The Computer Vision and Pattern Discovery for BioImages group uses advanced computer vision, machine learning and mathematical models to build better machines; for the improvement of health care and discovery of biological knowledge. The group analyses images of tissue, histological slides and 2D/3D live cells assays. These images were acquired using wide-field, confocal and light-sheet microscopes as well as infra-red camera and other kinds of clinical image devices.
In a clinical setting, imaging techniques are becoming important as they are usually non-invasive and advancement of clinical devices has made quantitative analysis of these images an important component for improving health care.
Motivated by the desire to device better cures for diseases and driven by enabling technologies, biological experiments are becoming more quantitative and generating large amounts of data. These images are then analyzed and used to create new biological hypotheses that are further validated using other experimental means. The group is also working towards the development of better image acquisition protocols to acquire high quality microscopy images.