Biology subjects

Svanera, M.

Publications and source records attributed to Svanera, M..

4 recordsLinked to original sources

bioRxiv2026

Diagnostic Labels and Measurement Timing Drive Systematic Inconsistency in ADNI Neuroimaging Data

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is widely used to train machine learning models for Alzheimer's disease, yet whether it provides consistent ground truth for predictive modeling has not been systematically tested. In this paper, we showed that ADNI contains three interacting sources of bias with direct implications for machine learning: (a) diagnostic label inconsistency, (b) technical measurement drift, and (c) longitudinal survivor bias. A substantial proportion of cases, particularly within intermediate stages, fall outside ADNI's own diagnostic thresholds. MRI field strength and evolving processing pipelines introduce significant technical variability in hippocampal volume, while cohort survivor bias arising from differential retention of participants across phases further distorts longitudinal estimates of disease progression. These findings indicated that ADNI does not provide the stable, internally consistent labels often required in machine learning applications. We proposed a practical framework for diagnostic validation, feature harmonization, and cohort accounting, offering guidance for building more robust and biologically meaningful predictive models from large-scale neuroimaging cohorts.

neuroscience↗

bioRxiv2024

Delineating In-Vivo T1-Weighted Intensity Profiles Within the Human Insula Cortex Using 7-Tesla MRI

The integral role of the insula cortex in sensory and cognitive function has been well documented in humans, and fine anatomical details characterising the insula have been extensively investigated ex-vivo in both human and non-human primates. However, in-vivo studies of insula anatomy in humans (in general), and within-insula parcellation (in particular) have been limited. The current study leverages 7 Tesla magnetic resonance imaging to delineate cortical depth intensity profiles within the human cortex. Our analysis revealed two separate clusters of relatively high and low signal intensity across the insula cortex located in three distinct compartments within the posterior, anterior-inferior, and middle insula. The posterior and anterior-inferior compartments are characterised by elevated T1-weighted signal intensities, contrasting with lower intensity observed in the middle insular compartment, compatible with ex-vivo studies. Importantly, the detection of the high T1-weighted anterior cluster is determined by the choice of brain atlas employed to define the insular ROI. We obtain reliable in-vivo within-insula parcellation at the individual and group levels, across two separate cohorts acquired in two separate sites (n1 = 21, Glasgow, UK; n2 = 101, Amsterdam, NL). Results are further confirmed by deriving cortical depth dependent profiles from T1Map and R1Map images. These results reflect new insights into the insula anatomical structure, in-vivo, while highlighting the use of 7 Tesla in neuroimaging with potential implications for individualised medicine approaches. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=125 SRC="FIGDIR/small/605123v3_ufig1.gif" ALT="Figure 1"> View larger version (51K): org.highwire.dtl.DTLVardef@1c27244org.highwire.dtl.DTLVardef@dbd256org.highwire.dtl.DTLVardef@1ce44f6org.highwire.dtl.DTLVardef@11183d0_HPS_FORMAT_FIGEXP M_FIG C_FIG

neuroscience↗

bioRxiv2020

An Unsupervised Deep Neural Network for Image Completion Resembles Early Visual Cortex fMRI Activity Patterns for Occluded Scenes

AO_SCPLOWBSTRACTC_SCPLOWThe promise of artificial intelligence in understanding biological vision relies on the comparison of computational models with brain data with the goal of capturing functional principles of visual information processing. Convolutional neural networks (CNN) have successfully matched the transformations in hierarchical processing occurring along the brains feedforward visual pathway extending into ventral temporal cortex. However, we are still to learn if CNNs can successfully describe feedback processes in early visual cortex. Here, we investigated similarities between human early visual cortex and a CNN with encoder/decoder architecture, trained with self-supervised learning to fill occlusions and reconstruct an unseen image. Using Representational Similarity Analysis (RSA), we compared 3T fMRI data from a non-stimulated patch of early visual cortex in human participants viewing partially occluded images, with the different CNN layer activations from the same images. Results show that our self-supervised image-completion network outperforms a classical object-recognition supervised network (VGG16) in terms of similarity to fMRI data. This provides additional evidence that optimal models of the visual system might come from less feedforward architectures trained with less supervision. We also find that CNN decoder pathway activations are more similar to brain processing compared to encoder activations, suggesting an integration of mid- and low/middle-level features in early visual cortex. Challenging an AI model and the human brain to solve the same task offers a valuable way to compare CNNs with brain data and helps to constrain our understanding of information processing such as neuronal predictive coding.

neuroscience↗

bioRxiv2019

Transfer learning of deep neural network representations for fMRI decoding

BackgroundDeep neural networks have revolutionised machine learning, with unparalleled performance in object classification. However, in brain imaging (e.g. fMRI), the direct application of Convolutional Neural Networks (CNN) to decoding subject states or perception from imaging data seems impractical given the scarcity of available data. New methodIn this work we propose a robust method to transfer information from deep learning (DL) features to brain fMRI data with the goal of decoding. By adopting Reduced Rank Regression with Ridge Regularisation we establish a multivariate link between imaging data and the fully connected layer (fc7) of a CNN. We exploit the reconstructed fc7 features by performing an object image classification task on two datasets: one of the largest fMRI databases, taken from different scanners from more than two hundred subjects watching different movie clips, and another with fMRI data taken while watching static images, ResultsThe fc7 features could be significantly reconstructed from the imaging data, and led to significant decoding performance. Comparison with existing methodsThe decoding based on reconstructed fc7 outperformed the decoding based on imaging data alone. ConclusionIn this work we show how to improve fMRI-based decoding benefiting from the mapping between functional data and CNN features. The potential advantage of the proposed method is twofold: the extraction of stimuli representations by means of an automatic procedure (unsupervised) and the embedding of high-dimensional neuroimaging data onto a space designed for visual object discrimination, leading to a more manageable space from dimensionality point of view.

neuroscience↗