Hepatoma extrahepatic metastasis prediction model based on radiomics and construction method and application thereof
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A radiomics, metastasis prediction technology, applied in neural learning methods, biological neural network models, informatics, etc., to improve performance and achieve the effect of individualized and precision medicine
Pending Publication Date: 2021-10-26
THE AFFILIATED HOSPITAL OF QINGDAO UNIV
View PDF0 Cites 1 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] Aiming at the technical problem that a mature and effective model for predicting extrahepatic metastasis of liver cancer based on radiomics methods has not been developed in the prior art, the present invention proposes a high-precision radiomics-based prediction model for extrahepatic metastasis of liver cancer. Construction method and application
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0081] This embodiment proposes a radiomics-based method for establishing a prediction model for extrahepatic metastasis of liver cancer, including the following steps:
[0082] (1) 277 patients who were pathologically confirmed as hepatocellular carcinoma and underwent liver resection were included as a data set, and they were randomly divided into a training group (n=193) and a validation group (n=84) according to a ratio of 7:3. );
[0083] (2) Collect the original medical images and clinical information of patients with liver cancer treated by hepatectomy, and extract 1130 imaging features from the CT images of each patient, that is, the preliminary radiomics features, of which 1130 imaging features Features include: first-order statistical features, morphological features, gray-scale co-occurrence matrix features (GLCM), gray-scale run-length features (GLRLM), gray-scale region size matrix features (GLSZM), gray-scale dependency matrix features (GLDM), wavelet Change fea...
Embodiment 2
[0092] This embodiment proposes a method for constructing a clinical model and a joint model, including the following steps:
[0093] (1) Univariate analysis was used to determine the impact of clinical characteristics on prognosis of patients with extrahepatic metastasis of liver cancer, and the clinical characteristics with p<0.05 were selected for multivariate regression analysis, and three clinical characteristics were determined through univariate analysis, namely body mass index (BMI ), neutrophil count (NEUT) and t stage, two qualitative imaging features, namely tumor diameter, MVI and Radscore (all P<0.05);
[0094] (2) Multivariate logistic regression analysis was performed on the above clinical characteristics and imaging qualitative characteristics. The analysis showed that tumor diameter (OR 0.721 [95% CI, 0.542-0.959)], P=0.025), t stage (P<0.0001) and radiomics score (OR, 1.618e6[95CI, 17.438-3.666e10], P=0.005) were independent predictors of liver cancer;
[00...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention provides a hepatoma extrahepatic metastasis prediction model based on radiomics and a construction method and application thereof, and can solve the technical problem that a mature and effective hepatoma extrahepatic metastasis prediction model based on a radiomics method is not developed in the prior art. The construction method comprises the following steps: acquiring an original medical image and clinical information; randomly dividing liver cancer patients into a training set and a verification set in proportion; extracting a preliminary image omics feature; the LASSO regression model carries out dimensionality reduction and screening on the preliminary image omics features in the training set to obtain first target image omics features, and the first target image omics features are utilized to construct various classifier models; using an SMOTE algorithm to amplify the first target image omics features to obtain amplified image omics feature data; carrying out dimensionality reduction by using an LASSO regression model and an RFC-RFE algorithm, screening the amplified image omics feature data, obtaining a second target image omics feature, constructing a plurality of classifier models by using the second target image omics feature, and calculating an image score; and evaluating the classifier models to select out the optimal classifier model through screening.
Description
technical field [0001] The invention belongs to the field of constructing a prediction model for extrahepatic metastasis of liver cancer, and in particular relates to a prediction model for extrahepatic metastasis of liver cancer based on radiomics, a construction method and an application thereof. Background technique [0002] Hepatocellular carcinoma (HCC) is currently the fourth most common cancer and the second leading cause of cancer-related death worldwide. Studies have reported that 13.5-42% of patients have extrahepatic metastasis at the time of diagnosis, and patients with extrahepatic recurrence often receive systemic chemotherapy or targeted therapy, and their survival rate is much lower than that of patients without extrahepatic metastasis. Recent studies have shown that actively dealing with extrahepatic metastases may improve the survival rate of patients. Therefore, identification of high-risk groups for extrahepatic metastases is an important issue to improve...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more