Scientific Lectures //
Title: Radiomics and Genomics: From the Genome to the Phenome and back again
Dr. Hugo Aerts - Assistant Professor, Dana-Faber Cancer Institute, Brigham and Women’s Hospital, Harvard Medical School; Head of the Computational Imaging and Biology Laboratory
Presented: May 23, 2013
ABSTRACT: The identification of prognostic markers in cancer is important to guide clinical decision making and to identify new drug targets. Cancer genotypes and phenotypes can be assessed at various levels, from the molecular and cellular levels, up to the macroscopic level of pathology and non-invasive imaging. The focus of my group is developing methods to quantitatively extract and link genotype and phenotype data. Radiomics addresses this issue by converting medical images (CT, PET and MRI), into minable data by the high-throughput application of large amounts of algorithms. By doing so we have a method to non-invasively decode the cancer phenotype.
In this talk, I will discuss recent developments in the field merging research areas of bioinformatics and medical imaging. Also, I will discuss our recent work of building a computational image analysis system to extract a rich quantitative feature set from medical imaging and use these features to build prognostic radiomics signatures. I will conclude with a discussion of future work on building integrative systems incorporating both molecular and phenotypic data to improve cancer therapies.
BIOGRAPHY: I am an Assistant Professor at Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School and the head of a laboratory focused on computational imaging and computational biology. My background is in engineering with a concentration on medical physics and bioinformatics. My research interests are in developing and applying methods in machine learning and biomedical informatics to problems in genomic medicine and medical imaging.