image enhancement of the pathological image.
In one embodiment, the flat-scan CT images of the lungs are head-to-tail scanned using flat-scan CT over the entire chest of the patient to be diagnosed, from the apex of the lung to the diaphragm.
In ONE embodiment, the NC-CT is obtained in a head-to-tail orientation using a multi-detector CT scanner (Toshiba Aquillion ONE TSX-301C/320, Tokyo, Japan; Philips iCT/256, the Netherlands; Siemens sensing/16, Germany). During one breath-hold, a cranio-caudal scan was performed of the entire chest from the apex of the lung to the lowest diaphragm. The scan parameters were as follows: the tube voltage is 100-120 kVp, the tube current is 100-300 mAs, the slice thickness is 1.25-2.50 mm, the worktable speed is 39.37 mm/s, and the frame rotation time is 0.8 s.
102: performing three-dimensional reconstruction on the lung flat scanning CT image to obtain whole lung imaging;
in a specific embodiment, NC-CT images are taken 1X 1 mm3Equidistant sampling and windowing with a window width of-600 HU and 1500 windows.
103: carrying out feature extraction on the whole lung imaging to obtain a feature vector;
in one embodiment, the method further includes performing ROI segmentation on the whole lung image to obtain a segmented whole lung image including N (N is a natural number, preferably 36) sub-regions, and performing feature extraction on the N sub-regions in the whole lung image to obtain feature vectors. Optionally, the ROI segmentation for whole lung imaging is performed automatically based on a deep learning segmentation method.
In one embodiment, the ROI segmentation for full Lung imaging is performed automatically by Medical imaging software, which is commercially available Medical imaging software such as InferReadTM CT Lung, version R3.12.3, Infervision Medical Technology Co., Ltd, segmented into 36 sub-regions, as shown in FIG. 4.
In one embodiment, the feature extraction is to perform feature extraction after filtering each sub-region in the whole lung imaging by using different filters, so as to obtain different categories of imagery omics features as feature vectors. Optionally, the different categories of imagery omics features include first order statistics, 3D shape-based features, gray level co-occurrence matrix (GLCM), Gray Level Run Length Matrix (GLRLM), gray level size region matrix (GLSZM), adjacent gray level hue difference matrix (NGTDM), and Gray Level Dependency Matrix (GLDM).
In a specific embodiment, feature extraction is performed on the N sub-regions in the whole lung imaging, and specifically, an image omics feature is extracted in a Python environment by using an open source software package named PyRadiomics (version 3.0.1; https:// radiomics. And respectively performing feature extraction on each sub-region in the whole lung imaging by adopting two groups of filtering operations (including Laplacians of Gaussians (LoG) and Wavelet decomplexions) to obtain image omics features of 7 categories as feature vectors. Optionally, the 7 categories of omics features include first-order statistics, 3D shape-based features, gray level co-occurrence matrix (GLCM), Gray Level Run Length Matrix (GLRLM), gray level size region matrix (GLSZM), adjacent gray level hue difference matrix (NGTDM), and Gray Level Dependency Matrix (GLDM). 1004 imagery omic features were extracted from each ROI segmentation, including 187 first-order statistical features, 14 three-dimensional shape features, 253 GLCM features, 176 GLRLM features, 165 GLSZM features, 55 NGTDM features, and 154 GLDM features.
In one embodiment, the method further comprises performing feature fusion on the obtained feature vectors, wherein the feature fusion is the feature fusion of each feature vector in the N sub-region feature vectors; optionally, the feature fusion is the feature fusion of the image omics features of different classes (7 large classes) in the feature vectors of the N sub-regions.
In one embodiment, 1004 features are extracted for each sub-region, features are extracted for 36 regions, 1004 × 36 features are obtained, and the features are counted by using 10 common statistics, wherein each statistic changes 1004 × 36 features into 1004 × 1 features, and 10 statistics are 1004 × 1 × 10 features.
In one embodiment, and referring specifically to fig. 5, for whole lung imaging, each of the 1004 imagery omic features is effectively considered a feature vector, i.e., fj = [ fj (r1, fj (r 2........ times., fj (r 36))]. Such a feature vector has a dimension of at most 36, taking into account data of a lung resection patient. To directly reverseMapping the distribution of these omics features in the pulmonary map imaging, ten common statistics were calculated for each feature vector, including maximum (s 1= max (fj)), minimum (s 2= min (fj)), median (s3= median (fj)), 10 th percentile (s4= percentile (fj,10)), 90 th percentile (s5= percentile (fj,90)), mean (s6= mean (fj)), standard deviation (s7= std (fj)), quartile distance (s8= percentile (fj,75) -percentile (fj,15)), skewness (s9= skew (fj)), and peak (s10= kurt (fj)). The final pulmonary proteomics descriptor vector v is defined as a concatenation of ten statistical data for each proteomics feature, i.e., v = [ s (f1) | s (f2) |. | | | s (f36); s = (s1, s2,. ·, s36)]. After this concatenation, v ∈ ℝ10040。
In one embodiment, the method further comprises performing feature dimension reduction on the obtained feature vector, wherein the feature dimension reduction is performed according to a P value, a correlation coefficient and LASSO regression; optionally, the feature dimensionality reduction is to perform feature sorting according to a P value, screen and retain features ranked in the top, calculate correlation coefficients between the screened features, delete features with larger P values in a feature group with larger correlation coefficients, and select features with nonzero coefficients from the retained features as feature vectors after dimensionality reduction by adopting LASSO regression.
In one embodiment, the Mann-Whitney U test was first used to perform a significance analysis on all features in the pulmonary imaging omics descriptor. These features are sorted according to the ascending p-value, leaving the top 1% of the sorted features for subsequent analysis. Then, a Pearson correlation coefficient (r) between each pair of remaining features is calculated. All pairs of features with | r | are filtered >0.85, and features in each of these pairs with larger p-values from the MannWhitney U test are deleted from the feature set. Finally, minimum absolute shrinkage with quintupling cross validation and selection operator (LASSO) regression is applied to select features with non-zero coefficients from the retained features for APE prediction.
104: and inputting the characteristic vector into a trained machine learning model to obtain a pulmonary embolism diagnosis classification result of the patient to be diagnosed.
In one embodiment, the machine learning model is selected from one or more of the following machine learning model algorithms: a logistic regression algorithm, naive Bayes classification, a support vector machine, k neighbors, a decision tree, a random forest, a gradient boosting decision tree, a perceptron algorithm and logistic regression; preferably, the decision tree is a gradient boosting decision tree.
In one embodiment, using the reduced-dimension features as inputs, eight common machine learning models, including na iotave bayes, logistic regression, nearest neighbor, random forest, decision tree, gradient boosting decision tree, support vector machine, and multi-layered perceptron, are selected and installed on the training set. Triple cross-validation is performed on the training set to determine the best hyper-parameters for each model and to select the best model. And selecting the area under the working characteristic curve (AUC) of the subject as the standard of the model performance evaluation.
Fig. 2 is a device for diagnosing pulmonary embolism based on a flat-scan CT image, which includes: a memory and a processor;
the memory is to store program instructions;
the processor is configured to invoke program instructions that, when executed, implement the method steps for diagnosing pulmonary embolism based on flat-scan CT images described above.
Fig. 3 is a system for diagnosing pulmonary embolism based on flat-scan CT image, which includes:
a flat-scan CT image obtaining unit 301, configured to obtain a flat-scan CT image of a lung of a patient to be diagnosed;
a whole lung imaging unit 302, configured to perform three-dimensional reconstruction on the lung flat scan CT image to obtain a whole lung image;
a feature extraction unit 303, configured to perform feature extraction on the whole lung imaging to obtain a feature vector;
and the pulmonary embolism diagnosis unit 304 is configured to input the feature vector into a trained machine learning model to obtain a pulmonary embolism diagnosis classification result of the patient to be diagnosed.
It is an object of the invention to provide a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the above-mentioned method steps for diagnosing a pulmonary embolism based on a flat-scan CT image.
The validation results of this validation example show that assigning an intrinsic weight to an indication can moderately improve the performance of the method relative to the default settings.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by hardware that is instructed to implement by a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
While the invention has been described in detail with reference to specific embodiments thereof, it will be apparent to one skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A method for diagnosing pulmonary embolism based on flat-scan CT image, the method comprising:
step 1: acquiring a flat scanning CT image of the lung of a patient to be diagnosed;
step 2: performing three-dimensional reconstruction on the lung flat scanning CT image to obtain whole lung imaging;
and step 3: carrying out feature extraction on the whole lung imaging to obtain a feature vector;
and 4, step 4: and inputting the characteristic vector into a trained machine learning model to obtain a pulmonary embolism diagnosis classification result of the patient to be diagnosed.
2. The method for diagnosing pulmonary embolism based on flat-scan CT image as claimed in claim 1, wherein the method further comprises performing ROI segmentation on the whole lung imaging to obtain a segmented whole lung imaging including N sub-regions, where N is a natural number, and performing feature extraction on the N sub-regions in the whole lung imaging to obtain a feature vector.
3. The method for diagnosing pulmonary embolism based on the flat-scan CT image as claimed in claim 2, wherein the feature extraction is to perform feature extraction on each sub-region in the whole lung imaging by using different filters, so as to obtain different categories of imagery group features as feature vectors.
4. The method for diagnosing pulmonary embolism based on flat-scan CT image as recited in claim 3, further comprising feature fusion of the obtained feature vectors, wherein the feature fusion is the feature fusion of each feature vector in N sub-region feature vectors.
5. The method for diagnosing pulmonary embolism based on flat-scan CT image as claimed in claim 1, wherein said step 3 further comprises performing feature dimension reduction on the obtained feature vector, wherein the feature dimension reduction is performed according to P value, correlation coefficient and least absolute shrinkage and LASSO regression.
6. The method for diagnosing pulmonary embolism based on the flat-scan CT image as recited in claim 1, wherein the flat-scan CT image of the lung is used for head-to-tail scanning of the whole chest of a patient to be diagnosed from the lung apex to diaphragm muscle by using flat-scan CT.
7. The method for diagnosing pulmonary embolism based on flat-scan CT image according to claim 1, wherein the machine learning model is selected from one or more of the following machine learning model algorithms: logistic regression algorithm, naive Bayes classification, support vector machine, k neighbor, decision tree, random forest, gradient boosting decision tree, perception machine algorithm and logistic regression.
8. A system for diagnosing pulmonary embolism based on flat-scan CT images, the system comprising:
the flat-scan CT image acquisition unit is used for acquiring a flat-scan CT image of the lung of a patient to be diagnosed;
the whole lung imaging unit is used for carrying out three-dimensional reconstruction on the lung flat scanning CT image to obtain whole lung imaging;
the characteristic extraction unit is used for carrying out characteristic extraction on the whole lung imaging to obtain a characteristic vector;
and the pulmonary embolism diagnosis unit is used for inputting the feature vector into a trained machine learning model to obtain a pulmonary embolism diagnosis classification result of the patient to be diagnosed.
9. An apparatus for diagnosing pulmonary embolism based on flat-scan CT image, the apparatus comprising: a memory and a processor;
the memory is to store program instructions;
the processor is adapted to invoke program instructions which, when executed, implement the pathological image classification method steps of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of diagnosing pulmonary embolism based on flat-scan CT-images according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210200366.8A CN114266774A (en) | 2022-03-03 | 2022-03-03 | Method, equipment and system for diagnosing pulmonary embolism based on flat-scan CT image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210200366.8A CN114266774A (en) | 2022-03-03 | 2022-03-03 | Method, equipment and system for diagnosing pulmonary embolism based on flat-scan CT image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114266774A true CN114266774A (en) | 2022-04-01 |
Family
ID=80833907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210200366.8A Pending CN114266774A (en) | 2022-03-03 | 2022-03-03 | Method, equipment and system for diagnosing pulmonary embolism based on flat-scan CT image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114266774A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783558A (en) * | 2022-04-25 | 2022-07-22 | 四川大学华西医院 | CTPA image report generation system for pulmonary embolism patients |
| CN114972296A (en) * | 2022-06-14 | 2022-08-30 | 中日友好医院(中日友好临床医学研究所) | High-resolution CT image analysis method, equipment and system based on lung map |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403201A (en) * | 2017-08-11 | 2017-11-28 | 强深智能医疗科技（昆山）有限公司 | Tumour radiotherapy target area and jeopardize that organ is intelligent, automation delineation method |
| CN112215799A (en) * | 2020-09-14 | 2021-01-12 | 北京航空航天大学 | Automatic classification method and system for grinded glass lung nodules |
| CN112819747A (en) * | 2019-10-31 | 2021-05-18 | 深圳市华嘉生物智能科技有限公司 | Method for automatically diagnosing benign and malignant nodules based on lung tomography image |
| CN113888532A (en) * | 2021-11-09 | 2022-01-04 | 推想医疗科技股份有限公司 | Medical image analysis method and device based on flat scanning CT data |
-
2022
- 2022-03-03 CN CN202210200366.8A patent/CN114266774A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403201A (en) * | 2017-08-11 | 2017-11-28 | 强深智能医疗科技（昆山）有限公司 | Tumour radiotherapy target area and jeopardize that organ is intelligent, automation delineation method |
| CN112819747A (en) * | 2019-10-31 | 2021-05-18 | 深圳市华嘉生物智能科技有限公司 | Method for automatically diagnosing benign and malignant nodules based on lung tomography image |
| CN112215799A (en) * | 2020-09-14 | 2021-01-12 | 北京航空航天大学 | Automatic classification method and system for grinded glass lung nodules |
| CN113888532A (en) * | 2021-11-09 | 2022-01-04 | 推想医疗科技股份有限公司 | Medical image analysis method and device based on flat scanning CT data |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114783558A (en) * | 2022-04-25 | 2022-07-22 | 四川大学华西医院 | CTPA image report generation system for pulmonary embolism patients |
| CN114972296A (en) * | 2022-06-14 | 2022-08-30 | 中日友好医院(中日友好临床医学研究所) | High-resolution CT image analysis method, equipment and system based on lung map |
| CN114972296B (en) * | 2022-06-14 | 2023-02-07 | 中日友好医院(中日友好临床医学研究所) | High-resolution CT image analysis method, equipment and system based on lung map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Niemeijer et al. | Information fusion for diabetic retinopathy CAD in digital color fundus photographs | |
| Gao et al. | Automatic feature learning to grade nuclear cataracts based on deep learning | |
| Shikata et al. | Automated segmentation of pulmonary vascular tree from 3D CT images | |
| Chawla et al. | A method for automatic detection and classification of stroke from brain CT images | |
| US7715608B2 (en) | System and method for 3D visualization of lung perfusion or density and statistical analysis thereof | |
| JP5081390B2 (en) | Method and system for monitoring tumor burden | |
| US6748044B2 (en) | Computer assisted analysis of tomographic mammography data | |
| DE102011013505B4 (en) | Method and system for the automatic detection and classification of coronary artery stenosis in cardiac CT volumes | |
| EP3701495B1 (en) | Tomographic data analysis | |
| Fernandes et al. | A novel fusion approach for early lung cancer detection using computer aided diagnosis techniques | |
| US10991460B2 (en) | Method and system for identification of cerebrovascular abnormalities | |
| CN109859168A (en) | A kind of X-ray rabat picture quality determines method and device | |
| CN114266774A (en) | Method, equipment and system for diagnosing pulmonary embolism based on flat-scan CT image | |
| JP2001137230A (en) | Computer aided diagnostic system | |
| US20050063579A1 (en) | Method of automatically detecting pulmonary nodules from multi-slice computed tomographic images and recording medium in which the method is recorded | |
| WO2021209887A1 (en) | Rapid, accurate and machine-agnostic segmentation and quantification method and device for coronavirus ct-based diagnosis | |
| CN109785320A (en) | It is a kind of to be classified to mammograms and known method for distinguishing using modified AlexNet model | |
| Yang et al. | A multi-stage progressive learning strategy for COVID-19 diagnosis using chest computed tomography with imbalanced data | |
| KR100998630B1 (en) | Method for automatic classifier of lung diseases | |
| CN114450716A (en) | Image processing for stroke characterization | |
| Garnavi et al. | A new segmentation method for lung HRCT images | |
| WO2020235461A1 (en) | Abnormality detection method, abnormality detection program, abnormality detection device, server device, and information processing method | |
| US20230316510A1 (en) | Systems and methods for generating biomarker activation maps | |
| JP2019536531A (en) | Apparatus for detecting opacity in X-ray images | |
| Ijaz et al. | Deep learning for pneumonia diagnosis using cxr images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |