no code implementations • 16 May 2024 • Michail Mamalakis, Antonios Mamalakis, Ingrid Agartz, Lynn Egeland Mørch-Johnsen, Graham Murray, John Suckling, Pietro Lio
In this study, for the first time, we propose a novel framework designed to enhance the explainability of deep networks, by maximizing both the accuracy and the comprehensibility of the explanations.
1 code implementation • 2 Sep 2023 • Michail Mamalakis, Heloise de Vareilles, Atheer AI-Manea, Samantha C. Mitchell, Ingrid Arartz, Lynn Egeland Morch-Johnsen, Jane Garrison, Jon Simons, Pietro Lio, John Suckling, Graham Murray
With respect to this mathematical formulation, we propose a 3D explainability framework aimed at validating the outputs of deep learning networks in detecting the paracingulate sulcus an essential brain anatomical feature.
no code implementations • 30 Mar 2021 • Carmen Jiménez-Mesa, Javier Ramírez, John Suckling, Jonathan Vöglein, Johannes Levin, Juan Manuel Górriz, Alzheimer's Disease Neuroimaging Initiative ADNI, Dominantly Inherited Alzheimer Network DIAN
We found in the permutation test that CV and RUB methods offer a false positive rate close to the significance level and an acceptable statistical power (although lower using cross-validation).
no code implementations • 16 Dec 2020 • Juan Manuel Gorriz, SiPBA Group, John Suckling
A connection between the General Linear Model (GLM) in combination with classical statistical inference and the machine learning (MLE)-based inference is described in this paper.
no code implementations • 16 May 2020 • Matthew Leming, Simon Baron-Cohen, John Suckling
In this work, we introduce a technique of deriving symmetric connectivity matrices from regional histograms of grey-matter volume estimated from T1-weighted MRIs.
no code implementations • 25 Feb 2020 • Matthew Leming, John Suckling
We applied our method to resting-state and task data from the UK BioBank, using two visualization techniques to measure the salience of three brain networks involved in task- and resting-states, and their interaction.
1 code implementation • 14 Feb 2020 • Matthew Leming, Juan Manuel Górriz, John Suckling
Employing class-balancing to build a training set, we trained 3$\times$300 modified CNNs in an ensemble model to classify fMRI connectivity matrices with overall AUROCs of 0. 6774, 0. 7680, and 0. 9222 for ASD vs TD, gender, and task vs rest, respectively.