The project aims to investigate new deep learning modelling approaches to leverage real-world large-scale image data sets that contain noisy and incomplete labels and imbalanced class prevalence – to enable the use of these data sets for modelling deep learning classifiers.
This project will develop novel methods for discovering and visualising optimal biomarkers from chest computed tomography images based on extensions of recently developed deep reinforcement learning techniques. Our project aims to discover previously unknown biomarkers associated with important clinical outcomes.
Recently, magnetic resonance and ultrasound imaging have found utility as adjuncts to mammography in the detection and management of breast cancer. This project will develop novel machine learning techniques that optimally integrate information from each of these data sources so as to improve the efficiency and accuracy of breast cancer diagnosis.
The centre’s research will allow robots to see, to understand their environment using the sense of vision. This is the missing capability that currently prevents robots from performing useful tasks in the complex, unstructured and dynamically changing environments in which we live and work.
Using Deep Learning, we are developing deep learning models that aim to identify the general health condition of a patient, using mortality as a training annotation.
In this project, we aim to take a few images of your favourite cartoon, and build a 3D mesh with a texture atlas.
Precise detection and delineation of several fetal anatomies from ultrasound using probabilistic boosting tree.
In this work, we propose the use of a hierarchical extension of expectation-maximization for the supervised learning of semantic visual classes.
This is older work on the design of representation methods using local image features.