Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore cutting-edge AI architectures that combine multi-modal foundation models with generative modeling for precision oncology in this conference talk. Learn how researchers are developing AI systems that move beyond traditional diagnosis and analysis to become predictive simulators of disease and therapy. Discover innovative approaches to capturing cancer complexity by learning across biological scales, from molecular interactions to tissue architecture, using principles from multi-modal representation learning and large-scale vision models. Understand how proteomics, pathology, and clinical annotations can be integrated into a unified virtual patient space through unsupervised learning and multi-scale neural network design tailored to high-dimensional multiplexed imaging. Examine how these representations enable consistent mapping of new biopsy samples and biomarker discovery while supporting downstream analyses of molecular, morphological, and spatial complexity. Investigate the extension of these frameworks with generative modeling to predict therapeutic responses, resistance dynamics, and enable in silico exploration of treatment outcomes. Gain insights into the broader vision of Virtual Patient Labs as digital counterparts of patients, where integrative models and generative simulation converge to anticipate disease trajectories and treatment responses, making in silico experimentation possible at patient scale and opening new avenues for AI-guided decision support in oncology.
