MSc projects

See here for a catalog sketching possible master's thesis projects related to machine learning and medical data analysis. Feel free to contact me if you're interested in more details.

Current MSc projects

• Øyvind Grutle and Jens Andreas Thuestad (2021–2023). Speech-to-text models to transcribe emergency calls (EMCC / 113). Their work is part of the AISMEC project.

Completed MSc projects (main supervisor)

More details about the completed projects can be found in my MSc project catalog.

• Kjetil Dyrland (2020–2022). Evaluation and Improvement of Machine Learning Algorithms in Drug Discovery. His thesis is available here.
• Jostein Digernes and Carsten Ditlev-Simonsen (2020–2022). A workflow-integrated brain tumor segmentation system based on fastai and MONAI. Their thesis is available here.
• Anders Benjamin Grinde and Bendik Johansen (2019–2021). Using Natural Language Processing with Deep Learning to Explore Clinical Notes. Their thesis is available here.
• Malik Aasen and Fredrik Fidjestøl Mathisen (2019–2021). De-identification of medical images using object-detection models, generative adversarial networks and perceptual loss. Their thesis is available here.
• Adrian Storm-Johannessen and Sondre Fossen-Romsaas (2018–2020). Medical image synthesis using generative adversarial networks. Their thesis is avaible here.
• Sivert Stavland (2018–2020). Machine learning and electronic health records. His thesis is available here.
• Sindre Eik de Lange and Stian Heilund (2017–2019). Autonomous mobile robots: Giving a robot the ability to interpret human movement patterns, and output a relevant response. Using advanced computer vision techniques (graph convolutional neural networks), and the Robot Operating System, the project investigated the potential of constructing robotic physical therapist for patient rehabilitation. They presented part of their work at EHiN 2018 in Oslo Spektrum, and at Christiekonferansen 2019. Their thesis is available here.
• Sathiesh Kumar Kaliyugarasan (2017–2019). Deep transfer learning in medical imaging. A study of how to best use transfer learning when training deep neural networks for biomedical image analysis. Sathiesh presented part of his work at NVIDIA's GTC Europe 2018 in Münich, at EHiN 2018 in Oslo Spektrum, and at Christiekonferansen 2019. His thesis is available here.
• Sean Meling Murray (2017–2018). An Exploratory Analysis of Multi-Class Uncertainty Approximation in Bayesian Convolutional Neural Networks. Sean developing and explored new techniques for obtaining robust uncertainty estimates for deep neural networks. His thesis is available here.

BSc projects

• Bendik Mathias Johansen and Kathinka Neteland (2019). Automating Reports on Water Consumption and Availability. A data science project together with Bouvet and Bergen Vann. The students created a system for producing weekly reports on water consumption and availability in Bergen, using Azure and Power BI.
• Jon Einar Haraldsvik, Stian Gudvangen Gjerløw, Didrik Fanuelsen Tranvåg (2015). Tryg Maintenance App – A cross-platform application using Appcelerator Studio Cloud Services and Arrow DB. The students developed a cross-platform mobile application for Tryg Forsikring. The project was awarded "best bachelor project" at the department in 2016. The students went on to start Appivate AS.

Current courses

I have established several new courses and course modules with two main goals: (i) teach our students in software engineering about machine learning engineering (DAT158, DAT255, PCS956-DL) and (ii) establish the field of Medical AI in Bergen, targeting students & researchers at the interface of medicine and technology (ELMED219, DLN-AI and others):

• DAT158: Machine learning engineering and advanced algorithms. A practical, project-based, hands-on exploration of the fundamentals of machine learning, focusing on applications of machine learning and the core software engineering principles for successful deployment of machine learning models.
• DAT255: Deep learning engineering. MSc course on practical applications of deep neural networks and the construction of deep learning-based software solutions.
• DAT801: Maskinlæring og data science for forretningsutvikling. The course is part of the program Teknologi for forretningsutvikling at HVL and UiB. It is aimed at managers and employees from the regional business community.
• ELMED219 is an elective course on computational medicine at the University of Bergen medical school. A collaboration between the Department of Biomedicine, University of Bergen, Department of Computing, Mathematics and Physics, Western Norway University of Applied Sciences, and Mohn Medical Imaging and Visualization Centre, Department of Radiology, Haukeland University Hospital. The course is offered to both medical students and engineering students and encourages collaborations between these disciplines, motivated by e.g. "The convergence revolution". Course website: ELMED219 @ MittUiB. Course code repository: https://github.com/MMIV-ML/ELMED219-2022. The course got some publicity during its first run. It was mentioned in the Norwegian government's "Nasjonal strategi for kunstig intelligens", in Teknologirådet's report on "Artificial Intelligence: Opportunities, Challenges and a Plan for Norway", in a hearing at Stortinget on "Langtidsplan for forskning og høyere utdanning 2019-2028", at forskning.no and the Faculty of Medicine newsletter.
• HVL-MMIV-DLN-AI A hands-on course on artificial intelligence in computational biotechnology and medicine. The course is part of the Digital Life Norway Research School portfolio. Course website: https://github.com/MMIV-ML/HVL-MMIV-DLN-AI-2022.
• DAT259-2022: Natural language processing. Offered to MSc students in our software engineering program.
• PCS956: Research Trends in Applied Machine Learning. I'm responsible for a module on deep learning. Module website PCS956-DL-2021.
• MMIV-DLN-AI A hands-on course on artificial intelligence in computational biotechnology and medicine. The course is part of the Digital Life Norway Research School portfolio. It was given for the first time in the spring of 2021. Course website: https://github.com/MMIV-ML/MMIV-DLN-AI-2021.

I'm also involved in HELIKT620: Health Care Informatics, a Continuing Education course at the University of Bergen. Topic: Artificial intelligence for natural language processing and speech recognition.

Past courses

• DAT259 – Medical data analysis and deep learning, spring 2019 and 2020.
• MAT106 – Videregående matematikk for elektroingeniører, spring 2019.
• DAT158: Machine learning and advanced algorithms. Fall 2018.
• DAT259 – Practical deep learning, spring 2018.
• MAT106 – Videregående matematikk for elektroingeniører, spring 2018.
• MAT100 – Grunnleggende matematikk for ingeniører, fall 2017, for students in the electrical engineering programs "Elkraftteknikk" and "Kommunikasjonssystemer"
• MAT106 – Videregående matematikk for elektroingeniører, spring 2016, for students in the electrical engineering programs "Elkraftteknikk" and "Kommunikasjonssystemer"
• BMED360 – In Vivo Imaging and Physiological Modelling, spring 2016
• MAT100 – Grunnleggende matematikk for ingeniører, fall 2015, for students in the electrical engineering programs "Elkraftteknikk" and "Kommunikasjonssystemer"
• MAT106 – Videregående matematikk for elektroingeniører, spring 2015, for students in the electrical engineering programs "Elkraftteknikk" and "Kommunikasjonssystemer"
• MAT100 – Grunnleggende matematikk for ingeniører, spring 2015, for students in the computer science engineering program "Dataingeniør"
• MAT100 – Grunnleggende matematikk for ingeniører, fall 2014, for students in the engineering programs "Produksjonsteknikk" and "Allmenn maskinteknikk"

I've created supporting e-learning material for multiple courses MAT106x, BMED360x, ELMED219x, NordBiomed, financed by the Erasmus+ KA2 strategic partnerships MedIm and HVL. To deliver these and other courses I set up the e-learning platform AkademiX, hosted on AWS. The platform is not currently operational.

From 2011 to 2013 I gave the following courses at the Norwegian University of Science and Technology, mainly to students in engineering programs:

• TMA4125 – Matematikk 4, spring 2013
• TMA4100 – Matematikk 1, fall 2012
• MA0002 – Brukerkurs B, spring 2012
• TMA4100 – Matematikk 1, fall 2011

I have been a substitute lecturer in MAT212 – Functions of several variables at the University of Bergen in 2010, and in Les algèbres de Hopf combinatoires en théorie quantique des champs perturbative, Université de Strasbourg, 2009