MedTech West lunchseminar with Professor Yongyi Yang from the Illinois Institute of Technology, USA
On 21 October, 2016, we have the pleasure to invite you to a lunchseminar with Prof. Yongyi Yang from Illinois Institute of Technology, USA. Prof. Yang will speak about Bio-imaging and bioimage analysis: Part-A: 4D reconstruction methods for optimizing cardiac gated SPECT
Part-B: A content-based mammogram retrieval system as a diagnostic aid
The presentation will cover two research topics. The first part of the talk is focused on spatiotemporal (4D) reconstruction methods in cardiac gated SPECT imaging. Myocardial perfusion imaging with SPECT is currently the most frequently ordered test in nuclear medicine for assessing regional coronary blood flow, and gated SPECT permits quantitative evaluation of left ventricular function. However, cardiac gated SPECT images suffer from increased noise due to the reduced counts in individual gate frames. In recent years we have developed 4D image reconstruction methods to combat this noise by exploiting the fact that the desired image information is relatively consistent in time. The key in 4D reconstruction is to incorporate motion-compensated smoothing that follows the trajectories of cardiac motion, thereby preserving the integrity of critical perfusion and wall motion information during noise smoothing. Recently we further extended this approach for respiratory motion correction, enabling fully 4D reconstruction with both cardiac and respiratory gating. We will present reconstruction results obtained on some clinical acquisitions, and demonstrate that 4D reconstruction can be used to lessen radiation dose.
The second part of the talk is focused on development of a content-based mammogram retrieval system as a diagnostic aid in mammographic interpretation. We present a study on an automated mammogram retrieval system for assisting radiologists in diagnosis of clustered microcalcifications 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 BI-RAD assessment.
Dr. Yongyi Yang is currently the Harris Perlstein Endowed Chair Professor of Electrical and Computer Engineering and Professor of Biomedical Engineering at the Illinois Institute of Technology. Dr. Yang’s research interests are in signal and image processing, medical imaging, machine learning, pattern recognition, and biomedical applications. He has produced pioneering research in spatiotemporal (4D) reconstruction methods for cardiac diagnostic imaging and in computerized techniques for breast cancer detection and diagnosis. He has authored or co-authored over 240 peer-reviewed publications (6,200+ citations, h-index 31 per Google Scholar). Under NIH funding, he developed a content-based mammogram retrieval system, which has recently proven to improve the diagnostic accuracy of mammographic interpretation by radiologists. He developed 4D reconstruction methods for improving the accuracy of cardiac SPECT images and for reducing the radiation dose in SPECT. He also contributed to functional neuroimaging and infrared diagnostic iris imaging. Dr. Yang has served on numerous NIH study sections and NSF review panels. He has served as guest editor for several journal special issues on medical imaging, and is presently a Senior Area Editor of the IEEE Transactions on Image Processing. He is an elected member of the IEEE Bio Imaging and Signal Processing Committee.
Please, note that this seminar is in the MedTech West conference room at Röda stråket 10B, Sahlgrenska University Hospital.
A light lunch will be served to registered participants, last day to register is Monday 17 October 2016 at 13.00 pm.
When? 21 Oct, 2016, 11:30-12:30 (13:00 incl. lunch)
Where? MedTechWest conference room at Röda stråket 10B, Sahlgrenska University Hospital