IOMP Webinar Series on AI and ML in Medicine

Prof. Madan Rehani, President, IOMP

Moderator: Prof. Eva Bezak, SG, IOMP

Speakers:

Dr. Johan Verjans
Cardiologist
Royal Adelaide Hospital and Deputy director
Medical Machine Learning
Australian Institute for Machine Learning
Adelaide

Engaging medical professionals, physicists, engineers, and biologists in medical machine learning projects: experience from the Australian Institute for Machine Learning

About the Speaker:
Dr Verjans is a physician-scientist combining cutting-edge research and patient care as a Cardiologist at the Royal Adelaide Hospital. During his research career (PhD Maastricht University, University of California; Post-doctoral fellow, Harvard Medical School), he has predominantly focused on translational pre-clinical and clinical imaging biomarkers using advanced invasive and non-invasive molecular imaging strategies to detect, track and predict disease at an early stage. His recent research has focused on imaging biomarkers from large datasets using supervised and unsupervised machine learning strategies. As Deputy Director of Medical Machine Learning at the Australian Institute for Machine Learning at the University of Adelaide, his main role is to connect world-class machine learning capabilities to the Biomedical Precinct in Adelaide. He is Associate editor of the Netherlands Heart Journal, including editor of a focus issue on Machine Learning in Cardiology. He authored recently the Cardiology chapter for Springer Nature’s first book on Artificial intelligence in Medical Imaging.

Dr. Price Jackson
Senior Medical Physicist
Peter McCallum Cancer Centre
Melbourne

Expanding Quantitative Medicine through AI and Automation.

AI is showing the potential to automate many time-consuming measurements in medical imaging. While efforts to standardise and improve the efficiency of existing manual processes are of great benefit, there is also the potential to apply complex quantitative analyses in routine imaging that would otherwise be too resource intensive to consider for the larger population; often times with a clinical value that is yet unclear. This talk will provide examples of AI organ segmentation as applied to nuclear medicine and radiation oncology with discussion of initiating research work in these areas.

About the Speaker:
Dr Jackson is a medical physicist at Peter MacCallum Cancer centre. He has worked as a post-doctoral researcher supporting their radionuclide therapy service where he developed image-based dosimetry software and protocols. He is currently a clinical radiology physicist and maintains a number of research interests in image analysis which now includes development of neural network tools.

Assoc. Prof. Lois Holloway
Research Medical Physicist
Ingham Institute for Applied Medical Research
Sydney

AI in clinical trials

Clinical trials in radiation oncology require stringent quality assurance to ensure that protocol violations do not impact on the ability to answer the trial question. Consistency in clinical trials is essential to ensuring that we correctly answer the clinical trial question being asked, without this we risk biased results or studies that despite significant time, energy and resources are underpowered to answer the question posed. Manual review to ensure this occurs is an incredibly time consuming exercise and challenging to achieve in a timely manner. There are a number of approaches using artificial intelligence being considered to address these challenges. These include deep learning networks to consider autosegmentation approaches and knowledge based planning approaches which both utilise retrospective datasets to predict likely outcomes on current datasets. As per all artificial intelligence approaches these must be validated carefully.

About the Speaker:
A/Prof Holloway leads the medical physics research group at the Ingham Institute and Liverpool & Macarthur Cancer Therapy centres. She has an interest in learning from ‘large’ datasets and in particular imaging data such that we can make the best decisions for our patients. She leads the OzCAT distributed data learning research program and is a member of the Australian MRI-linac research program.

Dr. Jonathan Sykes
Lead Radiation Oncology Medical Physicist – Research
Sydney West Cancer Network
Sydney

Panel discussion: Speakers + Dr Sykes

About the Panellist:
Dr Jonathan Sykes is an Australia and UK Qualified Medical Physicist with 25 years’ experience in clinical radiotherapy and related research at Western Sydney Local Health District and two of the UKs largest (and leading) cancer centres. He is internationally recognised for research and development in image guided radiotherapy (IGRT) and clinical applications of image registration. He is also an Adjunct Senior Lecturer at the University of Sydney where he lectures on the Masters Medical Physics course and is associate supervisor for 4 PhD and 1 Masters students.