Signals in the Noise: Multimodal AI for Smarter Diagnosis

In this episode of VALIANT Pulse, we feature the dissertation work of Can Cui at Vanderbilt, who pushes the frontier of machine learning in healthcare by tackling the complex challenge of multimodal data. From deep brain stimulation planning to cancer diagnosis with missing data, Cui’s work spans nine projects and modalities—from MRI and histopathology to genomics and free text. Central to this dissertation is the drive to make AI flexible, interpretable, and resilient—capable of thriving even when data is incomplete or labels are weak. Tune in to learn how multimodal fusion, prompt-guided segmentation, and self-supervised learning are changing the rules for clinical decision-making. The interpretations presented reflect scholarly insight, not peer-reviewed consensus or official clinical guidance.