arXiv subjects

Dipanjan Sengupta

Publications and source records attributed to Dipanjan Sengupta.

3 recordsLinked to original sources

arXiv2020

Procrustean Orthogonal Sparse Hashing

Hashing is one of the most popular methods for similarity search because of its speed and efficiency. Dense binary hashing is prevalent in the literature. Recently, insect olfaction was shown to be structurally and functionally analogous to sparse hashing [6]. Here, we prove that this biological mechanism is the solution to a well-posed optimization problem. Furthermore, we show that orthogonality increases the accuracy of sparse hashing. Next, we present a novel method, Procrustean Orthogonal Sparse Hashing (POSH), that unifies these findings, learning an orthogonal transform from training data compatible with the sparse hashing mechanism. We provide theoretical evidence of the shortcomings of Optimal Sparse Lifting (OSL) [22] and BioHash [30], two related olfaction-inspired methods, and propose two new methods, Binary OSL and SphericalHash, to address these deficiencies. We compare POSH, Binary OSL, and SphericalHash to several state-of-the-art hashing methods and provide empirical results for the superiority of the proposed methods across a wide range of standard benchmarks and parameter settings.

cs.LG↗

arXiv2019

Similarity Learning with Higher-Order Graph Convolutions for Brain Network Analysis

Learning a similarity metric has gained much attention recently, where the goal is to learn a function that maps input patterns to a target space while preserving the semantic distance in the input space. While most related work focused on images, we focus instead on learning a similarity metric for neuroimages, such as fMRI and DTI images. We propose an end-to-end similarity learning framework called Higher-order Siamese GCN for multi-subject fMRI data analysis. The proposed framework learns the brain network representations via a supervised metric-based approach with siamese neural networks using two graph convolutional networks as the twin networks. Our proposed framework performs higher-order convolutions by incorporating higher-order proximity in graph convolutional networks to characterize and learn the community structure in brain connectivity networks. To the best of our knowledge, this is the first community-preserving similarity learning framework for multi-subject brain network analysis. Experimental results on four real fMRI datasets demonstrate the potential use cases of the proposed framework for multi-subject brain analysis in health and neuropsychiatric disorders. Our proposed approach achieves an average AUC gain of 75% compared to PCA, an average AUC gain of 65.5% compared to Spectral Embedding, and an average AUC gain of 24.3% compared to S-GCN across the four datasets, indicating promising application in clinical investigation and brain disease diagnosis.

cs.CV↗

arXiv2018

Temporo-Spatial Collaborative Filtering for Parameter Estimation in Noisy DCE-MRI Sequences: Application to Breast Cancer Chemotherapy Response

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a minimally invasive imaging technique which can be used for characterizing tumor biology and tumor response to radiotherapy. Pharmacokinetic (PK) estimation is widely used for DCE-MRI data analysis to extract quantitative parameters relating to microvascu- lature characteristics of the cancerous tissues. Unavoidable noise corruption during DCE-MRI data acquisition has a large effect on the accuracy of PK estimation. In this paper, we propose a general denoising paradigm called gather- noise attenuation and reduce (GNR) and a novel temporal-spatial collaborative filtering (TSCF) denoising technique for DCE-MRI data. TSCF takes advantage of temporal correlation in DCE-MRI, as well as anatomical spatial similar- ity to collaboratively filter noisy DCE-MRI data. The proposed TSCF denoising algorithm decreases the PK parameter normalized estimation error by 57% and improves the structural similarity of PK parameter estimation by 86% com- pared to baseline without denoising, while being an order of magnitude faster than state-of-the-art denoising methods. TSCF improves the univariate linear regression (ULR) c-statistic value for early prediction of pathologic response up to 18%, and shows complete separation of pathologic complete response (pCR) and non-pCR groups on a challenge dataset.

eess.IV↗