Generating and analyzing Synthetic data for DeepSynthBody.org
Collecting and annotating medical domain data is time-consuming and costly. However, deep learning algorithms depend on high-quality datasets and annotations. In this regard, synthetic data shows promising directions to overcome this data deficiency problem in the medical domain. DeepSynthBody (DeepSynthBody.org) is the beginning of such an open-source project aiming at providing high-quality synthetic data.
The following sub-projects are available under this big project:
Sub-project 1: Generating medical data using Generative Adversarial Networks
Sub-project 2: Generating medical data using Diffusion Models
Sub-project 3: Conditional GANs and Diffusion models
Implement, train and evaluate different deep generative models for generating synthetic data for a selected medical dataset.
- Interdisciplinary research
- Machine learning / AI (deep generative models)
- Performing research with advanced deep learning algorithms
- Interested in learning (the rest can be learned during the thesis work)
- Pål Halvorsen
- Michael Riegler
- Vajira Thambawita
- Analyzing and Improving the Image Quality of StyleGAN
- DeepSynthBody: the beginning of the end for data deficiency in medicine