Biology subjects

Gopinath, K.

Publications and source records attributed to Gopinath, K..

3 recordsLinked to original sources

bioRxiv2026

On the accuracy of image registration in portable low-field 3D brain MRI

Portable low-field MRI offers an affordable and mobile alternative to conventional high-field scanners, enabling imaging in point-of-care and resource-limited settings. However, its lower signal-to-noise ratio, reduced resolution, and acquisition artifacts raise concerns about the accuracy of standard image registration methods. Reliable registration is critical for a wide range of emerging applications, including frequent brain monitoring, assessment of neurodegenerative disease progression, and evaluation of treatment effects such as those of Alzheimers therapeutics. In this work, we systematically evaluated state-of-the-art registration approaches on simulated low-field scans (obtained by downsampling high-field images) and on real low-field brain MRI data. We compared three representative approaches: classical optimization (NiftyReg), learning-based registration (SynthMorph), and synthesis-based registration (SynthSR+NiftyReg). Using downsampled high-field scans, all methods performed well, achieving high Dice scores and smooth deformation fields, indicating that reduced resolution alone does not hinder registration. In contrast, real low-field data exhibited lower accuracy, primarily due to geometric distortion and other acquisition-specific artifacts. Among the tested approaches, the synthesis-based pipeline achieved the most robust performance across subjects and modalities. Overall, existing algorithms can accommodate resolution limitations, however, future methods could further enhance coregistration by explicitly addressing the distortions present in low-field MRI scans.

neuroscience↗

bioRxiv2026

An integrated platform for simultaneous wide-field voltage/calcium imaging and fMRI (EPI & ZTE) reveals neuronal infraslow dynamics underlying functional connectivity

Wide-field optical imaging acquired simultaneously with functional MRI (fMRI) has the ability to provide unprecedented insight into the neural origins of time-varying whole-brain activity. Simultaneously linking cellular-scale activity to whole-brain fMRI remains challenging due to optical access, RF coil placement, and transmission constraints in the MRI environment. We present an integrated platform that combines a long-distance tube-lens optical path (>98% transmission), a chronically stable optically-fused cranial window, and a subject-conformal RF surface coil compatible with both echo planar imaging (EPI) and zero-echo-time (ZTE) fMRI. The system supports concurrent wide-field imaging of genetically encoded voltage or calcium indicators concurrently with intrinsic hemoglobin signals. In individual mice, wide-field optical and fMRI measures yield concordant functional connectivity, and cross-modal timing analyses demonstrate that neuronal infraslow dynamics (<0.1 Hz) underlie the majority of fMRI connectivity, after removing hemodynamic crosstalk. The platform's sensitivity, chronic stability, and sequence flexibility broaden access to cellular-to-whole-brain investigations across basic and translational neuroimaging.

neuroscience↗

bioRxiv2021

Benchmarking Geometric Deep Learning for Cortical Segmentation and Neurodevelopmental Phenotype Prediction

The emerging field of geometric deep learning extends the application of convolutional neural networks to irregular domains such as graphs, meshes and surfaces. Several recent studies have explored the potential for using these techniques to analyse and segment the cortical surface. However, there has been no comprehensive comparison of these approaches to one another, nor to existing Euclidean methods, to date. This paper benchmarks a collection of geometric and traditional deep learning models on phenotype prediction and segmentation of sphericalised neonatal cortical surface data, from the publicly available Developing Human Connectome Project (dHCP). Tasks include prediction of postmenstrual age at scan, gestational age at birth and segmentation of the cortical surface into anatomical regions defined by the M-CRIB-S atlas. Performance was assessed not only in terms of model precision, but also in terms of network dependence on image registration, and model interpretation via occlusion. Networks were trained both on sphericalised and anatomical cortical meshes. Findings suggest that the utility of geometric deep learning over traditional deep learning is highly task-specific, which has implications for the design of future deep learning models on the cortical surface. The code, and instructions for data access, are available from https://github.com/Abdulah-Fawaz/Benchmarking-Surface-DL.

neuroscience↗