Statistical Methods for Health Equity Webinar: Ira Ktena (Google DeepMind)
Thu, 13 Jul
|Zoom
Domain generalisation in healthcare machine learning is a challenge due to data discrepancies, but generative models can address underrepresentation and improve model performance.
Time & Location
13 Jul 2023, 16:00 – 17:00
Zoom
About the event
The Statistical Methods for Health Equity Series is a monthly online series co-hosted by the Data Science for Health Equity community, the Alan Turing Institute Health Equity Interest Group, and the Department of Statistical Science at University College London.
---
For our next webinar, we're delighted to welcome Ira Ktena from the Google DeepMind who will be joining us to explore some discussions around understanding how we can use generative models in healthcare to address underrepresentation of data and improve performance of machine learning models
Specific details on the topic are as below:
Topic:Â
Diffusion models for medical imaging: the path to fairer, more robust and private models
Abstract:
Domain generalization remains a ubiquitous challenge for machine learning for healthcare, where model performance in real-world conditions is lower than expected due to discrepancies between the data encountered in deployment environments and datasets used for model development. Underrepresentation of some groups or conditions during model development is a common cause of this phenomenon. In this talk, we will show that advances in generative models can help mitigate this unmet need in a steerable fashion, algorithmically enriching our training dataset with synthetic examples that address shortfalls of underrepresented conditions or subgroups. We will show that generative models can automatically learn realistic augmentations from data in a label-efficient manner. We will further discuss how differential privacy can be used to protect diffusion models from risks such as membership attacks, while still producing synthetic images that are useful for downstream tasks.
Ira Ktena is a Senior Research Scientist at Google DeepMind, working on Deep Learning for Healthcare. Her research interests span a broad range of topics with a strong focus on model robustness, fairness and multimodal representation learning. Prior to that she worked on graph representation learning for neuroimaging at Imperial College London and Harvard Medical School, where she collaborated with the Stroke Group at Massachusetts General Hospital on early outcome prediction.
--
Please direct any questions about the webinar series to Dr Brieuc Lehmann at b.lehmann@ucl.ac.uk.
Tickets
Event Ticket
£0.00Sale ended
Total
£0.00