Seeing Through Time: AI Models for Lung Cancer Risk and Diagnosis
Failed to add items
Add to basket failed.
Add to wishlist failed.
Remove from wishlist failed.
Adding to library failed
Follow podcast failed
Unfollow podcast failed
Seeing Through Time: AI Models for Lung Cancer Risk and Diagnosis
-
Narrated by:
-
By:
About this listen
In this episode of VALIANT Pulse, we feature the dissertation work of Thomas Z. Li, who takes on one of medicine’s most pressing challenges: how to predict and diagnose lung cancer with the data we already have. By integrating longitudinal chest CTs and multimodal electronic health records, Li develops a suite of AI models—transformers, joint embeddings, contrastive learning—to predict lung cancer diagnosis and long-term risk. From emphysema quantification to contrastive pretraining, his work explores how to make sense of asynchronous, sparse, and multimodal data with clinical rigor. Join us for an in-depth look at how machine learning might close the diagnostic gap for one of the world’s deadliest cancers. Opinions shared are individual interpretations and not peer-reviewed consensus.