新澳博,澳博国际

搜 索
当前位置: 首页 > 综合页 > 学术信息 > 正文
返回首页
新闻资讯
新澳博章程
新澳博概况
新澳博
教育教学
学科科研
招生就业
合作交流
澳博国际
数字图书馆
5月8日:智慧大讲坛——Image-retrieval aided diagnosis system for breast cancer in mammography(乳腺癌图像检索辅助诊断系统研究)
2019-05-05 14:36     (浏览次数:)

5月8日:智慧大讲坛——Image-retrieval aided diagnosis system for breast cancer in mammography(乳腺癌图像检索辅助诊断系统研究)

报告时间:2019年5月8日   16;00-17:30

报告地点:逸夫楼I311

报告人简介:

中文:杨永义是伊利诺伊理工大学电气与计算机工程系教授。他的研究兴趣是医学成像、机器学习、模式识别和生物医学应用。先后发表著作270多篇(引用超过7,100次,h因子为33)。目前研究主要集中在乳腺癌检测和诊断的计算机辅助技术,以及用于心脏诊断成像的图像重建方法。他是国际著名学术组织“美国医学及生物工程学院(AIMBE)”院士(Elected Fellow)。

英文:Yongyi Yang is the Harris Perlstein Professor in the Department of Electrical and Computer Engineering, Illinois Institute of Technology. His research interests are in medical imaging, machine learning, pattern recognition, and biomedical applications. He has over 270 peer-reviewed publications in these areas (over 7,100 citations, h-index=33 per Google Scholar). His research activities are in computer-aided techniques for breast cancer detection and diagnosis, and in image reconstruction methods for cardiac diagnostic imaging. He is an elected Fellow of the American Institute for Medical and Biological Engineering (AIMBE).

报告内容简介:

中文:乳房X线照片图像中微钙化(MC)的出现可能是乳腺癌的重要早期征兆。然而,由于其微妙的外观,MC病变可能难以诊断为良性或恶性。在本次演讲中,我们将展示一项自动乳房X线照片检索系统的研究,以帮助放射科医师诊断乳房X线照片中的MC病变。在计算机辅助诊断(CADx)中,显示与被评估的病变类似的一组病变有可能提高放射科医师的诊断准确性。我们首先通过考虑感知相似的图像特征和所考虑的病变的恶性可能性来开发相关病例的检索系统。然后,我们与一组乳房放射科医生进行观察者研究,以评估所提出的检索系统对一组测试病例的诊断价值。基于接收器操作特征分析,结果表明,检索CADx系统可以在恶性肿瘤的可能性和癌症风险评估方面提高读者对MC病变的诊断准确性。

英文:The occurrence of microcalcifications (MC) in mammogram images can be an important early sign of breast cancer. However, due to their subtle appearance, MC lesions can be difficult to diagnose as benign or malignant. In this talk we will present a study on an automated mammogram retrieval system for assisting radiologists in diagnosis of MC lesions in mammograms. In computer-aided diagnosis (CADx), displaying a set of lesions similar to the one being evaluated has the potential to improve radiologists’ diagnostic accuracy. We first develop a retrieval system for relevant cases by taking into account both perceptually similar image features and the likelihood of malignancy of the lesion under consideration. We then conduct an observer study with a group of breast radiologists to evaluate the diagnostic value of the proposed retrieval system on a set of test cases. Based on receiver-operating characteristic analysis, the results demonstrate that the retrieval CADx system can improve the readers’ diagnostic accuracy of MC lesions in terms of both likelihood of malignancy and cancer risk assessment.

主办单位: 智能技术与工程学院 发布单位:科研处

打印    收藏
关闭窗口
新澳博地址:重庆沙坪坝区大学城东路20号 邮编:401331 信息管理:新闻文化中心 技术支持:信息化处 版权所有:重庆科技学院    渝ICP备13000511号-1