This course focuses on computational quantification of biologically relevant microscopic structures in biomedical images. Students learn how (i) raw data is acquired before digitization; (ii) to read, display, and interpret various brightfield or fluorescence microscopy image data types using a computer; (iii) to detect, segment, and quantify heterogeneous structures in biomedical images; (iv) to leverage features extracted from biomedical images for classification; (v) to setup experiments in MATLAB via script writing for biomedical image analysis.
This journal club will provide graduate students with the opportunity to further develop their skills in the reading, interpretation, and communication of current scientific research in biomedical AI. Students learn how to read, critically evaluate, and discuss research papers focusing on developing AI pipelines to solve a broad ranges of biomedical research problems, involving novel AI model development as well as AI ethics and trustworthiness. Students also learn how to present the scientific results orally to a broad group of stakeholders of clinical and biomedical AI involving fellow colleagues, lay persons, clinical doctors, and patients. They gain in-depth knowledge about a broad range of biomedical research problems requiring AI to solve and gain insight into how to design pertaining experiments and ask a scientific question. Students learn how to apply AI skills to answer new biomedical questions.