A5081346151- Medical Image Segmentation Techniques
- Acute Ischemic Stroke Management
- 3D Shape Modeling and Analysis
- Medical Imaging and Analysis
- Retinal Imaging and Analysis
- Stroke Rehabilitation and Recovery
- Advanced Neural Network Applications
- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Digital Imaging for Blood Diseases
- AI in cancer detection
- Brain Tumor Detection and Classification
- Long-Term Effects of COVID-19
- Retinal Diseases and Treatments
- Venous Thromboembolism Diagnosis and Management
- Intracerebral and Subarachnoid Hemorrhage Research
- Traumatic Brain Injury and Neurovascular Disturbances
- Glaucoma and retinal disorders
- Medical Imaging Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Artificial Intelligence in Healthcare and Education
- Colorectal Cancer Screening and Detection
- Advanced Vision and Imaging
- Cardiac Arrest and Resuscitation
- Radiation Dose and Imaging
Wayne State University
2013-2025
Detroit Medical Center
2013-2025
Marwadi University
2023-2024
Arcadia
2024
Tamil Nadu Agricultural University
2024
Marwadi Education Foundation
2023
Philips (Finland)
2022
Hospital de Egas Moniz
2022
University of Thessaly
2022
Boston University
2022
Notwithstanding the significant advancements in field of deep learning, basic long short-term memory (LSTM) or Gated Recurrent Unit (GRU) units have largely remained unchanged and unexplored. There are several possibilities advancing state-of-art by rightly adapting enhancing various elements these units. Activation functions one such key element. In this work, we explore using diverse activation within GRU bi-directional (BiGRU) cells context speech emotion recognition (SER). We also...
Brain is the master and commanding organ of human body. Human brain affected by many dangerous diseases. tumor or neoplasm abnormal growth tissues in surrounding regions. MRI one method used for diagnosis. Many algorithms are proposed automatic extraction from MR images. Fuzzy c-Means (FCM) clustering watershed algorithm two commonly methods extraction. In this paper we implemented improved version fuzzy algorithm. an effective initial centroid selection based on histogram calculation atlas...
Human brain is the most complex and mysterious part of human body. Many functions are controlled by brain. Brain imaging a widely applicable method for diagnosing many abnormalities such as tumor, stroke, paralysis etc. Magnetic Resonance Imaging (MRI) one methods used imaging. It analysing internal structures in detail. tumor an abnormal mass tissue which cells grow multiply uncontrollably, seemingly unchecked mechanisms that control normal cells. The aim this paper to extract region from...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> Constructing a 3-D surface model from sparse-point data is nontrivial task. Here, we report an accurate and robust approach for reconstructing of the proximal femur dense-point distribution (DPDM). The problem formulated as three-stage optimal estimation process. first stage, <emphasis emphasistype="boldital">affine registration</emphasis>, to iteratively estimate scale rigid transformation...
We propose a novel method for reconstructing complete 3D model of given anatomy from minimal information. This reconstruction provides an appropriate intra-operative visualization without the need pre or imaging. Our #ts statistical deformable to sparse data consisting digitized landmarks and bone surface points. The also allows incorporation nonspatial such as patient height weight. is constructed using principal component analysis (PCA) set training objects. morphing then computes...
Diabetic retinopathy is the most general diabetes complication that affects eyes and results in blindness. It's due to impairment of arteries a veins located fundus eye (retina) are composed light sensitive tissues. The aim this research work design an efficient tool for Retinopathy using images acquired from portable camera. screening based on advanced machine learning computer vision algorithm which includes patch level prediction. In prediction will localize diseased region image like...
This paper addresses the problem of extrapolating extremely sparse three-dimensional set digitized landmarks and bone surface points to obtain a complete representation. The extrapolation is done using statistical principal component analysis (PCA) shape model similar earlier approaches by Fleute et al. procedure called Bone-Morphing highly useful for intra-operative visualization structures in image-free surgeries. We developed novel morphing scheme operating directly PCA space...
The use of three dimensional models in planning and navigating computer assisted surgeries is now well established. These provide intuitive visualization to the surgeons contributing significantly better surgical outcomes. Models obtained from specifically acquired CT scans have disadvantage that they induce high radiation dose patient. In this paper we propose a novel stable method construct patient-specific model provides an appropriate intra-operative 3D without need for pre or imaging....
Human brain is a complex system, made up of neurons and glial cells.Nothing in the universe can compare with functioning human brain.Due to its nature, diseases affected on also very nature.Brain imaging widely used method for diagnosing such deceases.Brain tumor an abnormal mass tissue which cells grow multiply uncontrollably, seemingly unchecked by mechanisms that control normal cells.Magnetic Resonance Imaging (MRI) commonly modality detecting diseases.In this work we proposed novel...
In this paper we present an automated blood vessel segmentation system algorithm for the retinal images under pathological conditions like Diabetic Retinopathy (DR) using matched filters and supervised classification techniques. Matched filter has been extensively used in enhancement of vessels due to cross sectional similarity Gaussian profile. However addition edges non also gives a strong response leading false detection. Based on structural spatial differences between segmented...