Principal Investigators

Ali Sadeghi-Naini, PhD

Scientist
Sunnybrook Health Sciences Centre
2075 Bayview Ave., Room M6 605
Toronto, ON
M4N 3M5

Education:

M.Sc., 2006 artificial intelligence, Tehran Polytechnic University, Iran
PhD, 2011, biomedical engineering, Western University, Canada
Postdoctoral Fellowship, 2015, medical biophysics and radiation oncology, University of Toronto, Canada

Appointments and Affiliations:

Scientist, Physical Sciences, Odette Cancer Research Program, Sunnybrook Research Institute
Scientist, department of radiation oncology, Sunnybrook Health Sciences Centre
Assistant professor, department of medical biophysics, U of T

Research Summary:

The focus of Dr. Sadeghi-Naini’s research is on developing computer-aided image-guided technologies to improve personalized cancer therapeutics. In particular, he is interested in developing integrated imaging and computational frameworks to detect and characterize cancer, to facilitate cancer-targeting interventions and to evaluate response to treatment.

In this context, he is investigating novel methods of multimodal cancer imaging to explore different stages during cancer development and decay from various structural and functional perspectives.

Specifically, he is developing integrated frameworks to adapt complementary aspects of quantitative ultrasound imaging, optical spectroscopy, elastography, computed tomography, and magnetic resonance imaging to characterize a tumour in terms of its micro-structure, physiology, perfusion, metabolism and biomechanical properties.Further, he is investigating alterations in such tumour characteristics to develop sensitive biomarkers of cancer response to treatment.

Dr. Sadeghi-Naini is also transforming multimodal imaging within computational frameworks to facilitate the planning and navigation of interventional procedures such as biopsy, brachytherapy and radiation therapy.

A particular area of interest is in developing ad hoc models for quantification of spatial heterogeneity in cancer imaging. Alterations within a tumour during its formation or degeneration are frequently inhomogeneous. Therefore, quantifying intra-tumour heterogeneity can provide further insights into tumour characteristics or rapidly flag a change in tumour state within its life cycle. In order to quantify intra-tumour heterogeneity noninvasively, Dr. Sadeghi-Naini is developing novel image-processing techniques to model and analyze the texture within tumour images. He is adapting machine learning techniques to determine how to correspond these textural features to specific tumour characteristics, or to a change that indicates tumour response to treatment.

 

News