Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic 3D brain tumor segmentation and classification

a brain tumor and automatic technology, applied in the field of tumor imaging, can solve the problems of significant waste of medical resources, and achieve the effect of improving the healthcare experience with machine intelligence and accurate analysis

Active Publication Date: 2018-01-25
SONY CORP
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The method significantly reduces the time required for tumor analysis, providing accurate and efficient segmentation and classification without user input, enhancing surgical preparation.

Problems solved by technology

Usually, it takes several hours for clinicians to manually contour the tumor classes from multiple pre-operative MRI scans which is a significant waste of medical resources.

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
  • Automatic 3D brain tumor segmentation and classification
  • Automatic 3D brain tumor segmentation and classification
  • Automatic 3D brain tumor segmentation and classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019]To expedite the process of tumor analysis, the automatic 3D brain tumor segmentation and classification method described herein is able to be implemented. There are many brain tumor segmentation challenges such as large intensity variations across subjects, unclear and irregular boundaries, and significant different tumor appearance in MRI across subject.

[0020]FIG. 1 illustrates multi-modal MRIs according to some embodiments. The multi-modal MRIs include T1, T1 contrast enhanced (T1c), T2 and T2 flair.

[0021]FIG. 2 illustrates a diagram of the automatic 3D brain tumor segmentation and classification method according to some embodiments. In the step 200, whole tumor segmentation is performed. Whole tumor segmentation includes data normalization 202 and initial segmentation 204. Data normalization 202 includes anatomy-structure-based intensity normalization. Initial segmentation 204 includes anatomy-guided graph-based segmentation. In the step 206, multi-class tumor segmentation ...

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

A fully automatic brain tumor segmentation and classification method and system improve the healthcare experience with machine intelligence. The automatic brain tumor segmentation and classification method and system utilize whole tumor segmentation and multi-class tumor segmentation to provide accurate analysis.

Description

FIELD OF THE INVENTION[0001]The present invention relates to tumor imaging. More specifically, the present invention relates to 3D brain tumor segmentation and classification.BACKGROUND OF THE INVENTION[0002]During neurosurgery, surgeons need to understand where the tumor is and the boundaries of its various components. Usually, it takes several hours for clinicians to manually contour the tumor classes from multiple pre-operative MRI scans which is a significant waste of medical resources.SUMMARY OF THE INVENTION[0003]A fully automatic brain tumor segmentation and classification method and system improve the healthcare experience with machine intelligence. The automatic brain tumor segmentation and classification method and system utilize whole tumor segmentation and multi-class tumor segmentation to provide accurate analysis.[0004]In one aspect, a method programmed in a non-transitory memory of a device comprises performing whole tumor segmentation and performing multi-class tumor...

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(United States)
IPC IPC(8): G06T7/00G01R33/48A61B5/00G06K9/62A61B5/055G06V10/764
CPCG06T7/11G06T7/0012G06K9/6267A61B5/055A61B5/7264G01R33/4808G01R33/4828G06T2207/30016G06T2200/04G06T2207/30096G06T2207/10088A61B2576/00G06T2207/20081G06T2207/20156G06T7/187G06T7/10G06V2201/03G06V10/764G06F18/24323G06F18/24G06T7/12
Inventor CHOU, CHEN-RUISONG, BILIU, MING-CHANG
Owner SONY CORP