SMS scnews item created by Dario Strbenac at Wed 10 Jun 2020 0935
Type: Seminar
Distribution: World
Expiry: 16 Jun 2020
Calendar1: 15 Jun 2020 1300-1400
CalLoc1: Zoom videoconferencing https://uni-sydney.zoom.us/j/2706664626
CalTitle1: Maths is Core to Cancer Care / AI for Biomedical Image Analysis
Auth: dario@210-1-221-196-cpe.spintel.net.au (dstr7320) in SMS-WASM

Special Event: Statistical Bioinformatics and AI for Cancer Care Joint Webinar: Fernandez-Penas and Kim

Maths is Core to Cancer Care: The Melanoma Case, Prof. Pablo Fernandez-Penas
(Dermatology) 

In clinical care, we use numbers to understand most of the biology components of the
human being and decide diagnosis and treatments. Measures such as blood pressure or
glucose levels have been around for too many years. But there has been areas that have
escaped to quantification and analysis, and one of the most critical ones for skin
cancer and melanoma in particular is imaging. Dermatology is a visual specialty that
relies on the skills of humans to make diagnosis. To add more complexity, if clinicians
can’t make a diagnosis, the biopsies they take to help them are read by humans using,
again, their visual skills. The time is coming for a more objective, quantifiable
measurements to help with these visual challenges, and for this information to be
combined with other sources of clinical data.  

AI for Biomedical Image Analysis - Experiences with Skin Lesion Images, Assoc. Prof.
Jinman Kim (School of Information Technologies) 

Medical imaging has an indispensable role in patient management in modern healthcare.
There are numerous medical imaging modalities available; they vary in complexity and
’sophistication’ from plain digital chest X-rays to simultaneous functional and
anatomical imaging with positron emission tomography (PET) and computed tomography (CT)
imaging (PET-CT) using the one device. The challenge is now on how to maximize the
extraction of meaningful information from the images while not overloading the user.
Fortunately, in parallel to the imaging improvements, we are in an era of artificial
intelligence (AI) fuelling the growth of smart decision support and analysis tools for
medical image interpretation. In a matter of few years, we have seen rapid rise in
research algorithms being integrated to computed aided diagnosis (CAD) systems for
clinical use. Yet, from an engineering view, we are only at the infancy of the AI
revolution towards healthcare. This talk will present the trend in AI development for
medical images, with examples on our research in skin lesion image analysis.