Bioimage Informatics draws upon advances in signal processing, optics, probe chemistry, molecular biology and machine learning to provide answers to biological questions from the growing numbers of biological images acquired in digital form. Microscopy is one of the oldest biological methods, and for centuries it has been paired with visual interpretation to learn about biological phenomena. With the advent of sensitive digital cameras and the dramatic increase in computer processing speeds over the past two decades, it has become increasingly common to collect large volumes of biological image data that create a need for sophisticated image processing and analysis. In addition, dramatic advances in machine learning during the same period set the stage for converting imaging from an observational to a computational discipline and allow the direct generation of biological knowledge from images.
Specialization Electives (3 credits/9 units)
Automation of Biological Research
This course covers principles and applications of optical methods in the study of structure and function in biological systems. Topics to be covered include: absorption and fluorescence spectroscopy; interaction of light with biological molecules, cells, and systems; design of fluorescent probes and optical biosensor molecules; genetically expressible optical probes; photochemistry; optics and image formation; transmitted-light and fluorescence microscope systems; laser-based systems; scanning microscopes; electronic detectors and cameras: image processing; multi-mode imaging systems; microscopy of living cells; and the optical detection of membrane potential, molecular assembly, transcription, enzyme activity, and the action of molecular motors. This course is particularly aimed at students in science and engineering interested in gaining in-depth knowledge of modern light microscopy.
This course introduces the fundamental techniques used in computer vision, that is, the analysis of patterns in visual images to reconstruct and understand the objects and scenes that generated them. Topics covered include image formation and representation, camera geometry and calibration, multi-view geometry, stereo, 3D reconstruction from images, motion analysis, image segmentation, object recognition. The material is based on graduate-level texts augmented with research papers, as appropriate. Evaluation is based on homeworks and final project. The homeworks involve considerable Matlab programming exercises.
Medical Image Analysis
The fundamentals of computational medical image analysis will be explored, leading to current research in applying geometry and statistics to segmentation, registration, visualization, and image understanding. Student will develop practical experience through projects using the National Library of Medicine Insight Toolkit (ITK), a new software library developed by a consortium of institutions including CMU. In addition to image analysis, the course will describe the major medical imaging modalities and include interaction with practicing radiologists at UPMC.
Visual Learning and Recognition
A graduate course in Computer Vision with emphasis on representation and reasoning for large amounts of data (images, videos and associated tags, text, gps-locations etc) toward the ultimate goal of Image Understanding. We will be reading an eclectic mix of classic and recent papers on topics including: Theories of Perception, Mid-level Vision (Grouping, Segmentation, Poselets), Object and Scene Recognition, 3D Scene Understanding, Action Recognition, Contextual Reasoning, Image Parsing, Joint Language and Vision Models, etc. We will be covering a wide range of supervised, semi-supervised and unsupervised approaches for each of the topics above.