Sumit Datta

Sumit Datta
Indian Institute of Information Technology and Management - Kerala

PhD in Electronics and Communication Engineering
Assistant Professor, School of Electronic Systems and Automation, Digital University Kerala (Formerly IIITM-Kerala)

About

34
Publications
29,688
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
134
Citations
Citations since 2016
31 Research Items
134 Citations
2016201720182019202020212022010203040
2016201720182019202020212022010203040
2016201720182019202020212022010203040
2016201720182019202020212022010203040
Introduction
I am an Assistant Professor at Digital University Kerala (Formerly IIITM-Kerala). My research interests include biomedical signal/image processing, compressed sensing MRI, super-resolution, and medical image analysis using deep learning.
Additional affiliations
July 2021 - present
Digital University Kerala (Former IIITM-Kerala)
Position
  • Professor (Assistant)
November 2019 - July 2021
Indian Institute of Technology Guwahati
Position
  • PostDoc Position
January 2015 - November 2019
Tezpur University
Position
  • Researcher

Publications

Publications (34)
Chapter
In clinical practice, continuous recording and monitoring of the standard 12-lead electrocardiogram (ECG) is often not feasible. The emerging technology and advancement to record the ECG signal without the help of the medical expert’s in-home care or ambulatory conditions with minimal complexity have become more common in recent times. We aim to de...
Article
Multi-channel electrocardiogram (MECG) compression on lightweight wireless body area network (WBAN) is highly challenging for long-term eHealthcare monitoring. Energy consumption involved in wireless transmission poses an obstacle in the implementation of WBAN. MECG is widely used to diagnose cardiovascular diseases (CVDs), which require a consider...
Article
In compressed sensing (CS)-based magnetic resonance imaging (MRI), it is very challenging to maintain the diagnostic quality due to limited measurements. Diagnostically critical information, like fine anatomical details, edges, and boundaries are distorted due to the leakage of energy and artifacts during CS-reconstruction. In this paper, we have p...
Article
Full-text available
Wireless body area networks (WBANs) are increasingly used for remote healthcare surveillance in recent times, where electrocardiogram (ECG) signals are continuously acquired and transmitted to a base station or remote hospital for their storage and subsequent analysis. Multichannel ECG (MECG) is preferred over single-channel ECG as it provides more...
Article
Full-text available
Diffusion-weighted (DW) and spectroscopic MR (MRS) images are found to be very helpful for diagnostic purposes as they provide complementary information to that provided by conventional MRI. These images are also acquired at a faster rate, but with low signal-to-noise ratio. This limitation can be overcome by applying image super-resolution techniq...
Article
Diffusion-weighted magnetic resonance imaging (DW-MRI) and spectroscopic MRI (MRSI) are powerful diagnostic imaging tools as they provide complementary information over conventional MRI. Imaging is done at a low-resolution (LR) as the scanning time for high-resolution (HR) MR images would be very long and not practical besides being expensive for i...
Article
3D magnetic resonance imaging (3D MRI) or multi-slice MRI involves significant data acquisition time. Traditionally, scanning rate of conventional MRI is restricted due to inherent physiological and instrumental limitations. In multi-slice parallel MRI (multi-slice pMRI) adjacent slices are highly correlated, so one can interpolate missing k-space...
Chapter
Recently, continuous remote healthcare monitoring has been revolutionized by the application of affordable wearable personal health systems based on wireless body area networks (WBAN). These are battery-driven devices and more commonly used for electrocardiogram (ECG) signal storing, processing and transmission; essential for efficient and convenie...
Chapter
The application of compressed sensing (CS) in magnetic resonance imaging (MRI) demonstrates that it is possible to reconstruct MR images from a few undersampled k-space measurements and thereby reducing the clinical MRI scan time drastically. Generally, in clinical practice radiologists prefer to use sedation for paediatric patients, and those havi...
Chapter
Multichannel electrocardiogram (MECG) provides significant information for the detection of cardiovascular diseases. Compressed sensing (CS) is a simultaneous sensing and reconstruction technique from a few compressed measurements with low level of distortion. CS promises to lower energy consumption of sensing nodes for wireless body area network (...
Chapter
Diffusion-weighted and Spectroscopic MR images are found to be very helpful for diagnostic purposes as they provide complementary information to that provided by conventional MRI. These images are also acquired at a faster rate, but with low signal-to-noise ratio. This limitation can be overcome by applying image super-resolution techniques. In thi...
Chapter
Compressed sensing (CS) in parallel magnetic resonance imaging (pMRI) has the potential to reduce the MRI scan time by many folds. Due to the application of CS, conventional linear reconstruction techniques would not work. To reconstruct MR images from undersampled measurements one needs to solve highly nonlinear optimization problems. Practical im...
Chapter
Compressed sensing MRI (CS-MRI) seeks good quality MR image reconstruction from relatively less number of measurements than the traditional Nyquist sampling theorem. This in return increases the computational effort for reconstruction which may be dealt with some efficient solvers based on convex optimization. To reconstruct MR image from undersamp...
Chapter
Performances of various compressed sensing reconstruction algorithms are compared under a common simulation environment with different real and synthetic MRI datasets. From experimental results, it has been observed that composite splitting based algorithms outperform others in terms of reconstruction quality, CPU time, and visual results. Addition...
Chapter
MRI has a number of applications in bioinformatics and neuroinformatis, like, functional MRI (fMRI), diffusion weighted MRI (DW-MRI), and magnetic resonance spectroscopy (MRS). It gives valuable information about anatomical structure, the functioning of organs, neuronal activity, and abnormality inside the human body. Although MRI has a number of c...
Chapter
Extensive research work is being carried out in the area of fast convex optimization-based compressed sensing magnetic resonance (MR) image reconstruction algorithms. The main focus here is to achieve throughputs of clinical compressed sensing MR image reconstruction in terms of quality of reconstruction and computational time. In this chapter, we...
Chapter
Magnetic resonance imaging (MRI) is a widely used medical imaging tool where data acquisition is performed in the k-space, i.e., the Fourier transform domain. However, it has a fundamental limitation of being slow or having a long data acquisition time. Due to this, MRI is restricted in some clinical applications. Compressed sensing in MRI demonstr...
Chapter
A significant progress has been already accomplished in compressed sensing magnetic resonance image reconstruction research. A few recent works have successfully integrated CS-MRI into the existing MRI scanner for clinical studies and within a short span of time it would be also available at a commercial scale. This chapter mainly aims to throw lig...
Article
3D magnetic resonance imaging (3D MRI) is one of the most preferred medical imaging modalities for the analysis of anatomical structures where acquisition of multiple slices along the slice select gradient direction is very common. In 2D multislice acquisition, adjacent slices are highly correlated because of very narrow inter-slice gaps. Applicati...
Article
A priori knowledge of the signal/image support based on its statistical and structural information in the transformed domain improves the quality of compressed sensing (CS) reconstruction. Hidden Markov tree (HMT) models the wavelet domain support of magnetic resonance images obtained from undersampled k-space data very well. With the support infor...
Article
Application of the compressed sensing (CS) in magnetic resonance imaging (MRI) significantly reduces the scan time as it is capable of recovering images at diagnostic resolution from a few random measurements in the k-space. In 2D multi-slice MRI, a strong inter-slice correlation exists which promotes further reduction in the scan time. In this pap...
Article
Full-text available
In this paper, we propose a novel two-stage algorithm for the detection and removal of random-valued impulse noise using sparse representations. The main aim of the paper is to demonstrate the strength of image inpainting technique for the reconstruction of images corrupted by random-valued impulse noise at high noise densities. First, impulse loca...
Conference Paper
Compressed sensing magnetic resonance imaging (CSMRI) have demonstrated that it is possible to accelerate MRI scan time by reducing the number of measurements in the k-space without significant loss of anatomical details. The number of k-space measurements is roughly proportional to the sparsity of the MR signal under consideration. Recently, a few...
Chapter
Compressed sensing in magnetic resonance imaging (CS-MRI) improves the MRI scan time by acquiring only a few k-space samples and then reconstructs the image using a nonlinear procedure from the highly undersampled measurements. Besides the standard wavelet sparsity, MR images are also found to exhibit tree sparsity across various scales of the wave...
Conference Paper
In this paper, we propose a novel two-stage algorithm for random-valued impulse denoising based on sparse representations and image inpainting. The overall algorithm consists of a detection stage followed by a filtering stage. In particular, first impulse locations are detected by applying sparse denoising and grey relational analysis. In the secon...
Chapter
Typically, magnetic resonance (MR) images are stored in k-space where the higher energy samples, i.e., the samples with maximum information are concentrated near the center only; whereas, relatively lower energy samples are present near the outer periphery. Recently, variable density (VD) random under-sampling patterns have been increasingly popula...
Conference Paper
Magnetic resonance imaging (MRI) is an essential soft tissue imaging technique. Major limitation of this imaging technique is due to its slow acquisition. MR image reconstruction using the compressed sensing (CS) has mainly two research areas, one, how efficiently MRI data can be acquired and the other is how fast the reconstruction can be done wit...

Questions

Questions (4)
Question
The international conference on Pattern Recognition and Machine Intelligence (PReMI) is the flagship biennial technical conference of the Machine Intelligence Unit, Indian Statistical Institute (ISI) Kolkata started in 2005. The current edition: PReMI2019, is the 8th edition of this mega event, which will be organized for the first time in the Northeast India at Tezpur University (A Central University), Tezpur in joint collaboration with the Machine Intelligence Unit, Indian Statistical Institute (ISI), Kolkata, India and the Department of EEE, Indian Institute of Technology Guwahati (IIT Guwahati), India during December 17-20, 2019. Please visit: <http://www.tezu.ernet.in/~premi2019/> www.tezu.ernet.in/~premi2019 for more details. All PReMI conferences are officially endorsed by International Association for Pattern Recognition (IAPR), an international association of non-profit, scientific or professional organizations (being national, multi-national, or international in scope) concerned with pattern recognition, computer vision, and image processing in a broad sense. PReMI 2019 at Tezpur University, Tezpur, is expected to bring together researchers, educators, students, practitioners, technocrats and policymakers from across academia, government, industry and non-governmental organizations to discuss, share and promote current works and recent accomplishments across all aspects of its theme. In this edition, PReMI introduces a Doctoral Symposium for PhD students besides holding regular technical sessions in order to give a common platform for young scholars to exchange their ideas between other researchers and students and get feedback of their work. It also offers an excellent opportunity to network with other researchers with common interests. Ph.D. students who are in the final stage of their work are invited to submit proposals for Doctoral Symposium. Based on feedback from an expert committee during the Symposium, best graduate student and runner-up awards will be conferred. Please visit <http://www.tezu.ernet.in/~premi2019/submission.html> www.tezu.ernet.in/~premi2019/submission.html for more information. Prospective authors are invited to submit full paper (maximum 8 pages only) through EasyChair via the conference link: <http://www.easychair.org/conferences/?conf=premi2019> www.easychair.org/conferences/?conf=premi2019. All accepted papers, whose author(s) register, would be included in the conference proceedings to be published by Springer International Publishing in its LNCS series. Past editions of PReMI were indexed by Scopus and other indexing agencies. In addition, extended versions of selected papers will be considered for publication in SCI indexed journals. Topics Covered (but not limited to): * Pattern Recognition * Data Mining * Soft Computing * Complex Systems * Big Data Analytics * Medical Imaging * Compressive Sensing * Speech and Audio Processing * Parallel Computing * Biomedical Signal Processing * Computational Biology & Bioinformatics * Smart & Intelligent Sensors * Biosensors * Image & Video Processing * Computational Intelligence * Remote Sensing * Information Retrieval * Data Sciences * Deep Learning * Biometrics * Text Mining * Brain Modeling * Cyber Physical System * Internet of Things * Computer Vision * Machine Learning * Digital Watermarking * Social Media Mining * Natural Computing * Computational Neuroscience * Statistical Methods & Learning * Natural Language Processing * Web Intelligence * Cognitive Science * Steganography * Quantum Information Processing Important dates Papers submission Submission Deadline: April 16, 2019 Paper Notification date: June 18, 2019 Camera-Ready: June 31, 2019 Doctoral Symposium Proposal deadline: June 16, 2019 Notification of Acceptance: August 18, 2019 General Co-Chairs Dhruba K. Bhattacharyya, Tezpur University, Tezpur Sushmita Mitra, Indian Statistical Institute, Kolkata Prabin K. Bora, Indian Institute of Technology Guwahati Organizing Co-Chairs Partha Pratim Sahu, Tezpur University, Tezpur Kuntal Ghosh, Indian Statistical Institute, Kolkata Prithwijit Guha, Indian Institute of Technology Guwahati Program Co-Chairs Bhabesh Deka, Tezpur University, Tezpur Pradipta Maji, Indian Statistical Institute, Kolkata Contact: PReMI 2019 Secretariat Email: <mailto:premi2019@tezu.ernet.in> premi2019@tezu.ernet.in
Question
What is the difference between complex MR image and magnitude MR image and what is the advantage of complex MR image for compressed sensing reconstruction?? please help
Question
I have simulated a number of transversal brain MR images using ``BrainWeb: custom MRI simulations''. But I am unable to simulate sagittal and coronal brain MR images.
Question
contrast-to-noise ratio (CNR) for MR image

Network

Cited By

Projects

Project (1)