Imaging Science Seminar: Multispectral Analysis and Deep Learning for Life Science and Biomedical Research

Imaging Science Seminar
Multispectral Analysis and Deep Learning for Life Science and Biomedical Research

Dr. Corey Toler-Franklin
Assistant Professor
Computer Science
University of Florida

Register Here for Zoom Link

Dr. Toler-Franklin will present novel non-photorealistic illustrative techniques that compute normals at different material layers as a function of emission wavelength. She will demonstrate the effectiveness of the acquired shape for scientific analysis with a comprehensive user study with experts from life science disciplines. She will then discuss a texture transfer framework that extends this work to reconstruct invisible (or faded) appearance properties in organic materials with complex color patterns.

Abstract:
Several plant and animal species are more comprehensively understood by multispectral analysis. For example, ultraviolet fluorescence reveals original color patterns on colorless fossils for species classification, while Infrared imaging permits study of subsurface materials hidden under pigments or dyes. However, accurate shape recovery of biological materials is challenging due to subsurface scattering and spatially varying surface reflectance. I will present novel non-photorealistic illustrative techniques that compute normals at different material layers as a function of emission wavelength. I will demonstrate the effectiveness of the acquired shape for scientific analysis with a comprehensive user study with experts from life science disciplines. I will then discuss a texture transfer framework that extends this work to reconstruct invisible (or faded) appearance properties in organic materials with complex color patterns. Key contributions include a novel ultraviolet illumination system that records changing material property distributions, and a color reconstruction algorithm that uses spherical harmonics and principles from chemistry and biology to learn relationships between color appearance and material composition and concentration. Finally, I will explain a novel algorithm that extends the effective receptive field of a convolutional neural network for multi-scale detection of cancerous tumors in high resolution slide scans. The results permit efficient real-time analysis of medical images in pathology and related biomedical research fields.

Speaker Bio:
Corey Toler-Franklin is an Assistant Professor of Computer Science at the University of Florida where she directs the Graphics, Imaging & Light Measurement Laboratory. She also holds affiliate positions at the American Museum of Natural History and the Florida Museum of Natural History. Dr. Toler-Franklin obtained a Ph.D. in Computer Science from Princeton University. She earned an M.S. degree from the Cornell University Program of Computer Graphics, and a B. Arch. degree from Cornell. Before joining UF faculty, Dr. Toler Franklin was a UC President's Postdoctoral Fellow at UC Davis, and a researcher at the UC Berkeley CITRIS Banatao Institute. She also held positions at Autodesk, Adobe, and Google. Dr. Toler-Franklin’s research in computer graphics and vision includes Machine Learning, Data Acquisition, Appearance Modeling, Imaging Spectroscopy and Non-Photorealistic Rendering, with real-world applications in Biodiversity, Bio-Medical Research and Archaeology. Her algorithms use mathematical principles in optics to capture and analyze the shape and appearance of complex materials. Her recent work develops AI algorithms for biomedical research. Collaborating with the UF College of Medicine Oncology and Pathology Departments, and the UF Neuroscience Department, Dr. Toler-Franklin developed deep learning algorithms for diagnosing metastatic cancers and studying behaviors associated with neurological disorders (Alzheimer's, autism, depression).

Intended Audience:
Undergraduates, graduates, and experts. Those with interest in the topic.