Vikas Singh

Tata Memorial Hospital

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Sterling C. Johnson

University of Wisconsin–Madison

Sathya N. Ravi

University of Illinois Chicago

Nagesh Adluru

University of Wisconsin–Madison

Vamsi Krishna Ithapu

META Health

Barbara B. Bendlin

University of Wisconsin–Madison

Rudrasis Chakraborty

Lawrence Livermore National Laboratory

Lopamudra Mukherjee

Indian Institute of Technology Guwahati

Jinhui Xu

University at Buffalo, State University of New York

Hyunwoo J. Kim

Korea University

Won Hwa Kim

Pohang University of Science and Technology

Cooperative Institutions

Alzheimer’s Disease Neuroimaging Initiative

312

University of California, San Francisco

210

San Francisco VA Medical Center

176

Cohort (United Kingdom)

144

University of Wisconsin–Madison

137

Washington University in St. Louis

University of Pennsylvania

Homi Bhabha National Institute

Tata Memorial Hospital

Harvard University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Scaling Recurrent Models via Orthogonal Approximations in Tensor Trains

2021 IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

Ronak Mehta Rudrasis Chakraborty Vikas Singh Yunyang Xiong

Modern deep networks have proven to be very effective for analyzing real world images. However, their application in medical imaging is still in its early stages, primarily due to the large size of three-dimensional images, requiring enormous convolutional or fully connected layers - if we treat an image (and not image patches) as a sample. These issues only compound when the focus moves towards longitudinal analysis of 3D image volumes through recurrent structures, and when a point estimate of model parameters is insufficient in scientific applications where a reliability measure is necessary. Using insights from differential geometry, we adapt the tensor train decomposition to construct networks with significantly fewer parameters, allowing us to train powerful recurrent networks on whole brain image volume sequences. We describe the "orthogonal" tensor train, and demonstrate its ability to express a standard network layer both theoretically and empirically. We show its ability to effectively reconstruct whole brain volumes with faster convergence and stronger confidence intervals compared to the standard tensor train decomposition. We provide code and show experiments on the ADNI dataset using image sequences to regress on a cognition related outcome.

10.1109/iccv.2019.01067

Cite

Citations (4)

SHG imaging and analysis of collagen fiber/fibril architecture in human ovarian cancer using machine learning and emission directionality

Paul J. Campagnola Melissa Champer Emily Shelton Vikas Singh

We have shown that diseases including cancers and fibroses have significant changes in the collagen fibril and fiber structure. We have used machine learning methods to classify normal and diseased tissues based on the fiber morphology in SHG images, however the important features remain unknown. Using the StyleGAN framework, we trained the latent space and used PCA for this determination. We found that curvature and density were the most important attributes in ovarian cancer. We previously demonstrated qualitative differences in the fibril size and spacing in several tissues. We now developed a more complete computational model of 3D phasematching. This in conjunction with wavelength- dependent measurements of the spatial emission pattern, will afford the extraction of average fibril size and packing. Collectively these determinations will be broadly applicable to identifying characteristic diagnostic targets in a wide range of diseases.

Collagen fiber

Collagen fibril

10.1117/12.3001103

Cite

Citations (0)

TCT-9 Invasive Strategy Versus Medical Therapy in Older Adults ≥75 Years of Age With Non–ST-Segment Elevation Acute Coronary Syndrome: A Systematic Review and Meta-analysis

Journal of the American College of Cardiology (2022)

Amit Rout Aakash Garg Vivek Lohana Vikas Singh Jennifer A. Rymer

Elevation (ballistics)

Medical Therapy

10.1016/j.jacc.2022.08.017

Cite

Citations (0)

P4-048: PREDICTING AMYLOID ACCUMULATION TRAJECTORIES IN A RISK-ENRICHED ALZHEIMER'S DISEASE COHORT WITH DEEP CONDITIONAL NEURAL NETWORKS

Alzheimer s & Dementia (2019)

Seong Jae Hwang Rebecca L. Koscik Tobey J. Betthauser Zirui Tao Won Hwa Kim

Understanding the longitudinal pattern of amyloid accumulation is crucial for the early detection and intervention in Alzheimer's disease (AD). Specifically, the onset time (OT) when amyloid accumulation crosses a critical threshold is one of the earliest signs of AD progression. In this study, we developed a sequential neural network to 1) extrapolate the PiB-PET amyloid trajectories retrospectively, 2) estimate the subject- and region-wise OTs, and 3) investigate their associations with an AD-risk factor in a preclinical cohort. Cognitively asymptomatic participants from the Wisconsin Registry for Alzheimer's Prevention (N=106) with three longitudinal [C11] PiB-PET scans separated by approximately 2 to 6 years were included. For each timepoint and subject, we measured the PiB distribution volume ratio (PiB-DVR) in 8 bilateral AAL regions and the age at scan. We developed a conditional recurrent invertible neural network called CRow which maps PiB-DVR trajectories to corresponding ages and predicts PiB-DVR trajectories beyond observed ages. We used all 106 subjects to train CRow and retrospectively predict their OTs. Following prior studies, the age when PiB-DVR reaches 1.2 was considered as the OT (minimum at 45). For each region, we tested the difference of the OTs between APOE+ (ε4-allele) and APOE- (no ε4-allele) groups using the two-sample t-test. Only the subjects with OTs (i.e., initially PiB-DVR < 1.2 but eventually PiB-DVR >= 1.2) in the corresponding regions were tested. Fig. 1 shows the predicted trajectories (dashed) given the original trajectories (solid) of the subjects with OTs in left-superior-temporal-gyrus (left) where the OTs were significantly different between the APOE groups (α=0.05 with the Bonferroni correction). Taking the average of the PiB-DVR trajectories across all 16 regions of those corresponding subjects (Fig. 1, right) showed no group differences, suggesting that the region-wise analysis is advantageous.

Pittsburgh compound B

Apolipoprotein E

10.1016/j.jalz.2019.06.3707

Cite

Citations (0)

Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population

NeuroImage (2010)

Chris Hinrichs Vikas Singh Guofan Xu Sterling C. Johnson

Modality (human–computer interaction)

10.1016/j.neuroimage.2010.10.081

Cite

Citations (391)

THE CHALLENGES AND IMPACT OF THE FINANCIAL SYSTEM ON ECONOMIC GROWTH IN THE CONTEXT OF THE INDIAN ECONOMY

ShodhKosh Journal of Visual and Performing Arts (2024)

Sameer Yadav Saurabh Singh Sanjay Kumar Singh Vikas Singh

This paper examines the intricate relationship between the financial system and economic growth in India, focusing on the challenges and potential impact of the financial sector on sustainable development. As one of the world’s fastest-growing economies, India faces unique financial challenges, including financial inclusion, regulatory concerns, digital transformation, and evolving macroeconomic conditions. The study analyzes the role of financial intermediaries, banking reforms, and capital markets in fostering economic growth, alongside systemic risks such as non-performing assets (NPAs) and currency volatility. By leveraging data from the Reserve Bank of India (RBI) and economic indicators, the paper highlights the dynamic role of the financial sector as a growth enabler, as well as the structural and policy challenges that could impede progress. Through a review of existing literature and empirical evidence, the study aims to contribute to a nuanced understanding of how India’s financial system can better support inclusive and stable economic growth.

10.29121/shodhkosh.v5.i5.2024.2598

Cite

Citations (0)

Preoperative neurocognitive dysfunction in and Indian cohort of brain tumor patients and factors associated with domain-specific dysfunction

WFNOS 2022 Abstract Book (2022)

Aliasgar Moiyadi Kanchi Jain Prakash Shetty Vikas Singh Parthiban Velayutham

Neurocognitive

Brain tumor

10.14791/btrt.2022.10.f-2668

Cite

Citations (0)

Multi-resolution statistical analysis on graph structured data in neuroimaging

2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) (2015)

Won Hwa Kim Vikas Singh Moo K. Chung Nagesh Adluru Barbara B. Bendlin

Statistical data analysis plays a major role in discovering structural and functional imaging phenotypes for mental disorders such as Alzheimer's disease (AD). The goal here is to identify, ideally early on, which regions in the brain show abnormal variations with a disorder. To make the method more sensitive, we rely on a multi-resolutional perspective of the given data. Since the underlying imaging data (such as cortical surfaces and connectomes) are naturally represented in the form of weighted graphs which lie in a non-Euclidean space, we introduce recent work from the harmonics literature to derive an effective multi-scale descriptor using wavelets on graphs that characterize the local context at each data point. Using this descriptor, we demonstrate experiments where we identify significant differences between AD and control populations using cortical surface data and tractography derived graphs/networks.

10.1109/isbi.2015.7164173

Cite

Citations (1)

Canonical Correlation Analysis on SPD(n) Manifolds

Springer eBooks (2015)

Hyunwoo J. Kim Nagesh Adluru Barbara B. Bendlin Sterling C. Johnson Baba C. Vemuri

Canonical correlation

10.1007/978-3-319-22957-7_4

Cite

Citations (5)

Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images

2009 IEEE Conference on Computer Vision and Pattern Recognition (2014)

Hyunwoo J. Kim Nagesh Adluru Maxwell D. Collins Moo K. Chung Barbara B. Bendin

Linear regression is a parametric model which is ubiquitous in scientific analysis. The classical setup where the observations and responses, i.e., (xi , yi ) pairs, are Euclidean is well studied. The setting where yi is manifold valued is a topic of much interest, motivated by applications in shape analysis, topic modeling, and medical imaging. Recent work gives strategies for max-margin classifiers, principal components analysis, and dictionary learning on certain types of manifolds. For parametric regression specifically, results within the last year provide mechanisms to regress one real-valued parameter, xi ∈ R, against a manifold-valued variable, yi ∈ . We seek to substantially extend the operating range of such methods by deriving schemes for multivariate multiple linear regression -a manifold-valued dependent variable against multiple independent variables, i.e., f : Rn → . Our variational algorithm efficiently solves for multiple geodesic bases on the manifold concurrently via gradient updates. This allows us to answer questions such as: what is the relationship of the measurement at voxel y to disease when conditioned on age and gender. We show applications to statistical analysis of diffusion weighted images, which give rise to regression tasks on the manifold GL(n)/O(n) for diffusion tensor images (DTI) and the Hilbert unit sphere for orientation distribution functions (ODF) from high angular resolution acquisition. The companion open-source code is available on nitrc.org/projects/riem_mglm.

Manifold (fluid mechanics)

Riemannian manifold

Univariate

Statistical manifold

10.1109/cvpr.2014.352

Cite

Citations (49)