CT radiomics-based pancreatic neuroendocrine tumor grading method

A technology of neuroendocrine and grading methods, applied in the field of tumor grading, can solve the problems of physical injury of patients, unfavorable treatment of patients, increase of diagnosis time, etc., and achieve the effect of relieving pain, shortening treatment time, and avoiding differences in diagnosis

Pending Publication Date: 2019-05-28
NANJING UNIV OF INFORMATION SCI & TECH
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the grading of pancreatic neuroendocrine tumors (PNET) in patients is mainly obtained through surgical pathological sections, but this method will cause damage to the patient's body, and will also increase the time of diagnosis, which is not conducive to timely treatment of patients

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
  • CT radiomics-based pancreatic neuroendocrine tumor grading method
  • CT radiomics-based pancreatic neuroendocrine tumor grading method
  • CT radiomics-based pancreatic neuroendocrine tumor grading method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Such as figure 1 As shown, the grading method of pancreatic neuroendocrine tumors based on CT radiomics of the present invention comprises the following steps:

[0021] (1) Radiologists performed abdominal CT scans on 99 PNET patients, and manually marked the PNET tumor areas;

[0022] (2) Extract radiomics features in each tumor area, including texture features Haralick, Laws, CoLlAGe, and wavelet features Gabor. Each feature contains various descriptions and statistical values. A total of 585 dimensions of omics were extracted from 99 patients features, which make up the data set;

[0023] (3) Divide the data set obtained in step (2) into a training set and a test set according to the sequence of abdominal CT scan time, wherein the ratio of the number of patients contained in the training set and the test set is 6:4. Apply bootstrap to the training set to sample it 100 times, each time the sub-samples obtained do not exceed 75% of the entire training set, and the fi...

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

No PUM Login to view more

Abstract

The invention discloses a CT radiomics-based pancreatic neuroendocrine tumor grading method. The method comprises the following steps of (1) collecting a PNET case abdomen CT image and marking the image with a PNET tumor area; (2) performing radiomics feature extraction in a PNET tumor region to obtain a data set; (3) dividing the data set into a training set and a test set, performing sampling onthe training set to obtain data subsets, performing feature screening by using an mRmR algorithm, and selecting target features; (4) training a support vector machine classifier on the training set by using the target feature, and taking the support vector machine classifier as a PNET hierarchical prediction model; and (5) testing the abdominal CT image of the PNET case to be tested by using a PNET grading prediction model to obtain grading. According to the method, the PNET patient is prevented from knowing the PNET level through surgical pathology. The pain of the patient is relieved, and the treatment time is shortened.

Description

technical field [0001] The invention relates to a grading method for tumors, in particular to a grading method for pancreatic neuroendocrine tumors based on CT radiomics. Background technique [0002] Pancreatic neuroendocrine tumors (PNET) account for 3% to 7% of pancreatic tumors. According to whether PNET causes clinical symptoms, it is divided into functional and non-functional. The diagnosis of functional PNET is mainly based on clinical manifestations and examination, while non-functional PNET is mostly found during physical examination and confirmed by postoperative pathology. [0003] In 2010, the World Health Organization (WHO) divided the tumor into three tissue grades according to the count of mitotic figures and the index of Ki-67 positive tumor cells, that is, low-grade (G1, 1 mitotic figure / 10HPF (high power field), Ki-67<3%), intermediate grade (G2, 2-20 mitoses / 10HPF, 3%-20% for Ki-67) and high-grade (G3, >20 mitoses / 10HPF, Ki-67 >20%). [0004] A...

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
no application Login to view more
IPC IPC(8): G16H50/20G16H50/70
Inventor 徐军赵增瑞边云
Owner NANJING UNIV OF INFORMATION SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap