Denoising and semantic segmentation of 4D datasets with undersampled micro X-ray CTs using deep learning

Authors: Dimitrios Bellos (University of Nottingham)
Co-authored by industrial partner: No

Type: Thesis

State: Published (Approved)
Published: July 2021
Diamond Proposal Number(s): 9396

Abstract: Over recent years, multiple imaging approaches has been proposed to depict the hidden inner structure of many different biological and non-biological systems in the form of 3D volumes. As time progressed due to multiple technological advances, these methods have become faster and more accessible, allowing in recent years the collection of time-resolved volumes that form 4D datasets. With 4D capturing techniques, the hidden inner structure of a system is collected repeatedly through time, allowing us to perceive not only its 3D structure, but temporal changes of this structure. Nevertheless, despite the technological advances in data collection there is still a major need for accurate, efficient and easy to use methods for 3D and 4D data analysis. One of the most difficult tasks associated with 3D or 4D studies is their semantic segmen- tation. Unfortunately for such high-dimensional data, performing this task manually may take many days of human work, or even months in the case of 4D data. Moreover for the case of 4D data, there are other problems that make their semantic segmentation chal- lenging. In particular, for time-series of micro X-ray Computed Tomograms (CTs), each tomogram is often undersampled in terms of projections due to time restraints. Specif- ically, in order to capture sufficient numbers of projections and perform the time-series collection quickly in order to capture temporal phenomena, the time allocated for each of its tomograms is low. Because of this only a limited amount of well-exposed projec- tions can be collected. This sets an ill-posed reconstruction problem, and the resulting tomogram’s reconstructions are low in signal-to-noise ratio. While computed tomography challenges grew, a new branch of computer vision approaches using deep learning have de- livered promising approaches that address both the the problem of a low signal-to-noise ratio, and semantic segmentation. Inspired by these computed tomography challenges and the considerable promise of deep learning approaches, this thesis will propose ap- proaches that address denoising and semantic segmentation of time-series, undersampled tomograms.

Subject Areas: Technique Development, Biology and Bio-materials, Information and Communication Technology

Instruments: I12-JEEP: Joint Engineering, Environmental and Processing , I13-2-Diamond Manchester Imaging

Added On: 19/07/2021 08:59

Discipline Tags:

Artificial Intelligence Technique Development - Life Sciences & Biotech Information & Communication Technologies Life Sciences & Biotech

Technical Tags:

Imaging Tomography