About

Ashok Veeraraghavan is a faculty member in the Department of Electrical and Computer Engineering at Rice University. His research focuses on Artificial Intelligence and Machine Learning. He is associated with the Rice University School of Engineering and Computing, contributing to the fields of data science and related areas.

Research topics

• Computer Science
• Physics
• Optics
• Computer vision
• Artificial Intelligence
• Mathematics
• Nanotechnology
• Algorithm
• Human–computer interaction
• Materials science

Selected publications

• Bias-Aware Conformal Prediction for Metric-Based Imaging Pipelines

  2026-04-08

  preprintOpen access

  Reliable confidence measures of metrics derived from medical imaging reconstruction pipelines would improve the standard of decision-making in many clinical workflows. Conformal Prediction (CP) provides a robust framework for producing calibrated prediction intervals, but standard CP formulations face a critical challenge in the imaging pipeline: common mismatches between image reconstruction objectives and downstream metrics can introduce systematic prediction deviations from ground truth values, known as bias. These biases in turn compromise the efficiency of prediction intervals, which is a problem that has been unexplored in the CP literature. In this study, we formalize the behavior of symmetric (where bounds expand equally in both directions) and asymmetric (where bounds expand unequally) formulations for common non-conformity scores in CP in the presence of bias, and argue that this measurable bias must inform the choice of CP formulation. We theoretically and empirically demonstrate that symmetric intervals are inflated by a factor of two times the magnitude of bias while asymmetric intervals remain unaffected by bias, and provide conditions under which each formulation produces tighter intervals. We empirically validated our theoretical analyses on sparse-view CT reconstruction for downstream radiotherapy planning. Our work enables users of medical imaging pipelines to proactively select optimal CP formulations, thereby improving interval length efficiency for critical downstream metrics.

  PublisherOA PDFDOI

• Guidestar-Free Adaptive Optics with Asymmetric Apertures

  ACM Transactions on Graphics · 2026-04-17

  articleOpen accessSenior author

  This work introduces the first closed-loop adaptive optics (AO) system capable of optically correcting aberrations in real-time without a guidestar or a wavefront sensor. Nearly 40 years ago, Cederquist et al. demonstrated that asymmetric apertures enable phase retrieval (PR) algorithms to perform fully computational wavefront sensing, albeit at a high computational cost. More recently, Chimitt et al. extended this approach with machine learning and demonstrated real-time wavefront sensing using only a single (guidestar-based) point-spread-function (PSF) measurement. Inspired by these works, we introduce a guidestar-free AO framework built around asymmetric apertures and machine learning. Our approach combines three key elements: (1) an asymmetric aperture placed at the system’s pupil plane that enables PR-based wavefront sensing, (2) a pair of machine learning algorithms that estimate the PSF from natural scene measurements and reconstruct phase aberrations, and (3) a spatial light modulator that performs optical correction. We experimentally validate this framework on dense natural scenes imaged through unknown obscurants. Our method outperforms state-of-the-art guidestar-free wavefront shaping methods, using an order of magnitude fewer measurements and three orders of magnitude less computation.

  PublisherDOI

• High-power dual-channel chamber for high-frequency magnetic neuromodulation

  Journal of Neural Engineering · 2026-03-19

  articleOpen access

  Abstract Objective. Several novel methods, including magnetogenetics and magnetoelectric stimulation, use high frequency alternating magnetic fields to precisely manipulate neural activity. To quantify the behavioral effects of such interventions in a freely moving mouse, we developed a dual-channel magnetic chamber, specifically designed for rate-sensitive magnetothermal-genetic stimulation, and adaptable for other uses of alternating magnetic fields. Approach. Through an optimized coil design, the system allows independent control of two spatially orthogonal uniform magnetic fields delivered at different frequencies within a 10 × 10 × 6 cm 3 chamber suitable for mouse studies. The two channels have nominal frequencies of 50 and 550 kHz with peak magnetic field strengths of 88 and 12.5 mT, achieved with resonant coil drives having peak voltages of 1.6 and 1.8 kV and currents of 1.0 and 0.26 kA, respectively. Additionally, a liquid cooling system enables magnetic field generation for second-level durations, and an observation port and camera allow video capture of the animal’s behavior within the chamber. Main results. The system generates high-amplitude magnetic fields across two widely separated frequency channels with negligible interference (<1%). Relatively uniform magnetic field distribution (±10% across 94% of the chamber volume) is maintained throughout the chamber, and temperature increase of the inner side of the coil enclosure during the operation is limited to <0.35 °C s −1 to ensure in vivo safety. Using cobalt-doped and undoped iron oxide nanoparticles, we demonstrate channel-specific heating rates of 3.5 °C s −1 and 1.5 °C s −1 , respectively, validating frequency-selectivity. Both channels can run continuously for 4 s stably. Significance. We present a novel magnetic stimulation platform that combines high-frequency, high-power capability with two independently-controlled channels generating different frequencies, along with a real-time behavioral observation system for freely moving animals. The system supports frequency-multiplexed stimulation strategies for precise modulation of neural activity, making it a versatile tool for advancing magnetogenetics, neural circuit interrogation, and noninvasive stimulation approaches in neuroscience and bioengineering.

  PublisherDOI

• Spatially resolved label-free multimodal multiphoton imaging reveals inflammation-induced lipid remodeling in triple-negative breast cancer following NOS2 inactivation and COX-2 inhibition

  2026-01-15

  article
  PublisherDOI

• Dual-modality, deep-learning-enabled endomicroscope with large field-of-view and depth-of-field for real-time in vivo imaging of epithelial hallmarks of cancer

  bioRxiv (Cold Spring Harbor Laboratory) · 2026-01-15 · 1 citations

  articleOpen access

  Abstract In vivo microscopy (IVM) has shown great promise to improve early detection of epithelial precancer, but it suffers from fundamental trade-offs that limit the resolution, field-of-view (FOV) and depth-of-field (DOF). Here, we present PrecisionView, a compact, deep-learning-enabled endomicroscope that breaks these constrains and achieves 20 mm 2 FOV and 500 µm DOF with 4 µm resolution, representing approximately 5× increase in FOV and 8× larger DOF compared to conventional IVM with similar resolution. PrecisionView integrates a deep-learning optimized phase mask and real-time reconstruction, enabling rapid in vivo assessment of two key hallmarks of cancer: epithelial cell nuclear morphology and subsurface microvasculature through fluorescence and reflectance imaging. By imaging oral cavity of healthy volunteers and cervical specimens with precancerous lesions, PrecisionView generates large-scale (1-3 cm 2 ) co-registered maps of cellular and vascular structures, revealing distinct microscopic patterns associated with anatomic structures and precancerous lesions. Our results suggest the potential of this computational endomicroscope to address the unmet need for early cancer detection at the point-of-care.

  PublisherOA PDFDOI

• Privacy-Aware Meta-Optics for Person Detection

  ACS Photonics · 2026-03-13

  articleOpen accessSenior authorCorresponding

  The ubiquitous use of computer vision technologies in our personal lives has led to privacy concerns. This paper presents a computational camera that optically filters out private attributes such as identity and still enables downstream vision task of person detection. Our approach involves replacing a traditional lens in an imaging setup with broadband meta-optics (MOs), the parameters of which are optimized in an end-to-end fashion using a differentiable look-up table for the MO and a person detection neural network. Privacy is introduced to the optimization pipeline using a novel and computationally inexpensive private Strehl integral regularization to preserve low-frequency details while filtering out high-frequency details that contain facial identity information. We experimentally validate our approach using captures from our privacy-aware meta-optics and demonstrate that this method achieves a better privacy utility trade-off compared to existing techniques. As such, we present the first privacy-aware broadband meta-optics for person detection.

  PublisherDOI

• Efficient Conformal Volumetry for Template-Based Segmentation

  arXiv (Cornell University) · 2026-02-28

  preprintOpen access

  Template-based segmentation, a widely used paradigm in medical imaging, propagates anatomical labels via deformable registration from a labeled atlas to a target image, and is often used to compute volumetric biomarkers for downstream decision-making. While conformal prediction (CP) provides finite-sample valid intervals for scalar metrics, existing segmentation-based uncertainty quantification (UQ) approaches either rely on learned model features, often unavailable in classic template-based pipelines, or treat the registration process as a black box, resulting in overly conservative intervals when applied directly in output space. We introduce ConVOLT, a CP framework that achieves efficient volumetric UQ by conditioning calibration on properties of the estimated deformation field from template-based segmentation. ConVOLT calibrates a learned volumetric scaling factor from deformation space features. We evaluate ConVOLT on template-based segmentation tasks involving global, regional, and label volumetry across multiple datasets and registration methods. ConVOLT achieves target coverage while producing substantially tighter intervals than output-space conformal baselines. Our work paves way to exploit the registration process for efficient UQ in medical imaging pipelines.

  PublisherDOI

• Guidestar-Free Adaptive Optics with Asymmetric Apertures

  Open MIND · 2026-02-02

  preprintSenior author

  This work introduces the first closed-loop adaptive optics (AO) system capable of optically correcting aberrations in real-time without a guidestar or a wavefront sensor. Nearly 40 years ago, Cederquist et al. demonstrated that asymmetric apertures enable phase retrieval (PR) algorithms to perform fully computational wavefront sensing, albeit at a high computational cost. More recently, Chimitt et al. extended this approach with machine learning and demonstrated real-time wavefront sensing using only a single (guidestar-based) point-spread-function (PSF) measurement. Inspired by these works, we introduce a guidestar-free AO framework built around asymmetric apertures and machine learning. Our approach combines three key elements: (1) an asymmetric aperture placed at the system's pupil plane that enables PR-based wavefront sensing, (2) a pair of machine learning algorithms that estimate the PSF from natural scene measurements and reconstruct phase aberrations, and (3) a spatial light modulator that performs optical correction. We experimentally validate this framework on dense natural scenes imaged through unknown obscurants. Our method outperforms state-of-the-art guidestar-free wavefront shaping methods, using an order of magnitude fewer measurements and three orders of magnitude less computation.

  DOI

• Efficient Conformal Volumetry for Template-Based Segmentation

  ArXiv.org · 2026-02-28

  articleOpen access

  Template-based segmentation, a widely used paradigm in medical imaging, propagates anatomical labels via deformable registration from a labeled atlas to a target image, and is often used to compute volumetric biomarkers for downstream decision-making. While conformal prediction (CP) provides finite-sample valid intervals for scalar metrics, existing segmentation-based uncertainty quantification (UQ) approaches either rely on learned model features, often unavailable in classic template-based pipelines, or treat the registration process as a black box, resulting in overly conservative intervals when applied directly in output space. We introduce ConVOLT, a CP framework that achieves efficient volumetric UQ by conditioning calibration on properties of the estimated deformation field from template-based segmentation. ConVOLT calibrates a learned volumetric scaling factor from deformation space features. We evaluate ConVOLT on template-based segmentation tasks involving global, regional, and label volumetry across multiple datasets and registration methods. ConVOLT achieves target coverage while producing substantially tighter intervals than output-space conformal baselines. Our work paves way to exploit the registration process for efficient UQ in medical imaging pipelines.

  PublisherOA PDF

• The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations

  arXiv (Cornell University) · 2026-03-30

  articleOpen access

  The approximation and convergence properties of implicit neural representations (INRs) are known to be highly sensitive to parameter initialization strategies. While several data-driven initialization methods demonstrate significant improvements over standard random sampling, the reasons for their success -- specifically, whether they encode classical statistical signal priors or more complex features -- remain poorly understood. In this study, we explore this phenomenon through a series of experimental analyses leveraging noise pretraining. We pretrain INRs on diverse noise classes (e.g., Gaussian, Dead Leaves, Spectral) and measure their ability to both fit unseen signals and encode priors for an inverse imaging task (denoising). Our analyses on image and video data reveal a surprising finding: simply pretraining on unstructured noise (Uniform, Gaussian) dramatically improves signal fitting capacity compared to all other baselines. However, unstructured noise also yields poor deep image priors for denoising. In contrast, we also find that noise with the classic $1/|f^α|$ spectral structure of natural images achieves an excellent balance of signal fitting and inverse imaging capabilities, performing on par with the best data-driven initialization methods. This finding enables more efficient INR training in applications lacking sufficient prior domain-specific data. For more details, visit project page at https://kushalvyas.github.io/noisepretraining.html

  PublisherOA PDF

Recent grants

• FlatScopes for Implantable and Scalable Optical Imaging of Neural Activity

  NIH · $430k · 2018–2020

• SaTC: CORE: Medium: Collaborative: Presentation-attack-robust biometrics systems via computational imaging of physiology and materials

  NSF · $318k · 2018–2022

• EAGER: Fabrication of Thin, Lens-Free Cameras for Visible and SWIR Imaging

  NSF · $150k · 2015–2017

• Deep learning microscope for slide-free and digital histology

  NIH · $3.5M · 2022–2027

• Collaborative Research: RI: Medium: Thermal Computational Imaging

  NSF · $616k · 2021–2025

Frequent coauthors

• Vivek Boominathan

  Rice University

  90 shared

• Jacob T. Robinson

  Baylor College of Medicine

  44 shared

• Chaojian Li

  Georgia Institute of Technology

  40 shared

• Richard G. Baraniuk

  37 shared

• Ashutosh Sabharwal

  Rice University

  37 shared

• Rama Chellappa

  37 shared

• Ph Lin

  Rice University

  36 shared

• Aswin C. Sankaranarayanan

  Carnegie Mellon University

  34 shared