Course · Medical Faculty · WS 2024/25

AI for Medical Diagnosis and Prediction

This 8-week intensive course provides non-computer science students with the essential skills to apply AI in medical diagnosis and prediction. The course covers topics such as medical image classification, detection, segmentation, and reconstruction, as well as time-series classification, regression, forecasting, and learning techniques like weakly-, semi-, and self-supervised learning. Ethical considerations, fairness, and robustness in AI are also highlighted.

About this course

The course description, objectives, audience, prerequisites, materials and evaluation are the same every semester and live on the course page.

Course Schedule (12 hours per week)

WeekLecture (3 hrs)DescriptionPractical Sessions (3 hrs)
Week 1Introduction to AI in HealthcareOverview of AI in healthcare, challenges, and opportunities.Image classification using CNNs on medical datasets.
Week 2Medical Image SegmentationExplore AI segmentation techniques like U-Net.Implement U-Net for medical image segmentation.
Week 3Object Detection in Medical ImagingObject detection models and challenges in medical images.Implement YOLO/Faster R-CNN on medical datasets.
Week 4Medical Image Reconstruction & Time-Series DataAI techniques for image reconstruction and medical time-series.Time-series classification using RNN/LSTM models.
Week 5Time-Series Forecasting & Weakly Supervised LearningForecasting techniques and weakly supervised learning in healthcare.Apply forecasting models and weakly labeled data.
Week 6Semi-Supervised & Self-Supervised LearningExplore semi- and self-supervised learning.Train models with limited labels using contrastive learning.
Week 7Fairness & Robustness in AI for HealthcareEthical AI, fairness, and robustness in healthcare AI models.Analyze bias and robustness in healthcare datasets.
Week 8Advanced Applications & Final Project PresentationExplore advanced AI applications and wrap-up project presentations.Student presentations and peer review of final projects.