Biology subjects

Thurairajah, A.

Publications and source records attributed to Thurairajah, A..

3 recordsLinked to original sources

bioRxiv2026

AFIDs-Validator: An Open-Access AI-Guided Platform for Learning Anatomical Landmark Placement

Accurate localization of anatomical landmarks is a foundational skill in anatomy and imaging that is often taught informally through expert mentorship, requiring access to data and desktop software. There is no openly accessible, interactive resource that teaches neuroanatomy with quantitative feedback. We present the AFIDs-Validator (validator.afids.io), an open-access, browser-based platform that pairs guided instruction with quantitative assessment. The platform combines (1) a learning mode in which a language-model neuroanatomy tutor operates inside an MRI viewer, giving anatomy-first instruction that responds to the learner's current image slice, orientation, and cursor position; and (2) a validation engine that accepts a learner's landmark file and returns per-landmark Euclidean error against expert-annotated references spanning 21 brain templates. To make the feedback interpretable, we analyzed 15,000 landmark annotations across 132 human subjects and found that landmark difficulty varies fourfold (median error ranged from 0.37 mm at the anterior commissure to 1.50 mm at the temporal horns) with heavy-tailed distributions at every landmark. These distributions are compiled into per-landmark reliability priors, so learners are scored against the empirical spread of trained raters rather than an arbitrary threshold, and difficult landmarks are not mistaken for poor performance. The AFIDs-Validator requires no installation, licensed software, or local data, and all code, reference data, and tutor design are openly released.

scientific communication and education↗

bioRxiv2025

Hippocampal grey matter changes across scales in Alzheimer's Disease

Alzheimers disease (AD) is a progressive and debilitating neurodegenerative disease of the central nervous system, characterized by deterioration in cognitive function including extensive memory impairment. The hippocampus, a medial temporal lobe region, is a key orchestrator in the encoding and retrieval of memory and is believed to be one of the first regions to deteriorate in AD. In this work we examined hippocampal macrostructure (specifically gyrification and thickness) and microstructure in Alzheimers disease (AD) and mild cognitive impairment (MCI) relative to healthy aged controls in the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset. We first utilized an iterative training paradigm to adapt an existing deep learning approach for capturing hippocampal topology to elderly individuals as well as individuals with potential hippocampal degeneration. Using this new model, we found notable decreases in both thickness and gyrification in AD and MCI across both the subfields and anterior-posterior axis. Using the diffusion tensor representation derived from diffusion MRI data, we found significant increases in the mean diffusivity across the extent of the hippocampus in AD and MCI, which may be related to a number of changes such as loss of neuronal cells, decreased fiber density, demyelination, and increased presence of CSF. Examining the primary direction of diffusion relative to canonical hippocampal axes, we found distinct diffusion orientation shifts in AD and MCI throughout the anterior-posterior extent of the subiculum and CA1. Specifically, we found a decrease in diffusion oriented tangentially, and an increase in diffusion oriented along the long-axis. This could potentially be related to the known degeneration of the perforant path, which is greatly affected in AD and is a largely tangential oriented pathway. The AD-related changes in diffusion orientations were found to not have significant spatial overlap with AD-related changes in mean diffusivity, suggesting that they may be capturing distinct spatially-localized disease processes. Finally, we showed that the macro- and microstructure of the hippocampus in AD changed less across age relative to MCI and controls. As well, the age-related hippocampal macrostructure changes in MCI appeared indistinguishable from healthy aging.

neuroscience↗

bioRxiv2022

Magnetic resonance imaging datasets with anatomical fiducials for quality control and registration

Tools available for reproducible, quantitative assessment of brain correspondence have been limited. We previously validated the anatomical fiducial (AFID) placement protocol for point-based assessment of image registration with millimetric (mm) accuracy. In this data descriptor, we release curated AFID placements for some of the most commonly used structural magnetic resonance imaging templates and datasets. The release of our accurate placements allows for rapid quality control of image registration, teaching neuroanatomy, and clinical applications such as disease diagnosis and surgical targeting. We release placements on individual subjects from four datasets (n = 132 subjects for a total of 15,232 fiducials) and more than 10 brain templates (4,288 fiducials), compiling over 300 human rater hours of annotation. We also validate human rater accuracy of released placements to be within 1-2 mm (using a total of 50,336 Euclidean distances), consistent with prior studies. Our data is compliant with the Brain Imaging Data Structure (BIDS) allowing for facile incorporation into modern neuroimaging analysis pipelines. Data is accessible on GitHub (https://github.com/afids/afids-data).

neuroscience↗