IEEE ICMA 2016 Conference
Plenary Talk 1
Quantitative Imaging Informatics in Cost effective PET Imaging
and Classification of Lung Disease
Andrew F. Laine, D.Sc.
Percy K. and Vida L. W. Hudson Professor
Chair, Department of Biomedical Engineering
Professor of Radiology (Physics), Department of Radiology
Director, Heffner Biomedical Imaging Laboratory
Columbia University, New York, NY, USA
This talk presents a novel method for emphysema quantification, based on parametric modeling of intensity distributions in the lung and a hidden Markov measure field model to segment emphysematous regions. The framework adapts to the characteristics of an image to ensure a robust quantification of emphysema under varying CT imaging protocols and differences in parenchymal intensity distributions due to factors such as inspiration level. Compared to standard approaches, the present model involves a larger number of parameters, most of which can be estimated from data, to handle the variability encountered in lung CT scans. The method was used to quantify emphysema on a cohort of 87 subjects, with repeated CT scans acquired over a time period of 8 years using different imaging protocols. The scans were acquired approximately annually, and the data set included a total of 365 scans. The results show that the emphysema estimates produced by the proposed method have very high intra-subject correlation values. By reducing sensitivity to changes in imaging protocol, the method provides a more robust estimate than standard approaches. In addition, the generated emphysema delineations promise great advantages for regional analysis of emphysema extent and progression, possibly advancing disease subtyping, including COPD.
An important tool for studying brain disorders is positron emission tomography (PET), a nuclear imaging technology that allows for the in vivo functional characterization and quantification of blood flow, metabolism, protein distribution, and drug occupancy using radioactively tagged probes (tracers). Full quantification of PET images requires invasive arterial input function (AIF) measurement through online arterial blood sampling for the duration of the scan (1-2 hours). The AIF is used to correct images by accounting for the tracer bioavailability, which depends on an individual's physiological capacity for clearance, distribution and metabolism of the tracer. However, AIF measurement is invasive, risky, time consuming, uncomfortable for patients, and costly. Perhaps most importantly, it is impractical at the point-of-care and therefore limits clinical utility of PET. We believe an integrative multi-modal approach is possible via the amount of personalized information about the physiological and biochemical makeup of individuals available in their electronic health record (EHR). This talk will outline a novel approach to combine EHR and dynamic PET imaging data in an optimization framework based on simulated annealing to non-invasively estimate the AIF. Techniques that will be outlined are applicable across imaging modalities, organs and diseases, such as functional imaging of prostate cancer images where increasingly more complex tracers are utilized for assessment and require AIF measurement.
Dr. Andrew F. Laine, received his D.Sc. degree from Washington University (St. Louis) School of Engineering and Applied Science in Computer Science, in 1989. He was a Professor in the Department of Computer and Information Sciences and Engineering at the University of Florida (Gainesville, FL) from 1990-1997. He joined the Department of Biomedical Engineering in 1997 and served as Vice Chair of the Department of Biomedical Engineering at Columbia University since 2003-2011. He is currently Chair of the Department of Biomedical Engineering and Director of the Heffner Biomedical Imaging at Columbia University and the Percy K. and Vida L. W. Hudson Professor of Biomedical Engineering and Professor of Radiology (Physics).
He has served on the program committee for the IEEE-EMBS Workshop on Wavelet Applications in Medicine in 1994, 1998, 1999, and 2004. He was the founding chair of the SPIE conference on “Mathematical Imaging: Wavelet Application in Signal and Image Processing”, and served as co-chair during the years 1993-2003. Dr. Laine has served as Chair of Technical Committee (TC-BIIP) on Biomedical Imaging and Image Processing for EMBS 2004-2009, and has been a member of the TC of IEEE Signal Processing Society, TC-BISP (Biomedical Imaging and Signal Processing) 2003-present. Professor Laine served on the IEEE ISBI (International Symposium on Biomedical Imaging) steering committee, 2006-2009 and 2009 – 2012. He was the Program Chair for the IEEE EMBS annual conference in 2006 held in New York City and served as Program Co-Chair for IEEE ISBI in 2008 (Paris, France). He served as Area Editor for IEEE Reviews in BME in Biomedical Imaging since 2007-2013. He was Program Chair for the EMBS annual conference for 2011 (Boston, MA). Professor Laine Chaired the Steering committee for IEEE ISBI, 2011-2013, and Chairs the Council of Societies for AIMBE (American Institute for Medical and Biological Engineers). Finally, he served as the IEEE EMBS Vice President of Publications 2008 – 2012, and currently the President of IEEE EMBS (Engineering in Biology and Medicine Society), 2015 - 2016. He is a member of the IEEE Big Data Initiative. He is a Fellow of IEEE and AIMBE.