ENTROPY-BASED TISSUE DISCRIMINATORS

基于熵的组织鉴别器

• 批准号: 8737902
• 负责人: SAMUEL A WICKLINE
• 金额: $ 18.43万
• 依托单位: WASHINGTON UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-09-30 至 2015-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8737902
• 关键词: Address; Algorithms; Back; Base Composition; Bayesian Analysis; Cardiac; Classification; Classification Scheme; Clinical; Color; Data; Data Set; Databases; Detection; Development; Diffuse; Dimensions; Discrimination; Disease; Ensure; Entropy; Environment; Evaluation; Expeditions; Fatty Liver; Fibrosis; Fishes; Foundations; Fractals; Frequencies; Heart; Histocompatibility Testing; Image; Image Analysis; Individual; Infarction; Injury; Investigation; Ischemia; Joints; Kidney; Knowledge; Label; Liver; Machine Learning; Maps; Measures; Methods; Metric; Microscopic; Normal tissue morphology; Organ; Outcome; Pathology; Pattern; Pharmaceutical Preparations; Physiological; Positioning Attribute; Procedures; Process; Property; Prostate; Radio; Reporting; Resolution; Rodent; Scheme; Shapes; Signal Transduction; Specificity; Staining method; Stains; Stream; Structure; Testing; Time; Tissue Differentiation; Tissue Model; Tissues; Ultrasonic Transducer; Ultrasonics; Ultrasonography; Visual Cortex; Work; attenuation; base; data reduction; design; detector; heart motion; indexing; meetings; n-dimensional; novel; public health relevance; radiofrequency; signal processing; sound; tissue processing; vector

DESCRIPTION (provided by applicant): The major problem addressed in this proposal is the development and evaluation of an automated noninvasive approach to discriminate different normal and pathological tissue types using machine learning algorithms; previous applications of machine learning have been based on features of the backscattered ultrasound that are essentially energy based. Our approach will be based on extracting features from images whose pixels are determined by the entropy contained in segments of the backscattered ultrasound. The unique attributes of entropy imaging suggest that the automated analysis we propose would be particularly robust for discrimination of deep tissues in a clinical environment.

描述（由申请人提供）：该提案解决的主要问题是开发和评估一种自动化非侵入性方法，以使用机器学习算法区分不同的正常和病理组织类型；以前的机器学习应用都是基于反向散射超声波的特征，这些特征本质上是基于能量的。我们的方法将基于从图像中提取特征，图像的像素由反向散射超声片段中包含的熵确定。熵成像的独特属性表明，我们提出的自动化分析对于临床环境中深层组织的区分特别强大。