Method and system for predicting curative effect of nasopharynx cancer induced chemotherapy

A prediction method and nasopharyngeal cancer technology, applied in the field of medical image analysis and prediction, can solve the problems of lack of standardized processing mode, inconsistency, and difficulty in guaranteeing the accuracy of prediction results, and achieve the effect of realizing personalized precision medicine and ensuring accuracy

Pending Publication Date: 2021-12-14
SHANDONG NORMAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The inventor found that in the existing research, the analysis process of radiomics did not form a standardized processing mode, and the results obtained by choosing different feature extraction methods, feature selection methods and different machine learning classifiers were inconsistent, which led to prediction Difficult to guarantee the accuracy of the results

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
  • Method and system for predicting curative effect of nasopharynx cancer induced chemotherapy
  • Method and system for predicting curative effect of nasopharynx cancer induced chemotherapy
  • Method and system for predicting curative effect of nasopharynx cancer induced chemotherapy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] like figure 1 and figure 2 , The present embodiment provides a method for prediction of NPC induction chemotherapy, comprising:

[0031] S101: obtaining a magnetic resonance image multimodal before induction chemotherapy.

[0032] S102: multimodal MR image region of interest delineated, image feature extraction region of interest to obtain imaging characteristics of the region of interest group.

[0033] General manually by the radiologist outlining the lesion area and regional lymph nodes of medical clinical data samples, will outline good focus area and regional lymph nodes as a region of interest. Feature extraction region of interest and to obtain a set of image characteristics, and the characteristics of all of the set of images is normalized.

[0034] In the present embodiment, a region of interest may be employed PyRadiomics feature extraction, feature extraction imaging features provided as a selected group, so to ensure a comprehensive feature extraction.

[0035] ...

Embodiment 2

[0092] The present embodiment provides a system for prediction of NPC chemotherapy induced, which specifically includes the following modules:

[0093] Multi-modal MRI image acquisition module for acquiring a multi-modal resonance image before induction chemotherapy;

[0094] Imaging Group characteristics acquisition module for multi-modal MRI image outline the region of interest, image feature extraction region of interest to obtain imaging a region of interest set of characteristics;

[0095] Mode wherein the multi-step sequential feature selection; best set of images characteristics screening module for a multi-step sequential manner utilizing feature selection, the set of images obtained meets the setting characteristics as characteristics of the best image group at least three steps of progressively feature selection;

[0096] Chemotherapy prediction module for optimum characteristics of image groups using the trained prediction SVM classifier to obtain a nasopharyngeal induc...

Embodiment 3

[0099] This embodiment provides a computer-readable storage medium, having stored thereon a computer program to achieve the above-described steps as nasopharyngeal cancer chemotherapy-induced prediction method when the program executed by the processor.

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 belongs to the field of medical image analysis and prediction, and provides a nasopharynx cancer induced chemotherapy curative effect prediction method and system. The method comprises the following steps: collecting a multi-modal magnetic resonance image before induced chemotherapy; performing region-of-interest sketching on the multi-modal magnetic resonance image, and extracting image features of the region-of-interest to obtain radiomics features of the region-of-interest; utilizing a multi-step step-by-step feature selection mode to obtain radiomics features meeting a set condition as optimal radiomics features; wherein the multi-step step-by-step feature selection mode is at least three-step step-by-step feature selection; and predicting the optimal radiomics characteristics by using the trained support vector machine classifier to obtain a predicted nasopharynx cancer induced chemotherapy curative effect result.

Description

technical field [0001] The invention belongs to the field of medical image analysis and prediction, and in particular relates to a method and system for predicting curative effect of nasopharyngeal carcinoma induction chemotherapy. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Nasopharyngeal carcinoma (NPC) is a malignant tumor that occurs in the nasopharyngeal mucosa, and the tumor cells are sensitive to radiotherapy and chemotherapy. In the late stage, a comprehensive treatment strategy of radiotherapy combined with chemotherapy is needed. Induction chemotherapy can reduce the tumor volume and reduce the irradiation dose of normal tissues around the target area to avoid severe radiation damage. However, patients receiving induction chemotherapy have to bear higher toxic and side effects. Heterogeneity was found in patient response to ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06K9/62G06K9/32
CPCG06T7/0012G06T2207/10088G06T2207/30096G06T2207/20104G06F18/2411G06F18/214
Inventor 李登旺杨超黄浦姜泽坤薄琳琳赵睿王建波朱慧李婕吴冰柴象飞章桦
Owner SHANDONG NORMAL UNIV
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