A5054939558- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Medical Image Segmentation Techniques
- Advanced Neuroimaging Techniques and Applications
- Atomic and Subatomic Physics Research
- COVID-19 diagnosis using AI
- Advanced NMR Techniques and Applications
- Advanced Neural Network Applications
- AI in Service Interactions
- Advanced Image and Video Retrieval Techniques
- Cognitive Functions and Memory
- Image and Video Stabilization
- Optical Imaging and Spectroscopy Techniques
- Face recognition and analysis
- Context-Aware Activity Recognition Systems
- Face and Expression Recognition
- Intelligent Tutoring Systems and Adaptive Learning
- Functional Brain Connectivity Studies
- Artificial Intelligence in Healthcare and Education
- Medical Imaging and Analysis
- Diet and metabolism studies
- Genetics and Neurodevelopmental Disorders
- Blood Pressure and Hypertension Studies
Columbia University
2019-2024
Resonance Research (United States)
2019-2024
SRM Institute of Science and Technology
2023
Dr. Hari Singh Gour University
2018
Yonsei University
2008
Severance Hospital
2008
Magnetic Resonance Imaging (MRI) is a critical component of healthcare.MRI data acquired by playing series radio-frequency and magnetic field gradient pulses.Designing these pulse sequences requires knowledge specific programming environments depending on the vendor hardware (generations) software (revisions) intended for implementation.This impedes pace prototyping.Pulseq (Layton et al., 2017) introduced an open source file standard that can be deployed Siemens/GE via TOPPE (Nielsen & Noll,...
This project introduces an innovative system for recognizing daily activities of intellectually disabled individuals using a multi-sensor approach. The proposed solution aims to enhance the quality life and independence people with intellectual disabilities by providing accurate real-time activity recognition. By leveraging wearable technology, continuously monitors analyzes various physiological movement data. comprehensive approach allows more nuanced understanding activities, potentially...
In today's age of automation, face recognition is a vital component for authorization and security. It has received substantial attention from researchers in various fields science such as biometrics computer vision. this paper, system using Principal Component Analysis (PCA) with Back Propagation Neural Networks (BPNN) analysed. A neural based algorithm presented to recognize the frontal views faces. The multi-variate data set image reduced PCA technique. BPNN used training learning,...
Magnetic Resonance Imaging (MR Imaging) is routinely employed in diagnosing Alzheimer's Disease (AD), which accounts for up to 60–80% of dementia cases. However, it time-consuming, and protocol optimization accelerate MR requires local expertise since each pulse sequence involves multiple configurable parameters that need contrast, acquisition time, signal-to-noise ratio (SNR). The lack this contributes the highly inefficient utilization MRI services diminishing their clinical value. In...
The usage of technology in education sector has taken a leap with the development Artificial Intelligence. aim this study is to review works done related chatbots pedagogical context period between 2017-2021. findings include (a) various contexts which are being used, (b) advantages and disadvantages using e-learning, (c) ways improve address (d) how personalization helps improvement students.
Abstract Aim Central obesity, hypertension and diabetes mellitus have been related individually to cognitive dysfunction. We aimed study the interactive effects of these co‐occurring risk factors on decline, which remain unclear in older patients with diabetes. Methods assessed metabolic profiles neuropsychological functions 60 out‐patients Type 2 examine associations central obesity functions, while controlling for other confounding subjects. Results Waist circumference was associated poor...
Children and the elderly are most susceptible to brain tumors. It's deadly cancer caused by uncontrollable cell proliferation inside skull. The heterogeneity of tumor cells makes classification extremely difficult. Image segmentation has been revolutionized because Convolution Neural Network (CNN), which is especially useful for medical images. Not only does U-Net succeed in segmenting a wide range pictures general, but also some particularly difficult instances. However, we uncovered severe...
Growing research has proven that mental illnesses, such as depression and chronic stress, can be better understood through the use of medical imaging. However, these findings fail utilization in real-world clinical settings. The intention this work is to demonstrate ability provide widespread access imaging computer-assisted technology across various community care providers, thus allowing meaningful outcomes population public health. We have created an end-to-end fully automated approach...
Quality assessment, including inspecting the images for artifacts, is a critical step during MRI data acquisition to ensure quality and downstream analysis or interpretation success. This study demonstrates deep learning model detect rigid motion in T1-weighted brain images. We leveraged 2D CNN three-class classification tested it on publicly available retrospective prospective datasets. Grad-CAM heatmaps enabled identification of failure modes provided an model's results. The achieved...
The routine brain screen protocol employed at our institution was accelerated using Look Up Tables to achieve a 1.94x gain in imaging throughput. Image-denoising performed on data by leveraging deep learning models trained contrast-specific publicly available datasets. These were corrupted native noise during forward modeling. In addition, subject-specific denoising demonstrated. superior performance of denoised automated volumetry Alzheimer’s Disease (AD) relevant anatomies T1w demonstrated...
These artifacts degrade image quality, often causing misdiagnosis. A 6-axis motion tracking sensor (ICM-20649, TDK-InvenSense) with a full-scale range of +-4000 degrees per second for the gyroscope and +-30g accelerometer was integrated 50mT scanner. The sensor’s readings can successfully be processed to detect motion. However, it resulted in zipper degraded quality phantom experiment. Still, placement on forehead or temples chin might not significantly impact brain data when coupled...
Quality assessment, including inspecting the images for artifacts, is a critical step during magnetic resonance imaging (MRI) data acquisition to ensure quality and downstream analysis or interpretation success. This study demonstrates deep learning (DL) model detect rigid motion in T
Raw data, simulated and acquired phantom images, quantitative longitudinal transverse relaxation times (T1/T2) maps from two open-source Magnetic Resonance Imaging (MRI) pulse sequences are presented in this dataset along with corresponding ".seq" files, sequence implementation scripts, reconstruction/analysis scripts [1]. Real MRI data were collected a 3T Siemens Prisma Fit 1.5T Aera via the Pulseq MR platform, silico generated using simulation module of Virtual Scanner [2]. This its...
Abstract Magnetic Resonance Imaging (MRI) is expensive and time-consuming. Protocol optimization to accelerate MRI requires local expertise since each MR sequence involves multiple configurable parameters that need for contrast, acquisition time, signal-to-noise ratio (SNR). The availability access technical training are limited in under-served regions, resulting a scarcity of required operate the hardware perform examinations. Along with other cultural temporal constraints, these factors...
MR artifacts degrade image quality and affect diagnosis, requiring thorough examination by the technician, reacquisition in some cases. We employ a combination of segmented acquisitions deep learning tool (ArtifactID) to perform more frequent updates during acquisition. ArtifactID identified wrap-around, Gibbs ringing motion artifacts, with mean accuracy 99.43%. The for rescans resulted 12.98% time gain over full-FOV sequence. In addition, alleviates burden on technician via automatic...