Introduction to deep learning for medical image analysis
AI techniques such as deep learning are increasingly seen as powerful tools to address many complex problems in pathology and radiology workflows involving image segmentation and classification. MathWorks understands that success goes beyond just developing a deep learning model. Ultimately, models need to be incorporated into an entire system design workflow to deliver a product or a service to the market.
In this technical talk, we'll explore in detail the workflow involved in developing and adapting a deep learning algorithm for a medical image classification or segmentation problem using real-world case studies such as Left-Ventricle (LV) segmentation from cardiac MRI images.
- Import and manage large sets of images
- Perform semi-automatic ground truth labeling
- Build networks from scratch with a drag-and-drop interface
- Efficiently train and evaluate a semantic segmentation algorithm on CPUs and GPUs
- Automatically generate optimized embedded code to deploy on a medical device
Who Should Attend
- Software and hardware engineers
- Data scientists
- Innovation leaders
- Project managers and technical managers
About the Presenters
As an application engineer at MathWorks in Munich, Germany, Sebastian Bomberg supports customers in implementing artificial intelligence projects. For instance, he develops applications for image classification and object detection. To this end, he uses techniques from deep learning as well as cloud computing and GPU computing. Sebastian Bomberg holds a Dipl.-Ing. degree from Technische Universität München, where he also worked as a researcher.
Dr. Christoph Kammer is an application engineer at MathWorks LFT Benelux and Switzerland. He supports customers in many industries focusing on machine and deep learning, image and signal processing and deployment to embedded or enterprise systems. Christoph has a master’s degree in Mechanical Engineering from ETHZ and a PhD in Electrical Engineering from EPFL, where he specialized in optimization and control design as well as the control and modelling of power systems.