Trial lecture
Trial lecture 14. December: kl.14.00-14.45.
Title: “Trustworthiness & interpretability/explainability of deep learning for medical data”.
Public defence
The candidate will defend his thesis 15. December at 14.00.
Both trial lectures and disputations will be digital on Zoom (zoom.us).
"Passcode: 122021"
"Webinar ID: 684 9981 8345"
Opponents
- First opponent: Wallapak Tavanapong, Professor, Iowa State University, Department of Computer Science, USA.
- Second opponent: Klaus Schöffmann, Assoc. Prof, Alpen-Adria-Universität Klagenfurt, Austria.
Coordinator commitee
Anis Yazidi. Professor, OsloMet, Faculty of Technology, Art and Design, Department of Computer Science.
Head of the public defence
Laurence Marie Anna Habib, Head of Department, Department of Computer Science.
Supervisors
- Michael A. Riegler, Department of Holistic Systems, SimulaMet, Norway.
- Professor Pål Halvorsen, Department of Holistic Systems, SimulaMet og Faculty of Technology, Art and Design, Department of Computer Science, OsloMet.
- Professor Hugo Hammer, Faculty of Technology, Art and Design, Department of Computer Science, OsloMet
Abstract
Vajira Lasantha Bandara Thambawita summarizes his doctoral project as follows:
Recent advancements in technology have made artificial intelligence (AI) a popular tool in the medical domain, especially machine learning (ML) methods, which is a subset of AI.
In this context, a goal is to research and develop generalizable and well-performing ML models to be used as the main component in computer-aided diagnosis systems. However, collecting and processing medical data has been identified as a major obstacle to produce AI-based solutions in the medical domain.
In addition to the focus on the development of ML models, this thesis also aims at finding a solution to the data deficiency problem caused by, for example, privacy concerns and the tedious medical data annotation process.
To accomplish the goals of the thesis, we investigated case studies from three different medical branches, namely cardiology, gastroenterology, and andrology.
Using data from these case studies, we developed ML models. Addressing the scarcity of medical data, we collected, analysed, and developed medical datasets and performed benchmark analyses.
A framework for generating synthetic medical data has been developed using generative adversarial networks as a solution to address the data deficiency problem.
Our results indicate that our generated synthetic data may be a solution to the data challenge. As an overarching concept, we introduced the DeepSynthBody as a basis for structured and centralized synthetic medical data generation.
The studies presented in the thesis, such as generating synthetic electrocardiogram (ECG), gastrointestinal-tract images and videos with and without polyps, and sperm samples, showed that DeepSynthBody can help to overcome data privacy concerns, the time-consuming and costly data annotation process, and the data imbalance problem in the medical domain.
Our experiments showed that we can generate realistic synthetic data providing comparable results to experiments using real data to tackle the identified problems. The final DeepSynthBody framework is available as an open-source project that allows researchers, industry, and practitioners to use the system and contribute to future developments.