Ultrasonic radiography characteristic automatic identification system and method based on artificial nerve network model

An artificial neural network and contrast-enhanced ultrasound technology, applied in the field of artificial neural network, can solve problems such as uncertainty, increased error rate, and inaccurate processing information

Inactive Publication Date: 2016-06-22
SHANGHAI TENTH PEOPLES HOSPITAL
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the human visual system has inaccurate and uncertain defects in processing information, resulting in subjective differences in the recognition of CEUS features by different image analysts
In addition, when the number of recognition times is large, image analysts will inevitably experience visual fatigue, slow response, etc., and the error rate will increase.

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
  • Ultrasonic radiography characteristic automatic identification system and method based on artificial nerve network model
  • Ultrasonic radiography characteristic automatic identification system and method based on artificial nerve network model
  • Ultrasonic radiography characteristic automatic identification system and method based on artificial nerve network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] 1. Design of CAD system for liver contrast-enhanced ultrasonography (CEUS).

[0050] (1) Establishment of liver CEUS database

[0051] The previously stored liver CEUS dynamic and static image data were retrospectively collected, and the target number of cases n was 1000. The contrast agent can be Sonovo (Bracco, Italy), and the CEUS imaging can adopt the low mechanical index (mechanical index <0.2) imaging mode. The nature of the lesion is confirmed by clinical, imaging or pathological data. Easier-to-diagnose cases such as hepatic cysts and focal loss of fat in the liver were excluded. The diagnostic criteria for different types of lesions refer to relevant guidelines or literature (Claudon 2008). details as follows.

[0052] 1. Hepatocellular carcinoma: those without liver cirrhosis need to be confirmed by pathology; those with liver cirrhosis need to be confirmed by pathology for nodules with a diameter of less than 2 cm, and nodules with a diameter of more tha...

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 provides an ultrasonic radiography characteristic automatic identification system and method based on an artificial nerve network model; the system comprises the following elements: a data input unit used for inputting ultrasonic radiography image data; a data storage unit used for collecting and storing the inputted ultrasonic radiography image data; a data processing unit used for extracting various ultrasonic radiography image characteristics from the collected ultrasonic radiography image data, building an artificial nerve network according to the various ultrasonic radiography image characteristics and corresponding identification results, and identifying to-be processed images according to the artificial nerve network; a data output unit used for outputting the processing result of the data processing unit. The ultrasonic radiography characteristic automatic identification system and method can help to identify pathology CEUS characteristics of an interested area (pathology area).

Description

technical field [0001] 本发明涉及人工神经网络技术,提供了一种超声造影(CEUS)的计算机辅助特征识别方法;具体地,提供了一种基于人工神经网络模型超声造影特征自动识别系统及方法。 Background technique [0002] 超声造影(Contrast-enhancedultrasound,CEUS)成像技术是超声医学近年来的革命性突破,通过向外周静脉注射新型超声造影剂,采用造影剂特异成像技术,能实时直观显示感兴趣区(病变区域)的微循环灌注,使超声检查从单纯的形态学观察进步到功能性成像水平。利用病灶表现出来的CEUS特征,医师可完成诊断及治疗。 [0003] 但目前CEUS特征的识别环节主要依靠肉眼,其准确性依赖不同图像分析人员的分析水平、耐心与经验。再加上人类的视觉系统处理信息存在不准确和不确定的缺陷,造成不同图像分析人员对CEUS特征的识别存在主观差异。此外,当识别次数较多时,图像分析人员难免出现视觉疲劳、反应迟钝等现象,错误率提高。因此,为提高CEUS特征识别的准确率与效率,需开发出一种结论客观、状态稳定的自动图像识别系统。 [0004] 计算机辅助判断(Computer-aideddiagnosis,CAD)是一种可用于医学图像分析的辅助系统,其作用在于使图像信息客观化,进而帮助图像分析人员得出更准确的结论。CAD的主要优点在于快速的数据处理,提供重复性高、客观、准确的信息,突破个人知识和经验的局限性,减少图像分析人员因经验不足或视觉疲劳等主观性原因造成的错漏。CAD充分认识到计算机的局限性,目的不是代替人的思维,而是为图像分析人员的判断提供帮助。 [0005] 当今的CAD已逐渐加入人工智能(ArtificialIntelligence)理念,目的在于利用计算机来完成用人的智慧才能完成的工作。它用人工的方法,对人脑的思维活动过程进行模拟;当使得设备或机器的功能与脑功能大体等价时,这种设备或机器的功能就可以认为是具有某种程度的人工智能。 [0006] 人工智能CAD系统目前主要基于人工神经网络(Artificialneuralnetwork,ANN)实现。ANN是一种应用类似于大脑神经突触连接的结构进行信息处理的数学模型,试图通过模拟大脑神经网络处理、记忆信息的方式进行信息处理。它...

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): G06F19/00
CPCG16H50/20
Inventor 徐辉雄郭乐杭
Owner SHANGHAI TENTH PEOPLES HOSPITAL
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