Dr Fani Deligianni


Fani Deligianni
PhD, MSc, MSc, MEng


Short Bio

Dr Fani Deligianni’s holds a PhD in Medical Image Computing at ICL (2002-2006), an MSc in Advanced Computing (awarded project distinction) at ICL (2001-2002), an MSc in Neuroscience at UCL (awarded project distinction) (2008-2010) and a MEng (equivalent) in Electrical and Computer Engineering at Aristotle University (1995-2000), Greece.

Her interests lie within medical image computing, statistical machine learning, wearable sensors, neuroimage analysis and neuroscience. Recently, her work has been focused on workload assesment based on neurophysiological signals. She has also done work on human motion analysis with wearable sensors and single rgb(d) camera.

Her PhD work was on augmenting 3D reconstructed models of the bronchial tree with 2D video images acquired during bronchoscopy. Bronchial deformation was modeled based on Active Shape Models (ASM) and a predictive tracking algorithm was incorporated to improve tracking of the endoscopic camera.

In 2008, she was awarded an MRC Special Research Training Fellowship in Biomedical Informatics to explore links between structural connectivity as it is measured with Diffusion Weighted Imaging (DWI) and functional brain connectivity captured with resting-state (rs)-fMRI. She was based at the Biomedical Image Analysis group in Computing Department of Imperial College London. Her research work suggests a prediction framework to study the link between structural brain connectivity and functional brain connectivity. She developed sophisticate computational approaches in machine learning, statistics and network analysis for the investigation of human brain structure and function. In 2012 she moved to UCL and continued her work on the link between functional and structural brain connectomes. She applied her approach in functional data derived from simultaneous resting-state EEG-fMRI and microstructural indices obtained from neurite orientation dispersion and density imaging of the human brain. In particular, she uses graph theory, machine learning and statistics to describe and characterise complex interconnections between multi-modal brain networks. The methodological challenges that she has addressed include: (i) data mining of large and complex datasets based on predictive modelling of their connectivity/covariance structure, (ii) model selection based on cross-validation that highlights the model with the best prediction performance, (iii) model identification that provide a statistically rigorous framework to choose the most reliable features and control for the false positive rate based on randomised Lasso and bootstrapping and (iv) forming a threshold statistic to examine both similarities and differences between networks.

Fani is also a former member of the Centre for Brain and Cognitive Development (CBCD) at Birkbeck. She worked at CBCD from 2006 to 2008 and she developed a toolbox for contingent eyetracking, Talk2Tobii, to investigate the development of social skills in toddlers. The toolbox is used in several labs and is now integrated in T2T Package and SMART-T.

Her commitment to excellence in academic teaching is reflected in the fact that she is a Fellow of the Higher Education Academy since 2015. Both learning and research are processes of creating knowledge and I support the idea that teaching benefits and inspires research. She has co-supervised(assistant supervisor) three PhD students and several MRes/MSc/UG project thesis and group projects. Her students track record include: (Freer et al. ICRA 2020 submitted, Gu et al. IEEE Transactions on Image Processing, submitted, Gu et al. IEEE Transactions on Neural Networks and Learning Systems, submitted, Freer et al. BSN 2019, Gu et al. BSN 2018, Parker et al. PLoS ONE, 2014)

She is an active reviewer of Journals such as IEEE Trans Med Imaging, NeuroImage, Science Robotics, Human Brain Mapping, Frontiers, PLoS ONE, IEEE Journal of Biomedical Informatics, IEEE signal processing letters, Neurobiology of Aging, Magnetic Resonance in Medicine, Information Fusion and international conferences such as MICCAI, IEEE ISBI and IROS.

Contact Details

Email: fadelgr at gmail dot com
Twitter: @fd301
LinkedIn Profile
Publon Profile