Artificial Intelligence in Medicine

• Introduction: Clinical motivation, clinical data, clinical workflows
• ML for medical imaging
• Data curation for medical applications
• Domain shift in medical applications: Adversarial learning and Transfer learning
• Self-supervised learning and unsupervised learning
• Learning from sparse and noisy data
• ML for unstructured and multi-modal clinical data
• NLP for clinical data
• Bayesian approaches to deep learning and uncertainty
• Interpretability and explainability
• Federated learning, privacy-preserving ML and ethics
• ML for time-to-event modeling, survival models
• ML for differential diagnosis and stratification
• Clinical applications in pathology/radiology/omics

At the end of the module students should be able to recall the important topics in the area of artificial intelligence in medicine, understand the relations between the topics, apply their knowledge to own deep learning projects, analyse and evaluate social and ethical implications and develop own strategies to apply the learned concepts to their own work.

Introduction to Deep Learning (IN2346)
Computer Aided Medical Procedures I (IN2021)

Lecture, tutorial, problems for individual study. Guest lectures will be held by experts from local hospitals and med-tech companies to ensure that the covered topics are relevant for clinical practice. Assignments are provided on a weekly basis via the teaching portal and will be aligned to the lectures and tutorials in terms of content. They are discussed in the next tutorial class, and a solution is presented. Work on the assignments and participation in the tutorial class are voluntary. They serve as a means for students to deepen and test their acquired knowledge – as a self-monitoring aid to prepare for the written exam.

Slide show, blackboard

Recommended:
1. I. Goodfellow, Y. Bengio and A. Courville. Deep Learning. MIT Press, 2016. Available at http://www.deeplearningbook.org
2. E. J. Topol. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25, 44–56, 2019. https://doi.org/10.1038/s41591-018-0300-7
3. A. Esteva, K. Chou, S. Yeung, et al. Deep learning-enabled medical computer vision. npj Digit. Med. 4, 5, 2021. https://doi.org/10.1038/s41746-020-00376-2
4. B. Norgeot, G. Quer, B.K. Beaulieu-Jones et al. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. Nat Med 26, 1320–1324 (2020). https://doi.org/10.1038/s41591-020-1041-y
5. V. Sounderajah, H. Ashrafian, R. Aggarwal et al. Developing specific reporting guidelines for diagnostic accuracy studies assessing AI interventions: The STARD-AI Steering Group. Nat Med 26, 807–808 (2020). https://doi.org/10.1038/s41591-020-0941-1

Optional
6. E. Topol. Deep Medicine - How Artificial Intelligence Can Make Healthcare Human Again. 2019.

The exam takes the form of a written test. The duration is 90 minutes, and no material is allowed (closed book). Questions allow to assess whether the student is able to understand fundamentals, differences and application areas of Artificial Intelligence in Medicine as well as methods for computer-aided diagnosis and decision making. Using practical case studies will assess whether the student is able to select an appropriate artificial intelligence or machine learning approach for a given application. All problems and questions demand the students to phrase their individual responses.