Resources & Expertise

Our diverse range of resources and expertise include:

• Prototype design and development

• Patent landscape review

• Data and medical image analysis

• AI integration and application

• Laboratory-scale simulation and representation of real-world scenarios 

• Computational modelling and investigation

• Technical consultation

Pneumocephalus and air travel: an experimental investigation on the effects of aircraft cabin pressure on intracranial pressure

This study, in collaboration with Sunway Medical Centre, investigates the effects of aircraft cabin pressure on intracranial pressure (ICP) elevation of a pneumocephalus patient. We propose an experimental setup that simulates the intracranial hydrodynamics of a pneumocephalus patient during flight. It consists of an acrylic box (skull), air-filled balloon [intracranial air (ICA)], water-filled balloon (cerebrospinal fluid and blood) and agarose gel (brain). The cabin was replicated using a custom-made pressure chamber. The setup can measure the rise in ICP during depressurization to levels similar to that inside the cabin at cruising altitude. This study provides laboratory data that may be used by doctors to advise post-neurosurgical patients if they can safely fly. Read more here. 

Virtual patients: Improving mechanical ventilation treatment in hospitals

The MET hub collaborates with International Islamic University Malaysia to develop model-based methods that potentially offer non-invasive and cost-effective treatment in hospital care. In particular, mathematical models of the patient's physiological system can be developed to describe the patient's condition. For example, retrospective data of mechanically ventilated respiratory failure patient with a virtual patient model can be used for investigation of the effectiveness of a model-based treatment.  The virtual patient model potentially reduces the need for multiple clinical trials that are exhaustive for testing the performance of medical treatment. 

Deep learning-based brain metastases detection using nonlocal networks on MRI images

This research project involves collaboration with Sunway Medical Centre and seeks to demonstrate automatic detection of BM on three MRI datasets using a deep learning-based approach. To improve the performance, the network is iteratively co-trained with datasets from different domains. A systematic approach is proposed to prevent catastrophic forgetting during co-training. The CAVEAT deep learning detection ecosystem alleviated the scarcity of training data in a single dataset with a small FP rate and improved sensitivity. In addition, the proposed method is MRI sequence-agnostic, which is advantageous for clinical applications. Read more about it here.