Kuldeep Kumar

Laurent Chauvin, Kuldeep Kumar, Christian Desrosiers et al.

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 proposed to quantify the variability of keypoint geometry in location and scale. Our distance measure may be estimated between $O(N^2)$ image pairs in $O(N~\log~N)$ operations via keypoint indexing. Experiments report the first results for the task of predicting family relationships from medical images, using 1010 T1-weighted MRI brain volumes of 434 families including monozygotic and dizygotic twins, siblings and half-siblings sharing 100%-25% of their polymorphic genes. Soft set equivalence and the keypoint geometry kernel improve upon standard hard set equivalence (HSE) and appearance kernels alone in predicting family relationships. Monozygotic twin identification is near 100%, and three subjects with uncertain genotyping are automatically paired with their self-reported families, the first reported practical application of image-based family identification. Our distance measure can also be used to predict group categories, sex is predicted with an AUC=0.97. Software is provided for efficient fine-grained curation of large, generic image datasets.

Kuldeep Kumar, Kaleem Siddiqi, Christian Desrosiers

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 this work, we address this by proposing a set of kernel dictionary learning and sparsity priors based methods. Proposed frameworks include L-0 norm, group sparsity, as well as manifold regularization prior. The proposed methods allow streamlines to be assigned to more than one bundle, making it more robust to overlapping bundles and inter-subject variations. We evaluate the performance of our method on a labeled set and data from Human Connectome Project. Results highlight the ability of our method to group streamlines into plausible bundles and illustrate the impact of sparsity priors on the performance of the proposed methods.

Kuldeep Kumar, Laurent Chauvin, Mathew Toews et al.

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 paper presents a multi-modal analysis of genetically-related subjects to compare and contrast the information provided by various MRI modalities. The proposed framework represents MRI scans as bags of SIFT features, and uses these features in a nearest-neighbor graph to measure subject similarity. Experiments using the T1/T2-weighted MRI and diffusion MRI data of 861 Human Connectome Project subjects demonstrate strong links between the proposed similarity measure and genetic proximity.

Kuldeep Kumar, Pietro Gori, Benjamin Charlier et al.

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. Recent publications have highlighted that using microstructure measures along fibers improves tractography analysis. Also, many neurodegenerative diseases impacting white matter require the study of microstructure measures as well as the white matter geometry. Motivated by these, we propose to use a novel computational model for fibers, called functional varifolds, characterized by a metric that considers both the geometry and microstructure measure (e.g. GFA) along the fiber pathway. We use it to cluster fibers with a dictionary learning and sparse coding-based framework, and present a preliminary analysis using HCP data.

Chintan Amrit, Jos van Hillegersberg, Kuldeep Kumar

Today's dynamic and iterative development environment brings significant challenges for software project management. In distributed project settings, "management by walking around" is no longer an option and project managers may miss out on key project insights. The TESNA (TEchnical Social Network Analysis) method and tool aims to provide project managers both a method and a tool for gaining insights and taking corrective action. TESNA achieves this by analysing a project's evolving social and technical network structures using data from multiple sources, including CVS, email and chat repositories. Using pattern theory, TESNA helps to identify areas where the current state of the project's social and technical networks conflicts with what patterns suggest. We refer to such a conflict as a Socio-Technical Structure Clash (STSC). In this paper we report on our experience of using TESNA to identify STSCs in a corporate environment through the mining of software repositories. We find multiple instances of three STSCs (Conway's Law, Code Ownership and Project Coordination) in many of the on-going development projects, thereby validating the method and tool that we have developed.