Designing and Implementing an Interactive Cloud Platform for Teaching Machine Learning with Medical Data
摘要
Machine learning (ML), especially deep learning (DL), is a field of research that has recently attracted enormous attention and is currently evolving rapidly. New applications in economics, industry, and healthcare create new challenges for the sustainable development of our society. We describe the organization and realization of a machine learning seminar that integrates a theoretical seminar and a practical tutorial focusing on the employments of DL in liver cancer diagnostics. The seminar has been designed for master students in mathematics and computer science with the aim to prepare them for potential master theses and future work assignments in the area of ML in healthcare. The students were educated in accessing and understanding the information about four different DL architectures provided in scientific publications. They were instructed in implementing these models in the PyTorch framework for image classification and segmentation using publicly available medical data. To offer the students easy access to the necessary computing power, we created a remote development platform based on modern cloud technologies, making fast and efficient training of the models possible. We publish the code for this interactive cloud platform, providing an easy-to-handle, out-of-the-box solution that eliminates the need for high technical literacy among students or the acquisition of hardware. Additionally, we publish the exercises and standard solutions and offer a helpful guide and first-hand experience for future seminars with a similar scope.