Profile:
Brian C. Lovell, born in Brisbane, Australia in 1960, received his BE in Electrical Engineering (Honours I) in 1982, BSc in Computer Science in 1983, and PhD in Signal Processing in 1991, all from the University of Queensland (UQ). Currently, he is the Project Leader of the Advanced Surveillance Group at UQ. Professor Lovell served as the President of the International Association of Pattern Recognition from 2008 to 2010, is a Senior Member of the IEEE, a Fellow of the IEAust, Fellow of the Asia-Pacific AI Association, and has been a voting member for Australia on the Governing Board of the International Association for Pattern Recognition since 1998.
He is an Honorary Professor at IIT Guwahati, India; an Associate Editor of the Pattern Recognition Journal; an Associate Editor-in-Chief of the Machine Learning Research Journal; a member of the IAPR TC4 on Biometrics; and a member of the Awards Committee and Education Committee of the IEEE Biometrics Council.
In addition, Professor Lovell has chaired and co-chaired numerous international conferences in the field of pattern recognition, including ICPR2008, ACPR2011, ICIP2013, ICPR2016, and ICPR2020. His long term project with Sullivan Nicholades Pathology has recently won the National iAwards.
Talk Title:
Revolutionizing Pathology Diagnoses: A Journey from Immunology Microscopy to Fully Automated Imaging
Abstract:
Pathology plays a crucial role in diagnosing diseases worldwide, accounting for 70% of all diagnoses. However, the field faces significant challenges, such as a shortage of senior pathologists and an aging population. To address these issues, a transformative project was initiated to modernize immunology microscopy through the integration of digital imaging and computer vision.
Traditional microscopy techniques in pathology had seen little change over the past 50 years and remained largely not unlike the pioneering work of Louis Pasteur in the 19th century. The initial clinical project focused on digitally processing the ANA-IFF immunology test, which was successfully implemented in 2011, albeit covering only a fraction of the workload. This achievement led to notable benefits, including substantial cost savings in consumables, amounting to $150,000 in reagents and $25,000 in glass annually, and significantly accelerated diagnosis.
Building on this success, the research team secured two ARC grants and a Fellowship, enabling a dedicated effort towards designing a fully automated system capable of handling all microscopy processes and analyzing results. The primary challenge lay in achieving fast and 100% reliable automated image capture, particularly when dealing with challenging specimens at very high magnification, using a x100 oil immersion lens.
This talk will delve into the journey of how innovation and automation in pathology have the potential to revolutionize micoscopy, making it possible to image almost anything fully automatically. The presentation will highlight the milestones reached and the transformative outcomes achieved in bridging the gap between traditional microscopy and cutting-edge digital imaging using AI.