top of page

Publications

AI applications in medical imaging
人工智能於醫學影像中的應用

Dr Vince Varhanabhuti
Clinical Assistant Professor
Department of Diagnostic Radiology
LKS Faculty of Medicine, HKU
 

 

Over the past few years, we have witnessed rapid advancement in the use of artificial intelligence (AI) in areas from navigation, to self-driving cars, to predictive modelling of a person’s behaviour, and more recently this has been applied to healthcare. Because medical imaging has been in digitised formats since the 1980s, this makes it highly suitable for AI applications, and therefore radiology is one of the earliest medical disciplines to pursue AI applications. There are several use cases now in the medical literature. The most commonly known examples where AI has been utilised include chest x-ray diagnosis and mammograms for breast cancer screening.

In the department of diagnostic radiology at HKU, we have been leading the research in applying machine learning and artificial intelligence to medical imaging. We have done some work on using this technology to detect abnormalities on chest CT, brain CT, brain MRI. We have also developed machine learning models with the use of quantitative imaging techniques to predict disease recurrence in cancer patients. We have applied this to liver, nasopharyngeal and oesophageal cancers to name a few. More recently, we have also been applying deep learning for COVID-19 detection on chest X-rays. 

However, with rapid advancement comes the need for proper and rigorous clinical validation, ensuring patients’ clinical benefit is realised in the real-world. This process is often called clinical validation and is the cornerstone to ensure clinical translation. At HKU Department of Diagnostic Radiology, we have been performing several ‘real-world’ clinical validation studies. For example, we have recently completed a study comprising of over 1400 subjects in eye imaging screening which validated the use of AI technology for automated diagnosis of eye diseases. Another study included looking at the human and AI interaction when a radiologist is presented with the task of reading CT scans with the input of AI as assistance. In this study, we tried to establish if the AI finding influences decision making, and what is the best mode of collaboration between AI and human radiologist. The perception of AI technology is also important and how patients react or modify their behaviours to AI technology regarding their health status has still largely not been investigated. These are some of the areas for future investigations in our departments.

There is no doubt that AI technology to healthcare will be disruptive, and we strive to remain at the forefront in these areas of research so that we can ensure the benefits to Hong Kong patients.

 
<posted on《am730》, 7th June 2021>

Keeping Humans in the Loop

Dr Vince Varhanabhuti
Clinical Assistant Professor
Department of Diagnostic Radiology
LKS Faculty of Medicine, HKU
 

 

Robo-doctors are still the domain of science fiction. But researchers in engineering and medicine are developing human-controlled advanced technologies that will improve healthcare.

The promise of robotics in healthcare is often equated with the development of self-driving cars. The latter technology has accelerated and these cars are now being tested on roads, although not without challenges. Could we one day have autonomous medical droids performing surgery, like those seen in the Star Wars movies?

Not for a long time yet, caution researchers. Although robotics and artificial intelligence (AI) technologies are being applied in medicine, humans remain firmly in the picture.

“Many people think AI will replace clinical duties, especially those of the radiologist who reviews and interprets medical images. But we can’t look forward to this any time soon,” said Dr Kwok Ka-wai of the Department of Mechanical Engineering, who specialises in surgical robotics, AI and related systems.

“Taking the driver out of a car is easy in comparison. Taking out a clinician is a lot more difficult.”

That is because there are many more hurdles to overcome, says Dr Vince Vardhanabhuti of the Medical Faculty’s Department of Diagnostic Radiology, who uses big data and analytics in his research. Medical decisions are based on a wide variety of data – not just medical images but laboratory tests, pre-existing conditions, gender, age and a host of other factors. Plus, there is the liability factor.

“Who is responsible when AI gets it wrong? At the very least, this is why doctors need to remain in the loop with overall responsibility until such times when people can fully trust AI. I think we are still a long way from that,” he said. “In the short term, I think it is more likely that AI and humans will work in collaboration – the AI will be used as a team member, a bit like in the multidisciplinary collaborative teams that we now see in medical practice.”

To that end, the two scholars and their teams have been developing ways to use robotics and AI alongside humans to improve diagnosis and treatment......

Join our mailing list for updates on publications and events

Thanks for submitting!

Address:

Room 406, Block K Queen Mary Hospital, Pokfulam Road Hong Kong SAR, China

Tel:

852-2255 3307

Copyright © 2019 - All Rights Reserved - Department of Diagnostic Radiology, The University of Hong Kong

bottom of page