UCL Microstructure Imaging Group
We use mathematical and computational modeling together with cutting-edge machine learning and parameter estimation techniques to engineer new biomedical imaging techniques. Our primary focus is on magnetic resonance imaging (MRI) for medicine. Specifically, our techniques enhance understanding and early detection of neurological conditions, such as Alzheimer’s diseases, other dementias, multiple sclerosis, and psychiatric disorders, and assist in the diagnosis and treatment assignment for solid cancers. The “microstructure imaging” paradigm uses model-based approaches to estimate tissue features traditionally accessible only through invasive biopsy and histology. The ultimate aim is replace such procedures, which currently underpin the gold-standard diagnosis of most cancers and many neurological disorders, with non-invasive imaging. Our Research page details our general approach and specific work.
- Rss / CMIC Platform Grant awarded to Grussu F., Cardoso M.J., Wheeler-Kingshott C.A.M. and Alexander D.C.
Tue, 13 Jun 2017 14:52:10 GMT
Grussu F. was awarded a CMIC pump-priming award to work on multi-site, multi-modal quantitative MRI of the spinal cord, under the mentorship of Cardoso M.J., Wheeler-Kingshott C.A.M. and Alexander D.C. (June 2017-June 2018).
- Rss / Image quality transfer and applications in diffusion MRI - Alexander et al. Neuroimage (2017) 152:283-298
Tue, 30 May 2017 11:26:18 GMT
New paper on Image Quality Transfer (IQT) using machine learning to propagate information from high quality images, e.g. from a bespoke scanner, to more standard low-quality images.
- Rss / Apparatus for histological validation of MRI in prostate - Bourne et al., 2017
Tue, 09 May 2017 10:02:58 GMT
3D-printed prostate molds designed from MRI can guide histology, allowing us to see what microstructural features really contributes to MRI signals
- Rss / Danny Alexander and Andrada Ianus awarded ISMRM fellowships.
Tue, 25 Apr 2017 15:04:36 GMT
Danny received senior fellowship of the ISMRM and Andrada received junior fellowship of the ISMRM at the annual meeting in Honolulu on 24th April 2017.
- Rss / Machine learning based compartment models with permeability - Nedjati-Gilani et al.
Sun, 23 Apr 2017 09:54:15 GMT
Gilani et al use Monte Carlo simulations and machine learning to learn a mapping between features derived from diffusion weighted MR signals and ground truth microstructure parameters