Video Healthcare
Globally, the access to healthcare has been steadily increasing over the last decades. Combined with the rapid development of medical sensing technologies, this leads to an enormous amount of patient data with an unprecedented level of detail. Artificial intelligence is playing an increasingly important role in processing and analyzing this data to support medical specialists in the diagnosis and treatment of disease. Besides alleviating the burden of interpreting large volumes of data, AI is much better suited than humans to find subtle patterns in large data sets of multi-modal medical data, leading to new insights and a more efficient and effective healthcare system. Especially with the increasingly complex signals that novel imaging modalities are able to capture, AI plays an essential role in fully exploiting the information contained in those signals.
Next to data analysis, the combination of modern AI with an understanding of the image acquisition process enables better medical imaging, e.g. faster MRI scans or high-quality CT scans with a lower dose of harmful radiation. These developments can even be taken one step further by giving the AI an active role during the sensing process, further optimizing medical scanners. Also, during medical procedures and treatment, AI can support medical specialists, in e.g. surgical navigation and treatment response monitoring. Furthermore, enriching biological models with AI can help in finding the optimal treatment path, further personalizing them by incorporating omics-data.
It is evident that AI will be an essential technology in the future hospital and in this track of the master program AI&ES, we will focus on the necessary knowledge and skills for driving this development.
What you will learn
- Medical image analysis using computer vision and machine learning (e.g. Computer-aided detection and diagnosis).
- The basic principles of medical imaging methods such as CT, MRI and ultrasound, and how AI could be leveraged to enhance them.
- Robotics and AI for assistive devices (hearing, speech, rehabilitation).
- AI for computer-assisted interventions to support e.g. surgical procedures.
- Predictive modelling for treatment response.
- Remote patient monitoring and anomaly detection.
- Efficient methods to harness information from large medical data sets (e.g. self-supervised learning, transfer learning and federated learning).
- Explainable AI for efficient communication of AI findings with medical experts.
- Trustworthy and self-critical AI.