Bio
“Blood Cell Reconstruction, Detection, Counting and Classification in Holographic Images”
Dr. Rene Vidal is the Herschel Seder Professor of Biomedical Engineering and the Inaugural Director of the Mathematical Institute for Data Science at The Johns Hopkins University. He has secondary appointments in Computer Science, Electrical and Computer Engineering, and Mechanical Engineering. He is also a faculty member in the Center for Imaging Science (CIS), the Institute for Computational Medicine (ICM) and the Laboratory for Computational Sensing and Robotics (LCSR). Vidal’s research focuses on the development of theory and algorithms for the analysis of complex high-dimensional datasets such as images, videos, time-series and biomedical data. His current major research focus is understanding the mathematical foundations of deep learning and its applications in computer vision and biomedical data science. His lab has pioneered the development of methods for dimensionality reduction and clustering, such as Generalized Principal Component Analysis and Sparse Subspace Clustering, and their applications to face recognition, object recognition, motion segmentation and action recognition. His lab creates new technologies for a variety of biomedical applications, including detection, classification and tracking of blood cells in holographic images, classification of embryonic cardio-myocytes in optical images, and assessment of surgical skill in surgical videos.
Click here to view webcast.
Abstract
“Blood Cell Reconstruction, Detection, Counting and Classification in Holographic Images”
Reconstructing, detecting, counting, and classifying various cell types in images of human blood is important in many biomedical applications. However, these tasks can be very difficult due to the wide range of biological variability, the resolution limitations of many imaging modalities, and the lack of cell-level annotations for training a classifier. This talk will present a new approach to reconstructing, detecting, counting and classifying blood cell populations in holographic images that overcomes these limitations. The proposed reconstruction approach dramatically improves image quality by using a sparsity prior on the reconstructed volume. The proposed detection, counting and classification approach can be trained without cell-level annotations by using a novel probabilistic generative model for an image of a population of cells. Experiments on holographic images of lysed blood show that our method achieves an error of 6.8% for all class populations, compared to errors of over 28.6% for all other methods tested.
Click here to view webcast.