[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119594-en":3,"doc-seo-119594-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119594,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Development of Machine Learning Methods for Ultrasound RF Data Processing and Analysis","This thesis develops and applies machine learning methods to improve processing and analysis of ultrasound radiofrequency (RF) data. It targets limitations of conventional ultrasound imaging by exploiting the information in RF signals and combining it with advanced models. The work covers detection and classification of novel ultrasound contrast agents using 1D CNNs and anomaly detection, and tissue differentiation in prostate imaging via machine learning with radiomics features. Results support more accurate, non-invasive diagnostic tools and enhanced image quality for clinical translation.","DEVELOPMENT OF MACHINE LEARNING METHODS FOR  \nULTRASOUND RF DATA PROCESSING AND ANALYSIS  \nby  \nTeja R. Pathour  \nAPPROVED BY SUPERVISORY COMMITTEE:  \nBaowei Fei, Co-Chair  \nShashank Sirsi, Co-Chair  \nKatherine Brown  \nYichen Ding  \nCopyright 2024 Teja R. Pathour All Rights Reserved  \nThis dissertation is dedicated to my parents.  \nDEVELOPMENT OF MACHINE LEARNING METHODS FOR  \nULTRASOUND RF DATA PROCESSING AND ANALYSIS  \nby  \nTeja R. Pathour, BS, MS  \nDISSERTATION  \nPresented to the Faculty of The University of Texas at Dallas in Partial Fulfillment  \nof the Requirements  \nfor the Degree of  \nDOCTOR OF PHILOSOPHY IN  \nBIOMEDICAL ENGINEERING  \nTHE UNIVERSITY OF TEXAS AT DALLAS  \nDecember 2024  \nACKNOWLEDGMENTS  \nI would like to thank my advisors Dr. Shashank Sirsi, Dr. Baowei Fei, and all my committee members for their valuable mentorship and guidance. I sincerely appreciate the help and support from all my lab members in Dr. Sirsi’s and Dr. Fei’s lab throughout the duration of my PhD. I would like to thank my family and friends who have supported me during this journey.  \nJuly 2024  \nDEVELOPMENT OF MACHINE LEARNING METHODS FOR  \nULTRASOUND RF DATA PROCESSING AND ANALYSIS  \nTeja R. Pathour, PhD  \nThe University of Texas at Dallas, 2024  \nSupervising Professors: Baowei Fei, Co-Chair  \nShashank Sirsi, Co-Chair  \nThis thesis presents the development and application of machine learning methods to enhance the processing and analysis of ultrasound radiofrequency (RF) data. The primary aim is to address current limitations in ultrasound imaging by leveraging the rich information contained in RF data and integrating it with advanced machine learning techniques. The research focuses on two main areas: the detection and classification of novel ultrasound contrast agents and the tissue differentiation in prostate imaging. Novel contrast agents, such as chemically crosslinked microbubble clusters (CCMCs), were synthesized and characterized. These agents exhibit unique acoustic signatures that, when analyzed using machine learning models like one-dimensional convolutional neural networks (1D CNNs) and anomaly detection models could be distinguished and separated. These unique acoustics when compared with the individual contrast agents, exhibited higher energy which can potentially lead to improved contrast of the image and visualizing the microvascular structures and tissue perfusion by using these contrast agents for super-resolution ultrasound imaging. In addition to these novel contrast agents, we explored  \nhemoglobin microbubbles (HbMBs) as oxygen sensors to detect oxygen levels in the surrounding by using the acoustic response of HbMBs in varying oxygen levels environment by using pixel intensity comparison and 1D CNN model. We also explored the potential of differentiating prostate peripheral zones and stromal regions using ex-vivo prostate RF data. Machine learning algorithms, combined with radiomics features extracted from RF data, were employed to accurately differentiate between various tissue types. The findings ofthis research underscore the potential of integrating RF data with machine learning models to overcome the inherent limitations of conventional ultrasound imaging. By enhancing image quality and diagnostic accuracy, these advancements pave the way for more effective, non-invasive diagnostic tools in clinical practice, ultimately improving patient outcomes and healthcare efficiency.  \nTABLE OF CONTENTS  \nACKNOWLEDGMENTS .............................................................................................................. v  \n[ABSTRACT................................................................................................................................... vi](ABSTRACT................................................................................................................................... vi)  \n[TABLE OF CONTENTS...............................](TABLE OF CONTENTS...............................)...","cbCaiopVFt5F9aYd","https://ap.wps.com/l/cbCaiopVFt5F9aYd","pdf",4616595,1,137,"English","en",105,"# Introduction\n## Motivation\n## Background\n## Innovation and Significance\n## Specific Aims\n## Contribution\n# Harnessing Chemically Crosslinked-Microbubble Clusters Using Deep Learning for Ultrasound Contrast Imaging\n## Introduction\n## Materials and Methods\n## Results\n## Discussion\n## Conclusion\n# Novel Hemoglobin Microbubbles for Blood Oxygen Level Detection Using Ultrasound Imaging and Deep Learning Techniques\n## Intr","[{\"question\":\"What is the primary goal of this thesis?\",\"answer\":\"To develop and apply machine learning methods that enhance ultrasound RF data processing and analysis, addressing limitations of conventional ultrasound imaging.\"},{\"question\":\"How are machine learning models used for ultrasound contrast agents?\",\"answer\":\"Chemically crosslinked microbubble clusters are synthesized and characterized, then distinguished and separated using models such as 1D CNNs and anomaly detection based on their acoustic signatures.\"},{\"question\":\"How does the thesis approach prostate tissue differentiation?\",\"answer\":\"It uses ex-vivo prostate RF data with machine learning combined with radiomics features extracted from RF signals to differentiate tissue regions such as prostate peripheral zones and stromal regions.\"}]","Development of Machine Learning Methods for Ultrasound RF Data Processing and Analysis | PDF",1785725181,345,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"development-of-machine-learning-methods-for-ultrasound-rf-data-processing-and-analysis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/development-of-machine-learning-methods-for-ultrasound-rf-data-processing-and-analysis/119594/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the primary goal of this thesis?","Question",{"text":75,"@type":76},"To develop and apply machine learning methods that enhance ultrasound RF data processing and analysis, addressing limitations of conventional ultrasound imaging.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are machine learning models used for ultrasound contrast agents?",{"text":80,"@type":76},"Chemically crosslinked microbubble clusters are synthesized and characterized, then distinguished and separated using models such as 1D CNNs and anomaly detection based on their acoustic signatures.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis approach prostate tissue differentiation?",{"text":84,"@type":76},"It uses ex-vivo prostate RF data with machine learning combined with radiomics features extracted from RF signals to differentiate tissue regions such as prostate peripheral zones and stromal regions.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]