Back to Projects

AI-enabled Imaging

Reading minds with Deep Learning: predicting behavioural states from functional imaging data

Project ID: 2020_032

Student: Simon Dahan

1st Supervisor: Emma Robinson, King’s College London
2nd Supervisor: Daniel Rueckert, Imperial College London
Clinical Champions: Tomoki Arichi, King’s College London

Aim of the PhD Project:

The goal is to:

  • Develop tools for spatio-temporal Deep Learning of brain function
  • For prediction of neuro-developmental outcome in vulnerable preterm babies,
  • And development of biomarkers sensitive to risk of ADHD and Autism

Project Description / Background:

Precision diagnosis of complex cognitive disorders, such as Autism and ADHD, is extremely challenging since such disorders are characterised by a highly heterogeneous range of cognitive and behavioural traits. Such traits are extremely difficult to characterise as they reflect subtle features of the spatio-temporal dynamics of brain activity.

Currently, the most popular technique for analysing resting-state functional imaging data is to perform spatial-ICA (independent component analysis [1]). This models the brain as a macroscale network, formed from a set of functionally specialised regions, each associated with a time course. Network connectivity is then inferred by estimating similarities between time courses using correlation measures [1].

Although matrix factorisation approaches such as ICA, have significantly improved our understanding of how brain function relates to behaviour, they smooth out vital sources of inter-subject variation. Specifically, ICA analyses look at the average properties of brain states over time, whereas, it has been shown that many behavioural measures are better predicted by dynamic measures [2]. Further, studies assume a single global average model of cortical organisation; however, there is growing evidence that this is not the case [3,4].

What is required are tools that can learn temporal and spatial features from the data without requirement for prior modelling or spatial normalisation of the data. This problem lends itself to deep learning; we therefore seek to take inspiration from recent works on spatio-temporal convolutional deep learning for natural image processing [5,6], cardiac imaging [7] and functional Magnetic Resonance Imaging (fMRI [8]), in order to classify pathological brain states, and support precision diagnosis of neuro-developmental disorders.

Given that studies of cognition require precision analysis of the brain’s surface (or cortex, [9,10]), a key objective will be to extend models to geometric deep learning [11,12], which trains on surface manifolds, rather than 2D or 3D grids.  Significant emphasis will also be placed on the development of interpretable models [6]. This will support clinical interpretation.

The most suitable candidate for this project will have programming expertise in Python, and experience in Deep Learning. Experience in working with spatio-temporal data sets or geometric deep learning would be a significant plus.


[1] Smith SM, et al. Trends in cognitive sciences. 2013 Dec 1;17(12):666-82. 
[2] Liégeois R, et al. Nature communications. 2019 May 24;10(1):2317.
[3] Bijsterbosch JD, et al. Elife. 2018 Feb 16;7:e32992.
[4] Kong R,et al. Cerebral Cortex. 2018 May 12;29(6):2533-51. 
[5] Tran D, et al.
[6] Meng et al.
[7]  Qin C, …, Rueckert D. MICCAI 2018 Sep 16 (pp. 472-480). Springer, Cham.
[8] Zhao Y, et al MICCAI 2018 Sep 16 (pp. 181-189). Springer, Cham.  
[9] Robinson EC, et al. Neuroimage. 2014 Oct 15;100:414-26.
[10] Glasser MF, Coalson TS, Robinson EC, et al. Nature. 2016 Aug;536(7615):171. 
[11] Bronstein MM, et al. IEEE Signal Processing Magazine. 2017 Jul 11;34(4):18-42.  
[12] Ktena SI, … Rueckert D. NeuroImage. 2018 Apr 1;169:431-42. 

Back to Projects