Kuldeep Kumar

Kuldeep Kumar
CHU Sainte-Justine Research Centre

PhD
Postdoc, Lab Jacquemont, CHU Sainte-Justine Research Center, University of Montreal.

About

38
Publications
6,099
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
163
Citations
Introduction
I am a postdoc in Prof. Jacquemont's lab, at the Centre Hospitalier Universitaire Saint Justine Research Center, UdeM, Canada. I am working on understanding the effects of rare copy number variations (CNVs), genome-wide, on cognition, brain structure, and function. I received my Ph.D. in applied research from ETS, under the supervision of Prof. Christian Desrosiers (LIVIA, ETS Montreal, Canada). My Ph.D. research focused on analyzing multi-modal human brain MRI data, using machine learning and data analysis techniques to obtain brain fingerprints for individual subject characterization. Prior to that, I worked as a Scientist in the Indian Space Research Organization (ISRO). My research interests include data science, imaging genetics, medical image analysis, and neuroscience.
Additional affiliations
October 2016 - March 2017
June 2012 - August 2013
Space Application Center
Position
  • Researcher
Education
July 2007 - June 2012
Indian Institute of Technology Kharagpur
Field of study
  • Electronics and Electrical Communications Engineering

Publications

Publications (38)
Preprint
Copy number variations (CNVs) are rare genomic deletions and duplications that can exert profound effects on brain and behavior. Previous reports of pleiotropy in CNVs imply that they converge on shared mechanisms at some level of pathway cascades, from genes to large-scale neural circuits to the phenome. However, studies to date have primarily exa...
Article
We propose a novel pairwise distance measure between image keypoint sets, for the purpose of large-scale medical image indexing. Our measure generalizes the Jaccard index to account for soft set equivalence (SSE) between keypoint elements, via an adaptive kernel framework modeling uncertainty in keypoint appearance and geometry. A new kernel is pro...
Article
Full-text available
Many copy number variants (CNVs) confer risk for the same range of neurodevelopmental symptoms and psychiatric conditions including autism and schizophrenia. Yet, to date neuroimaging studies have typically been carried out one mutation at a time, showing that CNVs have large effects on brain anatomy. Here, we aimed to characterize and quantify the...
Article
Copy Number Variants (CNVs) are associated with elevated rates of neuropsychiatric disorders. A ‘genetics-first’ approach, involving the CNV effects on the brain, irrespective of clinical symptomatology, allows investigation of mechanisms underlying neuropsychiatric disorders in the general population. Recent years have seen an increasing number of...
Article
Full-text available
Pathogenic Copy Number Variants (CNVs) and aneuploidies alter gene dosage and are associated with neurodevelopmental psychiatric disorders (NPDs) such as autism spectrum disorder or schizophrenia. Brain mechanisms mediating genetic risk for NPDs remain largely unknown, but there is a rapid increase in morphometry studies of CNVs using T1-weighted s...
Preprint
Full-text available
Polygenicity and pleiotropy are key properties of the genomic architecture of psychiatric disorders. An optimistic interpretation of polygenicity is that genomic variants converge on a limited set of mechanisms at some level from genes to behavior. Alternatively, convergence may be minimal or absent. We took advantage of brain connectivity, measure...
Article
Full-text available
Low-frequency 1q21.1 distal deletion and duplication copy number variant (CNV) carriers are predisposed to multiple neurodevelopmental disorders, including schizophrenia, autism and intellectual disability. Human carriers display a high prevalence of micro- and macrocephaly in deletion and duplication carriers, respectively. The underlying brain st...
Preprint
Full-text available
We propose a novel pairwise distance measure between variable sized sets of image keypoints for the purpose of large-scale medical image indexing. Our measure generalizes the Jaccard distance to account for soft set equivalence (SSE) between set elements, via an adaptive kernel framework accounting for uncertainty in keypoint appearance and geometr...
Preprint
Low-frequency 1q21.1 distal deletion and duplication copy number variant (CNV) carriers are predisposed to multiple neurodevelopmental disorders including schizophrenia, autism and intellectual disability. Human carriers display a high prevalence of micro- and macrocephaly in deletion and duplication carriers, respectively. The underlying brain str...
Article
Full-text available
13,15 ✉ 16p11.2 and 22q11.2 Copy Number Variants (CNVs) confer high risk for Autism Spectrum Disorder (ASD), schizophrenia (SZ), and Attention-Deficit-Hyperactivity-Disorder (ADHD), but their impact on functional connectivity (FC) remains unclear. Here we report an analysis of resting-state FC using magnetic resonance imaging data from 101 CNV carr...
Article
Full-text available
13,15 ✉ 16p11.2 and 22q11.2 Copy Number Variants (CNVs) confer high risk for Autism Spectrum Disorder (ASD), schizophrenia (SZ), and Attention-Deficit-Hyperactivity-Disorder (ADHD), but their impact on functional connectivity (FC) remains unclear. Here we report an analysis of resting-state FC using magnetic resonance imaging data from 101 CNV carr...
Preprint
Full-text available
Background: Copy Number Variants (CNVs) associated with autism and schizophrenia have large effects on brain anatomy. Yet, neuroimaging studies have been conducted one mutation at a time. We hypothesize that neuropsychiatric CNVs may exert general effects on brain morphometry because they confer risk for overlapping psychiatric conditions. Methods:...
Preprint
Full-text available
Copy number variants (CNVs) are among the most highly penetrant genetic risk factors for neuropsychiatric disorders. Their impact on brain connectivity remains mostly unstudied. Because they confer risk for overlapping conditions, we hypothesized that they may converge on shared connectivity patterns. We performed connectome-wide analyses using res...
Article
Neuroimaging studies typically adopt a common feature space for all data, which may obscure aspects of neuroanatomy only observable in subsets of a population, e.g. cortical folding patterns unique to individuals or shared by close relatives. Here, we propose to model individual variability using a distinctive keypoint signature: a set of unique, l...
Chapter
Full-text available
We propose a novel distance measure between variable-sized sets of image features, i.e. the bag-of-features image representation, for quantifying brain morphology similarity based on local neuroanatomical structures. Our measure generalizes the Jaccard distance metric to account for probabilistic or soft set equivalence (SSE), via a novel adaptive...
Article
This work presents an efficient framework, based on manifold approximation, for generating brain fingerprints from multi-modal data. The proposed framework represents images as bags of local features which are used to build a subject proximity graph. Compact fingerprints are obtained by projecting this graph in a low-dimensional manifold using spec...
Thesis
Full-text available
Understanding the structure and function of the human brain is an outstanding problem that is critical to the development of efficient treatments for neurological diseases like Alzheimer's and Parkinson's. While most studies make group level inferences, researchers have established that structure and function show variability across individuals. M...
Preprint
Full-text available
Diffusion magnetic resonance imaging, a non-invasive tool to infer white matter fiber connections, produces a large number of streamlines containing a wealth of information on structural connectivity. The size of these tractography outputs makes further analyses complex, creating a need for methods to group streamlines into meaningful bundles. In t...
Article
Full-text available
Diffusion magnetic resonance imaging, a non-invasive tool to infer white matter fiber connections, produces a large number of streamlines containing a wealth of information on structural connectivity. The size of these tractography outputs makes further analyses complex, creating a need for methods to group streamlines into meaningful bundles. In t...
Poster
Full-text available
Background • Context: → While most brain studies focus on extracting population-level characteristics, the brains of individuals are unique in terms of function, structure, and white matter organization; → Recent advances in hardware, analysis tools, and large-scale brain initiatives (HCP [1]) have allowed to quantify this uniqueness using the conc...
Article
Full-text available
This work presents an efficient framework, based on manifold approximation, for generating brain fingerprints from multi-modal data. The proposed framework represents images as bags of local features, which are used to build a subject proximity graph. Compact fingerprints are obtained by projecting this graph in a low-dimensional manifold, using sp...
Article
Full-text available
The extraction of fibers from dMRI data typically produces a large number of fibers, it is common to group fibers into bundles. To this end, many specialized distance measures, such as MCP, have been used for fiber similarity. However, these distance based approaches require point-wise correspondence and focus only on the geometry of the fibers. Re...
Article
Full-text available
So far, fingerprinting studies have focused on identifying features from single-modality MRI data, which capture individual characteristics in terms of brain structure, function, or white matter microstructure. However, due to the lack of a framework for comparing across multiple modalities, studies based on multi-modal data remain elusive. This pa...
Conference Paper
Full-text available
The extraction of fibers from dMRI data typically produces a large number of fibers, it is common to group fibers into bundles. To this end, many specialized distance measures, such as MCP, have been used for fiber similarity. However, these distance based approaches require point-wise correspondence and focus only on the geometry of the fibers. Re...
Conference Paper
Full-text available
So far, fingerprinting studies have focused on identifying features from single-modality MRI data, which capture individual characteristics in terms of brain structure, function, or white matter microstruc-ture. However, due to the lack of a framework for comparing across multiple modalities, studies based on multi-modal data remain elusive. This p...
Article
Full-text available
White matter characterization studies use the information provided by diffusion magnetic resonance imaging (dMRI) to draw cross-population inferences. However, the structure, function, and white matter geometry vary across individuals. Here, we propose a subject fingerprint, called Fiberprint, to quantify the individual uniqueness in white matter g...
Conference Paper
Full-text available
We present a kernel dictionary learning method to cluster fiber tracts obtained from diffusion Magnetic Resonance Imaging (dMRI) data. This method extends the kernelized Orthogonal Matching Pursuit (kOMP) model by adding non-negativity constraints to the dictionary and sparse weights, and uses an efficient technique based on non-negative tri-factor...
Conference Paper
Full-text available
This paper presents a novel method that combines kernel-ized dictionary learning and group sparsity to efficiently cluster white matter fiber tracts obtained from diffusion Magnetic Resonance Imaging (dMRI). Instead of having an explicit feature representation for the fibers, this method uses a non-linear kernel and specialized distance measures th...

Network

Cited By