sitem Center for Translational Medicine and Biomedical Entrepreneurship

Standalone Modules

Module 4 - Applied AI in Medical Imaging

 

Content

Participants will learn about the relationship between a clinical problem and a machine learning problem as well as the influence of training data quality and annotation errors on the ability of algorithms to learn. Participants will be introduced to state-of-the-art AI models and learn how to apply and validate them in practice.

Learning objectives

Once participants have successfully completed this module, you have an understanding for:

  • The formulation of a clinical problem as a machine-learning problem The challenges and practicalities of assembling a training set of medical images
  • The tradeoffs between manual or automatic labelling of training data How to select a state-of the art model, and have hands-on expe-rience training such a model
  • Selecting and applying appropriate metrics for the performance of a medical AI system and have gained hand on experience
  • How the results of validating a machine-learning model may affect design choices in a subsequent experiment

Learning content

This module covers a wide range of aspects, such as the introduc-tion to image classifiers, ChexNet dataset, image segmentation and Decathlon datasets, labeling of image data, automatic vs. manual methods, adapting existing code to a new problem: classification
It further contains the modern CNN architectures explained, adap-ting code to a new problem: segmentation, Deep Learning Classi-fiers versus old fashioned modelling, interpreting model perfor-mance, and issues in adapting code, 3D data, multimodal data, modern deep learning

Start & Duration

2020: 11 February 2021
2021: TBC

The completion of this module takes approximately 6 weeks.

Credits

3 ECTS

Fee

The cost of this standalone module is 2'400.– SFr.

Reference

02.004

 

Module Leaders

Senior Researcher, Support Center for Advanced Neuroimaging,University Hospital Inselspital, Bern

Dr. Richard McKinley

Richard McKinley is a Senior Researcher at the Support Centre for Advanced Neuroimaging, a research group in the University Clinic for Diagnostic and Interventional Neuroradiology in the Inselspital. Since 2014 he has been a researcher at the Inselspital, where he develops machine-learning techniques for interpreting, labeling and quantifying neuroimaging.

Vice Chair and Associate Professor, Department of Diagnostic, Interventional and Pediatric Radiology Inselspital, University of Bern

Prof. Dr. Hendrik von Tengg-Kobligk

Venia docendi (Habilitation) in 2012. Since 2013, Vice Chair, Department of Diagnostic, Interventional and Pediatric Radiology, Inselspital. Since 2014, Group Leader, Radiology Laboratory, Department of Clinical Research, University of Bern. Associate Professor at University of Bern since 2016. Since July 2017, Chief Attending Physician, covering sub subspecialities of Emergency Medicine, Thoracic-Cardiovascular Imaging and Imaging Laboratory.

Head of Lab for Artificial Intelligence and Translational Theranostics at Dept. Nuclear Medicine, University of Bern & Senior Scientist at Chair for Computer-aided Medical Procedure, Dept. Informatics, Technical University of Munich

Prof. Dr.-Ing. Kuangyu Shi

Prof. Dr.-Ing. Kuangyu Shi is head of Lab for Artificial Intelligence and Translational Theranostics at Dept. Nuclear Medicine, University of Bern, Switzerland and senior scientist at Chair for Computer-aided Medical Procedure, Dept. Informatics, Technical University of Munich (TUM), Germany.  He is currently in editorial board of Eur J Nucl Med Mol Imaging, EJNMMI Res, Nukearmedizin and J Med Artif Intell and served as reviewers of several medical and engineering journals, e.g. IEEE Trans Med Imaging, Med Image Anal, Meds Phys, Phys Med Biol, Theranostics, J Nucl Med.