Maryellen L. Giger

Maryellen L. Giger is presently Professor of Radiology, the Committee on Medical Physics, and the College at the University of Chicago and is Director of the Graduate Programs in Medical Physics at the University (serving as Chair of the Ph.D.-degree granting Committee on Medical Physics in the BSD. She also serves as Chief of Radiological Sciences and Vice-Chair for Basic Science Research in the Department of Radiology, University of Chicago. Involvement at the national and international level can be found in her CV.

Dr. Giger is considered one of the pioneers in the development of CAD (computer-aided diagnosis). She has authored or co-authored more than 240 scientific manuscripts (including 130 peer-reviewed journal articles), is inventor/co-inventor on approximately 25 patents, and serves as a reviewer for various granting agencies, including the NIH and the U.S. Army. She is currently chair of the CAD conference for the SPIE Medical Imaging meeting. Dr. Giger has been associate editor for Medical Physics and IEEE Transactions on Medical Imaging. She is an elected fellow of the American Institute for Medical and Biological Engineering (AIMBE) and the American Association of Physicists in Medicine (AAPM), is a Senior Member of IEEE, is the nationally-elected Treasurer of the AAPM, a prior Vice-President of the RSNA, and serves on various scientific program committees. She was recently elected to the leadership chain for AAPM and will serve as President-elect in 2008, President in 2009, and Chairman of the Board in 2010. For the RSNA, she is completing her term as chair of the RSNA Research Grant Study Section and chair of the physics subcommittee for the RSNA program committee. She has given several invited presentations on CAD at SPIE, BIROW, SCAR, IWDM, CARS, AAPM, and RSNA, as well as at various international meetings, and at workshops and conferences of the NCI. Her research interests include digital radiography and computer-aided diagnosis in breast imaging, chest/CT imaging, cardiac imaging, and bone radiography.

Giger lab focuses on the development of multimodality CAD (computer-aided diagnosis) methods. Her research interests include digital radiography and computer-aided diagnosis in breast imaging, chest/CT imaging, cardiac imaging, and bone radiography. The long-term goals of her research are to investigate, develop, and translate multi-modality computerized image analysis techniques for improved cancer diagnosis and patient care. Development of CAD methods includes novel means for lesion segmentation, and 2D and 3D extraction of features characterizing the tumors and local background surround. These methods include development of computerized self-assessing lesion segmentation methods, which include methods for the computer to self-assess whether or not the lesion is well segmented as well as development of methods for incorporating extracted lesions features from multiple views and/or modalities, including those that weight features by the accuracy of the corresponding segmentation and those that use Bayesian neural network (BANN) with automatic relevance determination (ARD) priors for joint feature selection and classification. Giger research also includes an investigation of the role of quantitative breast parenchymal characteristics in computerized analysis for both diagnosis and cancer risk assessment in an attempt to understand the relationship between image-based biomarkers and biological and clinical biomarkers. Additional research involves methods for the optimization of the computer/human interface for presentation of computer output in computer-aided diagnosis (CAD). Computer-determined estimates of the probability of malignancy of lesions are dependent on the prevalence of cancer in the training database, which most often does not correspond to the prevalence of cancer in the population from which the user has experience, e.g., the population seen in the user's medical practice. Thus, the user often has difficulty interpreting the computer-estimated probability of malignancy. Thus, Giger lab is developing approaches with which to transform computer output to those that would match the internal parameters of the reader and thus provide useful indices of the probability of malignancy. Giger lab is also developing methods for assessing risk of fracture and osteoporosis using measures of bone mass, bone structure, and clinical data. Specifically, they aim to develop computerized radiographic methods for quantifying bone structure (through radiographic texture analysis: gRTAh) that may be used together with measures of bone mass and clinical data for use in quantitatively assessing bone strength.