Skip to main content

End-to-End Design of Deep Learning for Computational Pathology | Mahdi S. Hosseini, PhD


For those of you who were unable to join the webinar live, the stream is now available for everyone to watch here or on YouTube.


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 cancer diagnostics. With increasing advancements in deep learning, image analytics, and enabling hardware, the research focus in this field has expanded and branched into a broad range of domains.

In this seminar we present our theoretical advancements in deep learning and computer vision algorithms with focused application in CoPath. We investigate this from both data-centric and model-centric approaches to cohesively relate between “data” and “learning-models” so to effectively design, train, and rationalize our algorithmic decisions.

From data-centric viewpoint we discuss our novel approach in designing tissue taxonomies for comprehensive representation of histology landmarks that are identified from primary organ sites. This builds a new foundation of representation learning problem in CoPath where tissues are labelled in multilabel classification problem; dubbed Atlas of Digital Pathology (ADP) database. We discuss several design approaches of multilabel representation learning from ADP and their diagnostics applications in classification, segmentation, and biomarker discovery patterns.

From model-centric viewpoint we discuss our recent theoretical advancements in deep learning by introducing several generalization measures from deep training regimes and augment them in optimization algorithms for interpretable training and searching of deep network architectures for data representation.

We conclude this talk with the objectives of future research plans and how to derive novel AI solutions that can facilitate the transformational changes in clinical pathology for cancer diagnostics.

Speaker Bio:

Mahdi S. Hosseini is an assistant professor of computer science in department of Computer Science and Software Engineering (CSSE) at Concordia University and a faculty member of Applied AI Institute at Concordia. He 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. He continued as a postdoctoral research fellow at UofT in collaboration with Huron Digital Pathology Inc at Waterloo Ontario. During his postdoctoral study at UofT, he received two fellowships of the MITACS-Elevate Award and NSERC research funding. Dr. Hosseini continues his collaboration with Huron Digital Pathology in the capacity of senior research scientist for transformational changes of digital pathology solutions in clinical healthcare systems.

Dr. Hosseini’s research is primarily advanced in both theory and practice of deep learning and computer vision algorithms in computational pathology applications and healthcare technologies. He is currently supervising several graduate students on related topics and his vision is to develop, in collaboration with hospitals and pathologists, meaningful computer aided diagnosis systems as assistive tools in clinical pathology for cancer diagnostics. He has published more than 30 papers and two patent applications in related fields. Dr. Hosseini’s reviewing services cover well-known venues in CVF foundation, ML Conferences and IEEE SPS. Dr. Hosseini is currently serving as an Area Chair (AC) for Computer Vision and Pattern Recognition (CVPR2023) conference in Vancouver, Canada. He was also a previous AC and a session chair for CVPR2022 in New Orleans, Louisiana, USA.

Back to top

© Concordia University