Biology subjects

Ozarkar, S. S.

Publications and source records attributed to Ozarkar, S. S..

5 recordsLinked to original sources

bioRxiv2025

SORDINO for Silent, Sensitive, Specific, and Artifact-Resisting fMRI in awake behaving mice

Blood-oxygenation-level-dependent (BOLD) functional magnetic resonance imaging (fMRI) has revolutionized our understanding of the brain activity landscape, bridging circuit neuroscience in animal models with noninvasive brain mapping in humans. This immensely utilized technique, however, faces challenges such as acoustic noise, electromagnetic interference, motion artifacts, magnetic-field inhomogeneity, and limitations in sensitivity and specificity. Here, we introduce Steady-state On-the-Ramp Detection of INduction-decay with Oversampling (SORDINO), a transformative fMRI technique that addresses these challenges by maintaining a constant total gradient amplitude while acquiring data during continuously changing gradient direction. When benchmarked against conventional fMRI on a 9.4T system, SORDINO is silent, sensitive, specific, and resistant to motion and susceptibility artifacts. SORDINO offers superior compatibility with multimodal experiments and carries novel contrast mechanisms distinct from BOLD. It also enables brain-wide activity and connectivity mapping in awake, behaving mice, overcoming stress- and motion-related confounds that are among the most challenging barriers in current animal fMRI studies.

neuroscience↗

bioRxiv2025

Parameter Efficient Fine-tuning of Transformer-based Masked Autoencoder Enhances Resource Constrained Neuroimage Analysis

Recent innovations in artificial intelligence (AI) have increasingly focused on large-scale foundational models that are more general purpose in contrast to conventional models trained to perform specialized tasks. Transformer-based architectures have become the standard backbone in foundation models across data modalities (image, text, audio, video). There has been a keen interest in applying parameter-efficient fine-tuning (PEFT) methods to adapt these models to specialized downstream tasks in language and vision. These methods are particularly essential for medical image analysis where the limited availability of training data could lead to overfitting. In this work, we evaluated different types of PEFT methods on pre-trained vision transformers relative to typical training approaches, such as full fine-tuning and training from scratch. We used a transformer-based masked autoencoder (MAE) framework, to pretrain a vision encoder on T1- weighted (T1-w) brain MRIs. The pretrained vision transformers were then fine-tuned using different PEFT methods that reduced the trainable model parameters to as few as 0.04% of the original model size. Our study shows that: 1. PEFT methods were competitive with or outperformed the reference full fine-tuning approach and outperformed training from scratch, with only a fraction of the trainable parameters; 2. PEFT methods with a 32% reduction in model size boosted Alzheimers disease (AD) classification by 3% relative to full fine-tuning and 11% relative to a 3D CNN, with only 258 training scans; and 3. PEFT methods performed well on diverse neuroimaging tasks including AD and Parkinsons disease (PD) classification, and "brain-age" prediction based on T1-w MRI datasets - a standard benchmark for deep learning models in neuroimaging; 4. smaller model sizes were competitive with larger models in test performance. Our results show the value of adapting foundation models to neuroimaging tasks efficiently and effectively in contrast to training stand- alone special purpose models.

neuroscience↗

bioRxiv2024

Evaluating Synthetic Diffusion MRI Maps created with Diffusion Denoising Probabilistic Models

Generative AI models, such as Stable Diffusion, DALL-E, and MidJourney, have recently gained widespread attention as they can generate high-quality synthetic images by learning the distribution of complex, high-dimensional image data. These models are now being adapted for medical and neuroimaging data, where AI-based tasks such as diagnostic classification and predictive modeling typically use deep learning methods, such as convolutional neural networks (CNNs) and vision transformers (ViTs), with interpretability enhancements. In our study, we trained latent diffusion models (LDM) and denoising diffusion probabilistic models (DDPM) specifically to generate synthetic diffusion tensor imaging (DTI) maps. We developed models that generate synthetic DTI maps of mean diffusivity by training on real 3D DTI scans, and evaluating realism and diversity of the synthetic data using maximum mean discrepancy (MMD) and multi-scale structural similarity index (MS-SSIM). We also assess the performance of a 3D CNN-based sex classifier, by training on combinations of real and synthetic DTIs, to check if performance improved when adding the synthetic scans during training, as a form of data augmentation. Our approach efficiently produces realistic and diverse synthetic data, potentially helping to create interpretable AI-driven maps for neuroscience research and clinical diagnostics.

neuroscience↗

bioRxiv2024

Brain Age Analysis and Dementia Classification using Convolutional Neural Networks trained on Diffusion MRI: Tests in Indian and North American Cohorts

Deep learning models based on convolutional neural networks (CNNs) have been used to classify Alzheimers disease or infer dementia severity from T1-weighted brain MRI scans. Here, we examine the value of adding diffusion-weighted MRI (dMRI) as an input to these models. Much research in this area focuses on specific datasets such as the Alzheimers Disease Neuroimaging Initiative (ADNI), which assesses people of North American, largely European ancestry, so we examine how models trained on ADNI, generalize to a new population dataset from India (the NIMHANS cohort). We first benchmark our models by predicting "brain age" - the task of predicting a persons chronological age from their MRI scan and proceed to AD classification. We also evaluate the benefit of using a 3D CycleGAN approach to harmonize the imaging datasets before training the CNN models. Our experiments show that classification performance improves after harmonization in most cases, as well as better performance for dMRI as input.

neuroscience↗

bioRxiv2023

Predicting Brain Amyloid Positivity from T1 weighted brain MRI and MRI-derived Gray Matter, White Matter and CSF maps using Transfer Learning on 3D CNNs

Abnormal {beta}-amyloid (A{beta}) accumulation in the brain is an early indicator of Alzheimers disease and practical tests could help identify patients who could respond to treatment, now that promising anti-amyloid drugs are available. Even so, A{beta} positivity (A{beta}+) is assessed using PET or CSF assays, both highly invasive procedures. Here, we investigate how well A{beta}+ can be predicted from T1 weighted brain MRI and gray matter, white matter and cerebrospinal fluid segmentations from T1-weighted brain MRI (T1w), a less invasive alternative. We used 3D convolutional neural networks to predict A{beta}+ based on 3D brain MRI data, from 762 elderly subjects (mean age: 75.1 yrs. {+/-}7.6SD; 394F/368M; 459 healthy controls, 67 with MCI and 236 with dementia) scanned as part of the Alzheimers Disease Neuroimaging Initiative. We also tested whether the accuracy increases when using transfer learning from the larger UK Biobank dataset. Overall, the 3D CNN predicted A{beta}+ with 76% balanced accuracy from T1w scans. The closest performance to this was using white matter maps alone when the model was pre-trained on an age prediction in the UK Biobank. The performance of individual tissue maps was less than the T1w, but transfer learning helped increase the accuracy. Although tests on more diverse data are warranted, deep learned models from standard MRI show initial promise for A{beta}+ estimation, before considering more invasive procedures. Clinical RelevanceEarly detection of A{beta} positivity from less invasive MRI images, could offer a screening test prior to more invasive testing procedures.

neuroscience↗