Feature extraction method for ultrasound tissue characterization based on Hilbert-Huang transform

A technology of feature extraction and yellow transformation, applied in instruments, character and pattern recognition, computer parts, etc., can solve the problem of difficult frequency band division and so on.

Inactive Publication Date: 2017-11-17
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In WT, because the high-pass and low-pass decomposition filters are not completely ideal filters, there is a serious crossover phenomenon between each frequency band, so it is difficult to achieve strict division of each frequency band

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
  • Feature extraction method for ultrasound tissue characterization based on Hilbert-Huang transform
  • Feature extraction method for ultrasound tissue characterization based on Hilbert-Huang transform
  • Feature extraction method for ultrasound tissue characterization based on Hilbert-Huang transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] A feature extraction method for ultrasonic tissue characterization based on Hilbert-Huang transform, comprising the following steps:

[0085] S1: Collect multiple frames of ultrasonic echo RF signals of tissue samples, select a region of interest (Region Of Interest, referred to as ROI), and construct an ultrasonic RF time series;

[0086] S2: Using the HHT algorithm, perform feature extraction on the ultrasonic RF time series, and obtain sample feature vectors based on time, frequency and energy relationships;

[0087] S3: Use the rankfeatures algorithm to perform feature screening and feature fusion, calculate the sample feature fusion index, and use the feature fusion index as a feature to characterize the organization.

[0088] In the step S1, the specific process of constructing the ultrasonic RF time series is as follows:

[0089] S1-1: scan the tissue, and obtain multiple frames of its ultrasonic echo RF signal;

[0090] S1-2: Demodulate a certain frame of ultras...

Embodiment 2

[0131] Present embodiment except following feature other structures are with embodiment 1:

[0132] Such as figure 1 As shown, this embodiment is a feature extraction method based on Hilbert-Huang transform ultrasonic tissue characterization applied to the detection of tissue microstructure changes before and after chemotherapy in breast cancer tissue, including the following steps:

[0133] Step 1: Construct ultrasound RF time series

[0134] Sonix TOUCH produced by Canada Ultrasonix Company and a broadband linear array ultrasonic probe with a center frequency of 6.6 MHz were used to scan the thoracic subcutaneous tissue of female BALB / C nude mice, and record multi-frame ultrasonic echo RF signals. In this experiment, 27 female BALB / C nude mice aged 4 to 6 weeks were used as experimental subjects. Firstly, human breast cancer cells MCF-7 were cultured, then 10% fetal bovine serum and 100 units / ml streptomycin were added, placed in an environment with a temperature of 37°C a...

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 feature extraction method for ultrasound tissue characterization based on the Hilbert-Huang transform. The method comprises the steps of acquiring multiple frames of ultrasonic echo RF signals of a tissue sample, selecting regions of interest, and constructing an ultrasonic RF time sequence; extracting features of the ultrasound RF time sequence by using a HHT algorithm to obtain sample feature vectors based on the relation of time, frequency and energy; and performing feature screening and feature fusion by using a rankfeatures algorithm, calculating a sample feature fusion index, and taking the feature fusion index as the feature for tissue characterization. The feature fusion index provided by the invention can effectively reflect the difference between different types of tissue samples and is suitable for the feature extraction of the ultrasonic tissue characterization.

Description

technical field [0001] The invention relates to the technical field of ultrasonic tissue characterization, in particular to a feature extraction method for ultrasonic tissue characterization based on Hilbert-Huang transform. Background technique [0002] Since the mechanism of ultrasonic interaction with biological tissue is not yet clear, people can only indirectly achieve the purpose of identifying tissue structure, composition, and state by extracting ultrasonic echo information and interpreting it, thereby prompting people to extract ultrasonic tissue characterization features. Research. [0003] There are three main types of existing ultrasonic tissue characterization feature extraction methods: based on ultrasonic B-mode images, based on backscattered acoustic beam RF signals, and based on ultrasonic RF time series analysis. In the research based on ultrasonic B-mode images, the texture characteristics of the gray-scale distribution of B-mode images are mainly used. T...

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): G06K9/00G06K9/62
CPCG06F2218/08G06F18/253
Inventor 林春漪曹文雄
Owner SOUTH CHINA UNIV OF 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