Abstract

The computational advantages of deep learning in AI, integrated with digital pathology for microscopy imaging, has led to the emergence of a new field called Computational Pathology (CoPath) that is poised to transform clinical pathology globally. The field of CoPath is dedicated to the creation of automated tools that address and aid steps in the clinical workflow for diagnosing and treatment of cancer diseases. With increasing advancements of foundation modeling in deep learning and image analytics, the research focus in this field has expanded and branched into a broad range of domains. In this seminar talk I will cover two topics: first, I will present the ongoing research trends in deep learning and computer vision applied in computational pathology by reviewing the benefits and challenges of data scaling for foundational modeling. We investigate this from data preparation, self-supervised learning and downstream tasking for clinical applications. In second topic, I will delve into the ongoing research problems that we are currently addressing in our research lab Atlas Analytics@Concordia. Specifically, I will cover the works related to foundational modeling with different cohort scale of whole slide images, efficient deep learning design algorithms, as well as diffusion generative modeling. In addition, I will introduce the expansion of the Atlas of Digital Pathology (ADP) project and it's deriving applications from novel perspectives. I will conclude this talk with the objectives of discussing challenges in clinics and research for future AI developments in CoPath and how they can facilitate the transformational changes in clinical pathology for cancer diagnostics.

Bio

Dr. Mahdi S. Hosseini is an assistant professor of computer science in department of Computer Science and Software Engineering (CSSE) and a faculty member of Applied AI Institute at Concordia University in Montreal, Canada. He has received his PhD from The Edward S. Rogers Sr. Department of Electrical and Computer Engineering (ECE) at the University of Toronto (UofT) in 2016 from Multimedia Lab under the supervision of Professor Konstantinos N. Plataniotis and completed his NSERC post-doctoral fellowship and MITACS Elevate at UofT prior to his tenure-track stream. Dr. Hosseini's research is primarily advanced in foundational developments of deep learning and computer vision algorithms with focused applications in computational pathology and healthcare technologies. He has extensive knowledge in research and development of digital and computational pathology infrastructures in relation to both industry and healthcare clinics. He is currently supervising 2 PhD, 6 MSc, and 2 UG students on related topics. Dr. Hosseini's vision is to develop, in collaboration with hospitals, healthcare technology and industries, meaningful computer aided diagnosis systems as assistive tools to be integrated in clinical pathology for cancer diagnosis. He is a recipient of prestigious Amazon Research Award (ARA) on Generative AI for Fall 2023 competition. Dr. Hosseini has secured more than $0.7 Million, as PI, to support his research. He has published more than 30 papers and four patent applications in related fields. His reviewing services cover well-known venues in CVF foundation, ML Conferences and IEEE SPS. He is a member of college reviewer for CIHR grants and currently serving as Area Chair (AC) to ECCV2024. He was a previous AC for NeurIPS2023, CVPR2024, CVPR2023 and CVPR2022.