Author name cluster

Alex P. Leff

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

YNICL Journal 2025 Journal Article

Deep convolutional neural networks outperform vanilla machine learning when predicting language outcomes after stroke

Thomas M.H. Hope
Howard Bowman
Alex P. Leff
Cathy J. Price

BACKGROUND: Current medicine cannot confidently predict patients' language skills after stroke. In recent years, researchers have sought to bridge this gap with machine learning. These models appear to benefit from access to features describing where and how much brain damage these patients have suffered. Given the very high dimensionality of structural brain imaging data, those brain lesion features are typically post-processed from the images themselves into tabular features. With the introduction of deep Convolutional Neural Networks (CNN), which appear to be much more robust to high dimensional data, it is natural to hope that much of this image post-processing might be unnecessary. But prior attempts to demonstrate this (in the area of post-stroke prognostics) have so far yielded only equivocal results - perhaps because the datasets that those studies could deploy were too small to properly constrain CNNs, which are famously 'data-hungry'. METHODS: The study draws on a much larger dataset than has been employed in previous work like this, referring to patients whose language outcomes were assessed once during the chronic phase post-stroke, on or around the same days as they underwent high resolution MRI brain scans. Following the model of our own and others' past work, we use state of the art 'vanilla' machine learning models (boosted ensembles) to predict a variety of language and cognitive outcomes scores. These models employ both demographic variables and features derived from the brain imaging data, which represent where brain damage has occurred. These are our baseline models. Next, we use deep CNNs to predict the same language scores for the same patients, drawing on both the demographic variables, and post-processed brain lesion images: i.e., multi-input models with one input for tabular features and another for 3-dimensional images. We compare the models using 5 × 2-fold cross-validation, with consistent folds. RESULTS: The CNN models consistently outperform the vanilla machine learning models, in this domain. CONCLUSIONS: Deep CNNs offer state of the art performance when predicting language outcomes after stroke, outperforming vanilla machine learning and obviating the need to post-process lesion images into lesion features.

Details DOI

YNICL Journal 2018 Journal Article

Predicting language outcomes after stroke: Is structural disconnection a useful predictor?

Thomas M.H. Hope
Alex P. Leff
Cathy J. Price

For many years, researchers have sought to understand whether and when stroke survivors with acquired language impairment (aphasia) will recover. There is broad agreement that lesion location information should play some role in these predictions, but still no consensus on the best or right way to encode that information. Here, we address the emerging emphasis on the structural connectome in this work - specifically the claim that disrupted white matter connectivity conveys important, unique prognostic information for stroke survivors with aphasia. Our sample included 818 stroke patients extracted from the PLORAS database, which associates structural MRI from stroke patients with language assessment scores from the Comprehensive Aphasia Test (CAT) and basic demographic. Patients were excluded when their lesions were too diffuse or small (<1 cm3) to be detected by the Automatic Lesion Identification toolbox, which we used to encode patients' lesions as binary lesion images in standard space. Lesions were encoded using the 116 regions defined by the Automatic Anatomical Labelling atlas. We examined prognostic models driven by both "lesion load" in these regions (i.e. the proportion of each region destroyed by each patient's lesion), and by the disconnection of the white matter connections between them which was calculated via the Network Modification toolbox. Using these data, we build a series of prognostic models to predict first one ("naming"), and then all of the language scores defined by the CAT. We found no consistent evidence that connectivity disruption data in these models improved our ability to predict any language score. This may be because the connectivity disruption variables are strongly correlated with the lesion load variables: correlations which we measure both between pairs of variables in their original form, and between principal components of both datasets. Our conclusion is that, while both types of structural brain data do convey useful, prognostic information in this domain, they also appear to convey largely the same variance. We conclude that connectivity disruption variables do not help us to predict patients' language skills more accurately than lesion location (load) data alone.

Details DOI

YNIMG Journal 2016 Journal Article

Distinguishing the effect of lesion load from tract disconnection in the arcuate and uncinate fasciculi

Thomas M.H. Hope
Mohamed L. Seghier
Susan Prejawa
Alex P. Leff
Cathy J. Price

Brain imaging studies of functional outcomes after white matter damage have quantified the severity of white matter damage in different ways. Here we compared how the outcome of such studies depends on two different types of measurements: the proportion of the target tract that has been destroyed (‘lesion load’) and tract disconnection. We demonstrate that conclusions from analyses based on two examples of these measures diverge and that conclusions based solely on lesion load may be misleading. First, we reproduce a recent lesion-load-only analysis which suggests that damage to the arcuate fasciculus, and not to the uncinate fasciculus, is significantly associated with deficits in fluency and naming skills. Next, we repeat the analysis after replacing the measures of lesion load with measures of tract disconnection for both tracts, and observe significant associations between both tracts and both language skills: i. e. the change increases the apparent relevance of the uncinate fasciculus to fluency and naming skills. Finally we show that, in this dataset, disconnection data explains significant variance in both language skills that is not accounted for by lesion load or volume, but lesion load data explains no unique variance in those skills, once disconnection and lesion volume are taken into account.

Details DOI

YNIMG Journal 2016 Journal Article

Modulation of frontal effective connectivity during speech

Rachel Holland
Alex P. Leff
William D. Penny
John C. Rothwell
Jenny Crinion

Noninvasive neurostimulation methods such as transcranial direct current stimulation (tDCS) can elicit long-lasting, polarity-dependent changes in neocortical excitability. In a previous concurrent tDCS-fMRI study of overt picture naming, we reported significant behavioural and regionally specific neural facilitation effects in left inferior frontal cortex (IFC) with anodal tDCS applied to left frontal cortex (Holland et al. , 2011). Although distributed connectivity effects of anodal tDCS have been modelled at rest, the mechanism by which ‘on-line’ tDCS may modulate neuronal connectivity during a task-state remains unclear. Here, we used Dynamic Causal Modelling (DCM) to determine: (i) how neural connectivity within the frontal speech network is modulated during anodal tDCS; and, (ii) how individual variability in behavioural response to anodal tDCS relates to changes in effective connectivity strength. Results showed that compared to sham, anodal tDCS elicited stronger feedback from inferior frontal sulcus (IFS) to ventral premotor (VPM) accompanied by weaker self-connections within VPM, consistent with processes of neuronal adaptation. During anodal tDCS individual variability in the feedforward connection strength from IFS to VPM positively correlated with the degree of facilitation in naming behaviour. These results provide an essential step towards understanding the mechanism of ‘online’ tDCS paired with a cognitive task. They also identify left IFS as a ‘top-down’ hub and driver for speech change.

Details DOI

YNIMG Journal 2016 Journal Article

The PLORAS Database: A data repository for Predicting Language Outcome and Recovery After Stroke

Mohamed L. Seghier
Elnas Patel
Susan Prejawa
Sue Ramsden
Andre Selmer
Louise Lim
Rachel Browne
Johanna Rae

The PLORAS Database is a relational repository of anatomical and functional imaging data that has primarily been acquired from stroke survivors, along with standardized scores on a wide range of sensory, motor and cognitive abilities, demographic details and medical history. As of January 2015, we have data from 750 patients with an expected accrual rate of 200 patients per year. Expansion will accelerate as we extend our collaborations. The main aim of the database is to Predict Language Outcome and Recovery After Stroke (PLORAS) on the basis of a single structural (anatomical) brain scan that indexes the stereotactic location and extent of brain damage. Predictions are made for individual patients by indicating how other patients with the most similar brain damage, cognitive abilities and demographic details recovered their language skills over time. Predictions are validated by longitudinal follow-ups of patients who initially presented with speech and language difficulties. The PLORAS Database can also be used to predict recovery of other cognitive abilities on the basis of anatomical brain scans. The functional imaging data can be used to understand the neural mechanisms that support recovery from brain damage; and all the data can be used to understand the main sources of inter-subject variability in structure–function mappings in the human brain. Data will be made available for sharing, subject to: funding, ethical approval and patient consent.

Details DOI

YNICL Journal 2013 Journal Article

Predicting outcome and recovery after stroke with lesions extracted from MRI images

Thomas M.H. Hope
Mohamed L. Seghier
Alex P. Leff
Cathy J. Price

Here, we present and validate a method that lets us predict the severity of cognitive impairments after stroke, and the likely course of recovery over time. Our approach employs (a) a database that records the behavioural scores from a large population of patients who have, collectively, incurred a comprehensive range of focal brain lesions, (b) an automated procedure to convert structural brain scans from those patients into three-dimensional images of their lesions, and (c) a system to learn the relationship between patients' lesions, demographics and behavioural capacities at different times post-stroke. Validation against data collected from 270 stroke patients suggests that our first set of variables yielded predictions that match or exceed the predictive power reported in any comparable work in the available literature. Predictions are likely to improve when other determinants of recovery are included in the system. Many behavioural outcomes after stroke could be predicted using the proposed approach.

Details DOI