Technology research

The Radiology Informatics Lab develops educational resources, new technology and advanced workflows to drive discovery and innovation in radiology informatics.

Some of the lab's projects are outlined below.

Educational tools to learn and use AI in radiology

Deep learning and artificial intelligence (AI) are growing fields in radiology. Many new researchers need resources for best practices and tutorials for AI. The lab is developing the necessary materials and resources.

MIDeL

MIDeL helps healthcare professionals and medical-imaging scientists use deep learning technologies for medical images. It is an extensive electronic textbook that seamlessly combines rich textual content with practical code examples. This approach creates a learning environment that allows users to understand how to apply deep learning techniques in medical imaging.

Learn more on the MIDeL GitHub page.

Noise reduction AI models for molecular breast imaging

The lab is developing AI models to lower the radiation dose of molecular breast imaging and shorten scan time. Shorter scan times reduce the signal-to-noise ratio in molecular breast imaging, making images harder to evaluate and making it easier to miss cancers.

The research team is finding techniques to remove noise that can boost the signal-to-noise ratio. This will lead to more accurate diagnoses with less exposure to radiation.

Reducing scanning time for secondary breast cancer screening

This project is developing deep learning methods to reduce molecular breast imaging scan time while preserving image quality, improving patient comfort without compromising diagnostic performance.

Predicting breast cancer risk using mammography and genetics data

This project integrates imaging and genetic data to predict breast cancer before it develops. This will enable earlier detection and more tailored screening and treatment strategies.

Synthetic data generation to improve fairness and reduce assumptions

Synthetic image data may be able to generate viable images of people from understudied groups. This will help ensure that diagnostic AI models that are trained on research data plus synthetic data are more accurate and better represent all people.

Fairness and demographics in radiology foundation models

As AI models become widely adopted in radiology, understanding whether they implicitly encode protected demographic attributes and how this affects equality across patient subgroups is essential before clinical deployment. This project quantifies demographic encoding across a range of AI models used in radiology and explores synthetic image generation as a strategy to mitigate assumptions.

Tabular medical data imputation

The lab is developing a model to impute missing data in large medical tabular datasets.

Using topological data analysis in medical-imaging research

Topological data analysis is revolutionizing medical imaging, offering nuanced insights into complex data structures. The lab is developing topological data analysis resources for aspiring researchers, including specialized courses, practical software tools and community forums. These resources will contribute to a full understanding and application of topological data analysis and advance medical imaging technologies and methodologies.