Women in Engineering

Wednesday June 28, 2017 at 5:00 p.m. Dr. Shiva Amiri, CEO of BioSymetrics Inc, will be presenting “Large-Scale Analytics and Machine Learning for Biomedical Data Types”. Day & Time: Wednesday June 28, 2017 5:00 p.m. – 6:00 p.m. Speaker: Dr. Shiva Amiri CEO of BioSymetrics Inc Toronto, Ontario, Canada Location: Room ENG288 Department of Computer Science Ryerson University 245 Church St, Toronto, M5B 1Z4 Contact: Alireza Sadeghian, Alex Dela Cruz Organizers: Signals & Computational Intelligence Chapter, WIE Abstract: The scale of data being generated in medicine and research can easily overwhelm typical analytic capabilities. This is particularly true with MRI/fMRI scanning, genomics data, streaming/wearables data in addition to other clinical data types, especially if in combination. Challenges include 1) large file sizes often in heterogeneous formats 2) currently no standard Protocol exists for extraction of standardized characteristics, and 3) traditional methods for group-wise comparison can often result in spurious findings. The talk will address these challenges by discussing customized processing pipelines built for multiple data types in biomedicine, which enable effective machine learning and other types of analytics on these datasets. This approach leverages the rapid model building capabilities of our real-time machine learning software to iterate through normalization parameters for each data type and disease class. In addition, this platform allows easy integration between the various medical data types (genome sequence, phenotypic, and metabolic data) allowing generation of more comprehensive disease classification models. The ability to standardize and pre-process multiple types of biomedical data for machine learning, no matter the source and type, and effectively combine it with other data types is a powerful capability and holds promise for the future of diagnostics and precision medicine. Biography: Shiva Amiri is the CEO of BioSymetrics Inc. where they are developing a unique real-time machine learning technology for the analysis of massive data in biomedicine. BioSymetrics specializes in providing optimized pipelines for complex data types and effective methods in the analytics of integrated data. Prior to BioSymetrics she was the Chief Product Officer at Real Time Data Solutions Inc., she has led the Informatics and Analytics team at the Ontario Brain Institute, where they developed Brain-CODE, a large-scale neuroinformatics platform across the province of Ontario. She was previously the head of the British High Commission’s Science and Innovation team in Canada. Shiva completed her Ph.D. in Computational Biochemistry at the University of Oxford and her undergraduate degree in Computer Science and Human Biology at the University of Toronto. Shiva is involved with several organisations including Let’s Talk Science and Shabeh Jomeh International.

Monday July 17, 2017 at 4:00 p.m. Dr. Trevor McKee, STTARR Innovation Research Centre for Cancer Research, will be presenting “A framework for general purpose digital pathology image analysis, using machine learning methods to identify cancer subsets and immunotherapy biomarkers”. Day & Time: Monday July 17, 2017 4:00 p.m. – 5:00 p.m. Speaker: Dr. Trevor McKee STTARR – Innovation Research Centre for Cancer Research Toronto, Ontario, Canada Location: Room ENG101 George Vari Engineering Building (intersection of Church & Gould) Ryerson University 245 Church St, Toronto, M5B 1Z4 Contact: Alireza Sadeghian, Alex Dela Cruz Organizers: Signals & Computational Intelligence Chapter Abstract: Histological staining, interpreted by a pathologist, has remained the gold standard for cancer diagnosis and staging for over 100 years. There is a growing need for better – and more personalized – cancer treatments, to provide oncologists with the tools they need to best treat their patients. The advent of “molecular medicine”, or targeted therapeutic strategies that rely on knowledge of particular mutations in a cancer in order to tailor treatment, has improved cancer therapy for many patients. This has led to the use of companion diagnostics, in which tumor biopsies are stained for a specific marker or set of markers, using immunohistochemical approaches. The information obtained from the degree of staining or spatial arrangement of stained cells within the tumor helps to identify tumor molecular subclasses that may benefit from such tailored therapeutic approaches. The increase in the number of slides being stained for specific markers and used in diagnosis, along with the increased need for quantitative assessment of the degree of staining, number of cells, or spatial arrangement of cells within the tumor, has increased the volume and type of work that pathologists encounter in their diagnostic workflow. Our team works on the development of tools for quantitative digital pathology analysis that can benefit pathologists, by building and validating semi-automated algorithms for cellular quantification and intensity scoring of stained slides. We use machine learning methods to learn features that distinguish different morphological regions from pathologist annotations. These are then fed into a tissue segmentation and classification framework to break the tissue down into its components, either on the individual cell level, or the glandular level. Staining intensity is quantified following colour deconvolution of the individual stain components, and reporting metrics are designed, in close collaboration with pathologists and biological scientists, to identify the appropriate outputs for comparing between treatment groups or different cancer types. The use of multiplexed digital pathology stains allows us to build a generalized analytical framework to perform “tissue cytometry”. This new technology can extract quantitative image-derived features in a reproducible and robust fashion, providing clinicians and biological scientists with tools to measure previously inaccessible phenomena, like measuring the hypoxic gradient directly within tumor sections, or comparing glucose uptake to lactic acid production in the same tumor sample. This approach establish the foundation for a bridge between traditional morphometric assessment of tumor biopsies, and the detailed spatially resolved chemical and molecular content maps of each tumor, providing an invaluable toolkit for the discovery of cancer molecular subtypes, and development of therapeutic interventions. Biography: Dr. Trevor McKee received his Ph.D. in Biological Engineering from the Massachusetts Institute of Technology in 2005, in the laboratory of Dr. Rakesh Jain of Harvard Medical School. During his graduate work, he pioneered the application of new imaging and analysis technologies to studying drug transport within tumors, and on developing methods to improve drug delivery. He also holds a Bachelors of Science in Chemical Engineering with a Biotechnology minor from the University at Buffalo. He moved to Toronto to continue postdoctoral work at the Ontario Cancer Institute, applying multi-modality imaging and quantitative image analysis methods to study preclinical cancer models. He has a successful track record of high-impact publications with a number of clinical and basic science collaborators, and has also collaborated with pharmaceutical companies on imaging-based preclinical testing of new compounds. He is currently Image Analysis Core Manager of the STTARR Innovation Centre, and manages a team of analysts to develop new algorithms for machine-learning powered image segmentation and quantification across a number of disease sites. His research interests lie in studying the tumor microenvironment, drug and oxygen delivery, and the development of tools for “tissue cytometry” – deriving complex biological and spatial relationships from tissue sections via computational image analysis methods.