LBLéonie Borne

Léonie Borne

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Léonie Borne has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Design of a top-down computer vision algorithm dedicated to the recognition of cortical sulci

    by LéoNie Borne

    Conception d’un algorithme de vision par ordinateur « top-down » dédié à la reconnaissance des sillons corticaux: Les plissements du cortex caractérisent de manière unique chaque être humain. Ils apparaissent pendant le dernier trimestre de grossesse, c’est-à-dire pendant la mise en place de l’architecture cérébrale. Les motifs de ces plis sont impactés par les spécificités de cette architecture propres à chaque individu. Ils pourraient donc dévoiler les signatures de certaines anomalies du développement à l’origine de pathologies psychiatriques. Le laboratoire d’analyse d’images de Neurospin développe depuis 25 ans un programme de recherche visant à mettre en évidence de telles signatures grâce à la conception d’outils de vision par ordinateur dédiés qu’il diffuse à la communauté (http://brainvisa.info).Cette thèse a permis l’émergence d’une nouvelle génération d’outils basés sur des techniques d’apprentissage automatique. Le premier outil proposé classifie automatiquement des motifs locaux de plissements du cortex, un problème qui n’avait jamais été abordé jusqu’ici. Le second outil vise l’étiquetage automatique des sillons corticaux en modélisant des mécanismes de reconnaissance « top-down » nécessaires pour pallier les faiblesses des démarches « bottom-up » développées jusqu’à présent. Ainsi, en plus d'avoir des taux de reconnaissances plus élevés et un temps d’exécution plus court, le nouveau modèle proposé est robuste aux erreurs de sous-segmentation, ce qui est l'une des plus grandes faiblesses de l'ancien système. Pour réaliser ces deux outils, plusieurs algorithmes d'apprentissage automatique ont été implémentés et comparés. Ces algorithmes s'inspirent d'une part des méthodes multi-atlas, en particulier de l'approche par patch, qui sont largement utilisées pour la segmentation anatomique d'images médicales et d'autre part des méthodes d'apprentissage profond qui révolutionnent aujourd'hui le monde de la vision par ordinateur. Les travaux de cette thèse confirment l'incroyable efficacité des techniques d'apprentissage profond pour s'adapter à des problèmes complexes. Cependant, les performances obtenues avec ces techniques sont généralement équivalentes à celles des approches par patch, voire moins bonnes si la base de données d'apprentissage est restreinte. Ce qui fait de l'apprentissage profond un outil particulièrement intéressant en pratique n'est autre que sa rapidité d'exécution, d'autant plus pour l'analyse des bases de données colossales aujourd'hui disponibles.

  • Open Access

    The relationship between sleep duration and cortical sulcal width in midlife and older adults

    by Caroline Faucher, Léonie Borne, Bryan Paton, Joseph Giorgio, Jurgen Fripp, Renate Thienel, Michelle K Lupton, Michael Breakspear

    Background: Emerging evidence suggests that poor sleep is associated with worse cognitive and structural brain health, and an increased risk of developing dementia (Bubu et al., 2016; Fjell et al., 2022; Tai et al., 2022). The present study investigated the influence of sleep duration on the cognition‐brain relationship in older adults using sulcal width (SW), a reliable measure of changes in the ageing brain (Bertoux et al., 2019). The influence of napping, depression likelihood, and genetic risk for dementia (APOE ε4 status) was also explored.Method: Participants were 137 cognitively normal adults, aged 46‐72 from the Prospective Imaging Study of Ageing (PISA). Demographic information, sleep duration, and depressive symptoms were collected via online questionnaires. Cognition was assessed using the Cambridge Brain Systems battery. APOE genotype was determined from blood‐extracted DNA. Imaging data was acquired using a 3T Siemens PRISMA scanner. SW was extracted using the Morphologist pipeline (Borne et al., 2020).Canonical Partial Least Squares (PLS) were used to obtain latent variables of cognition and SW. ANCOVAs measured the effect of sleep duration categories (7‐7.5 hours versus {<7 or ≥8 hours}) on the cognitive and SW components, with sex and age as covariates. Status of depression likelihood was added as a covariate of interest. The effect of napping, and APOE ɛ4 allele on these same components were measured by ANCOVAs, with sex and age as covariates.Result: We observed a significant effect of sleep duration on SW (F(1, 133) = 4.17, p = 0.043, Fig. 1). This effect remained significant (F(1,132) = 4.89, p = 0.029) after including depression likelihood as a covariate, which was also significant in the model (F(1,132) = 4.62, p = 0.034). A significant interaction between APOE ε4 status and age (p = 0.050) on SW was also observed.Conclusion: Results add weight to studies suggesting that not too much or too little sleep is needed to maintain brain health in later life (Li et al., 2022; Liang et al., 2019). Depression, a risk factor for dementia (Livingston et al., 2020), was also associated with poorer brain health. Results suggest that at approximately 60 years of age, the influence of a positive APOE ε4 status is associated with increasing age‐related brain atrophy.

  • Open Access

    Can an online battery match in‐person cognitive testing in predicting age‐related cortical changes

    by Renate Thienel, Léonie Borne, Caroline Faucher, Gail Robinson, Jurgen Fripp, Joseph Giorgio, Nicholas G Martin, Michael Breakspear, Michelle K Lupton

    Background: Studies into cognitive changes typically employ detailed in person cognitive testing, which is not always feasible. Therefore, we compared the relationship between brain morphology (sulcal width) and cognitive functioning, using an online and an in‐person modality and disentangled the influence of age, sex, β‐Amyloid (Aβ) and APOE‐status.Method: 141 healthy participants (mean age 60, range 46‐71 years, 75% female) assessed with structural MRI; cognitive batteries both, face‐to‐face and online (Cambridge Brain Systems), Aβ status (Fluorine‐18 florbetaben‐PET scan) and APOE genotype (Lupton et al., 2021); Canonical Partial Least Square method to compare cognitive modalities and Sulcal width (SW; Morphologist pipeline‐BrainVISA toolbox; Borne et al., 2020). Age effects tested with two‐sided Wald Test. Analysis of covariance to test age and sex‐interactions, amyloid and APOE status, sex‐effects (controlling for age), Aβ, and APOE (controlling for age and sex).Result: The single robust mode for brain (SW) ‐ behaviour (cognition) covariation loaded most strongly onto memory and executive functions for both the onsite (1st mode, p = 0.013, cov = 3.55, z‐cov = 2.93, R2 = 0.18, z‐R2 = 0.95; 2nd mode, p>0.99), and the online battery (1st mode, p2 = 0.14, z‐R2 = 1.15; 2nd mode, p = 0.99) (Fig. 1).Cognition‐related SW showed a regional pattern similar for online and in person cognitive appraisal. Significant effect of sex on SW projections in both the online and onsite conditions with larger sulcal width for men (p2 = 0.15) was only slightly less than for the in‐person testing (R2 = 0.18). Brain‐behaviour z‐transformed covariance was likewise comparable across modalities.Conclusion: Similar sulcal width brain projections for both cognitive modalities, with memory and executive domains showing the strongest loadings. Aβ‐aggregation associated with a steeper cognitive projection slope for both batteries, suggesting that in our preclinical sample the early stages of Aβ accumulation accelerate cognitive ageing potentially before translation into structural brain changes. Adequate sensitivity of online cognitive tests for studying age‐related neurobiology of cognition is suggested.


  • Open Access

    Functional re-organization of hippocampal-cortical gradients during naturalistic memory processes

    by Léonie Borne, Ye Tian, Michelle K. Lupton, Johan N. van der Meer, Jayson Jeganathan, Bryan Paton, Nikitas Koussis, Christine C. Guo, Gail A. Robinson, Jurgen Fripp, et al.


  • Open Access

    A snapshot of brain and cognition in healthy mid-life and older adults

    by Léonie Borne, Michelle K. Lupton, Christine Guo, Philip Mosley, Robert Adam, Amelia Ceslis, Pierrick Bourgeat, Amir Fazlollahi, Paul Maruff, Christopher C. Rowe, et al.

    Deficits in memory are seen as a canonical sign of ageing and a prodrome to dementia in older adults. However, the nature of cognitive and brain changes across a wider aperture of adulthood is not well known. We quantify the relationship between cognitive function and brain morphology from mid-life to older adulthood, and the influence of age, sex, amyloid and genetic risk for dementia. We analyzed three observational cohorts (PISA, AIBL, ADNI) with cognitive, genetic and neuroimaging measures comprising a total of 1570 healthy mid-life and older adults (mean age 72, range 49-90 years, 1330 males) and 1365 age- and sex-matched adults with mild cognitive impairment or Alzheimer’s disease. Among healthy adults, we find robust modes of co-variation between regional sulcal width and multidomain cognitive function that change from mid-life to the older age range. The most prominent cortical changes in mid-life are predominantly associated with changes in executive functions, whereas they are most strongly associated with poorer memory function in older age. These cognitive changes are accompanied by an age-dependent pattern of sulcal widening. Amyloid exerts a weak, but significant, influence on cognition, but not on sulcal width. The APOE ɛ4 allele also exerts a weak influence on cognition, but only significantly in the (larger and older) AIBL cohort. These findings provide new insights into brain and cognition in mid-life and older adults, suggesting that cognitive screening in mid-life cohorts should encompass executive functions as well as memory.


  • Open Access

    Automatic recognition of specific local cortical folding patterns

    by Léonie Borne, Denis Rivière, Arnaud Cachia, Pauline Roca, Charles Mellerio, Catherine Oppenheim, Jean-François Mangin


  • Translational neuroscience applications for automated detection of rodent grooming with deep learning

    by Nicholas J. Burton, Léonie Borne, Elizbeth E. Manning