SEI: Collaborative Research: Endoscopic Multimedia Information System (EMIS)

摘要视频技术的进步正被纳入当今的医疗保健实践。例如，各种类型的内窥镜用于结肠镜，上消化道内窥镜，肠镜，支气管镜和膀胱镜。此外，数量迅速增加的以前的开放式手术现在正在转变为内镜手术，包括胆囊切除术、供体肾脏切除术、结肠和胰腺肿瘤切除术、裂孔疝矫正、冠状动脉搭桥术和微创神经外科手术。尽管在医学图像分析方面有大量的知识，但内窥镜检查视频并没有被系统地捕获用于实时或术后审查和分析。它们偶尔被录到磁带（即VHS）上。没有开发任何硬件和软件工具来捕获、分析和提供对此类视频中的医疗、科学或教育内容的用户友好和有效访问。本项目旨在开发一个内窥镜多媒体信息系统（EMIS），用于捕获高质量的内窥镜视频，分析捕获的视频，并提供对这些视频内容的有效访问。根据医学图像处理文献的研究，内窥镜视频图像与医学静止图像有显著差异。该项目将开发一种新的内窥镜视频捕捉系统，旨在保护患者的隐私，不干扰内窥镜手术，不限制特定的内窥镜供应商。信息和非信息帧自动分类的新算法。该技术不需要任何预定义的参数或阈值。针对突出病变（如息肉）的自动内容分析新算法。许多突出的病灶聚集在一起。首先将开发一种新的区域分割技术，可以识别孤立的病变。为了处理聚集性病变，将开发使用区域模式图的算法，该算法可以捕获相关区域的重要特征。该系统将直接有利于内窥镜研究、教育和培训。为研究生的研究型培训做出贡献，这些研究生将在PI和CoPI的机构中为计算机科学和医学信息学的研究生和本科课程的学生提供研究型高级培训。该项目将有助于培养具有独特技能的新一代计算机科学家，以补充传统的医学成像。这项研究将增加初中生和高中生参加各种大学项目（UTA暑期科学营，女性科学与工程项目）和国家项目的研究机会。(4)扩大代表性不足群体的参与。

ABSTRACTAdvances in video technology are being incorporated into today's healthcare practice. For example, various types of endoscopes are used for colonoscopy, upper gastrointestinal endoscopy, enteroscopy, bronchoscopy, and cystoscopy. In addition, a rapidly expanding number of formerly open surgical procedures now are being converted to endoscopic procedures including resection of gallbladders, retrieval of donor kidneys, resection of tumors of colon and pancreas, correction of hiatal hernias, coronary artery bypass grafting and minimal invasive neurosurgeries. Despite a large body of knowledge in medical image analysis, endoscopy videos are not systematically captured for real-time or post-procedure reviews and analyses. They are recorded occasionally to magnetic video-tapes (i.e., VHS). No hardware and software tools have been developed to capture, analyze, and provide user-friendly and efficient access to the medical, scientific, or educational content on such videos. This project aims to develop an Endoscopic Multimedia Information System (EMIS) to capture high quality endoscopy videos, analyze the captured videos, and provide efficient access to the content of these videos.Images of endoscopy videos significantly differ from medical still images as studiedin the literature of medical image processing. The project will develop a new capturing system for endoscopy videos designed for patient's privacy and is non-disruptive to endoscopic proceduresand non-restrictive to a particular endoscope vendor. New algorithms for automatic classification of informative and non-informative frames. The technique does not need any predefined parameters or thresholds. New algorithms for automatic content analysis for protruding lesions such aspolyps. Many protruding lesions are clustered together. A new region segmentation technique that can identify isolated lesions will be developed first. To handle clusteredlesions, algorithms using a region pattern graph that captures important characteristics of relevant regions will be developed..The proposed system will directly benefit endoscopic research, education, and training. Contributions to research-based training of graduate students who will contribute to research-based advanced training of students in graduate and undergraduate programs in computer science and medical informatics at PI and CoPI's institutions. The project will contribute to training of a new generation of computer scientists with a unique skill set supplement to traditionalmedical imaging. This research will enhance research opportunities for junior high and high school students participating in various university programs (UTA Summer Science Camp, Program for Women in Science and Engineering) and national programs. (4) Broaden the participation of under-represented groups.