Towards Secure and Intelligent Diagnosis: Deep Learning and Blockchain Technology for Computer-Aided Diagnosis Systems

Abstract: Designing a computer-aided diagnosis framework for automatic cancer diagnosis and grading via an ensemble of deep learning models is an area of active research. The first part of this research focuses on the classification and segmentation of cancerous regions in histopathology images of different cancer tissues by developing models using deep learning-based architectures. Training machine learning models, disease diagnosis and treatment often requires collecting patients' medical data. When a patient sends their data, it loses control of the data, and the privacy of data is dependent on the data requester. These issue makes data owners reluctant to share their personal and medical data due to privacy concerns. Motivated by the advantages of Blockchain technology in healthcare data sharing frameworks, the focus of the second part of this research is to integrate Blockchain technology in computer-aided diagnosis systems to address the problems of managing access control, provenance, and confidentiality of sensitive medical data.

Biography: Sara H. Kassani is a PhD candidate in the Department of Computer Science at the University of Saskatchewan under the supervision of Dr. Ralph Deters and Dr. Kevin Schneider. Her doctoral research has involved developing deep learning models to analyze histopathology images. In particular, she has designed deep learning models for lung, colorectal and breast cancer classification, and segmentation. Now, she conducts research on developing a multimodal modelling of neuroimaging features as well as clinical data to provide a reliable inference framework for Multiple sclerosis (MS) and help uncover the question of how the brain mediates biological constrained and distinct stages of MS progression, including cognitive decline.

January 27, 2021 at 2:00 PM