Robotic Knee Arthroscopy – Medical and Health Robotics Group, QUT. (October 2014 – to date)

Knee arthroscopy is a well-established, minimally invasive, diagnosis and treatment procedure of knee disorders and injuries. With the number of estimated worldwide cases exceeding 4 million each year, knee arthroscopy costs the healthcare system over 15 billion dollars annually. The procedure involves gaining access into the knee joint using sharp instruments to make ports/entry points. Through these points, the arthroscope is then inserted. Images from the arthroscopic camera are magnified and displayed on a monitor for the surgeons to view, examine and then rectify the damage using shaving or sharp instruments.

Despite its efficacy, there are reported complications that range from the minute to the more debilitating. The reasons behind these problems are multifactorial but can be grouped into operator inexperience, rigid anatomy, poor intra-articular vision and lack of a tissue demarcation between diseased and healthy tissue. However, we have a solution.

Our research is developing robotic knee arthroscopy techniques and devices to improve clinical outcomes for patients and reduce the cost of arthroscopy procedures and promoting a sustainable health care system. The aim is to develop techniques and systems to enable surgeons to routinely step out of the control loop of a number of surgical procedures and allow robots to carry out direct actions on patients. This will give the surgeon the role of supervisor rather than controller. Particularly, research will develop robotic vision systems that are capable of mapping knee joints in real-time via arthroscopically sourced video streams. The research will also explore control schemes that allow robots to hold and manipulate both the arthroscope and the surgical tools.

Diagnostic testing of malaria using deep learning – Medical and Health Robotics Group, QUT. (October 2014 – to date)

This research will develop a cost-effective, fast and consistently accurate, universal diagnostic testing technique for Malaria using a cheap imaging device (a smart phone). This will be achieved by combining state-of-the-art computer vision and machine learning techniques (deep convolutional neural networks) with advances in mobile technology and camera imaging.

About half of the world’s population are at risk of malaria. In 2012, an estimated 627,000 people died of malaria [WHO]. Most victims of malaria die because the disease is not diagnosed in time by health workers. Therefore, early (within a few hours of blood collection/early stage of infection) and accurate diagnosis of malaria is essential before antimalarial treatment is administered for effective disease management. This will also reduce the emergence and spread of drug resistance by reserving antimalarials for those who actually have the disease and aid efficient malaria surveillance and optimal use of resources.

This novel solution will pair some very cheap and easy to manufacture high-magnification microscopy hardware with any camera enabled smart phone. This combination will enable the examination of blood samples using software based on the latest advances in computer vision and pattern recognition to detect malaria parasites (the stage, species and density). As opposed to some prior proposed approaches, from LifeLens and Athelas, our solution will run on any smart phone without the need for a network connection. However, as the proposed solution will be based on smart phones, there will also be the option of uploading the results to health care professionals for further analysis when a network is available.

Improved healing in large segmental bone defects in small animals under the influence of BMP2 – Trauma Group, Institute of Health and Biomedical Innovation, QUT. (Feb 2014- Sept 2014)

Role of osteocytes (bone cell) in Osteoarthritis – Bone Group, Institute of Health and Biomedical Innovation, QUT. (October 2010 – Dec 2014)

TCam-2 cells as a viable in vitro model of testicular cancer – Department of Anatomy and Developmental Biology, Monash University, Monash Univerisy. (Aug 2008 – Feb 2010)