A5027824010- Image and Signal Denoising Methods
- Retinal Imaging and Analysis
- Medical Image Segmentation Techniques
- Advanced Image Processing Techniques
- Image Processing Techniques and Applications
- AI in cancer detection
- Advanced Neural Network Applications
- Cell Image Analysis Techniques
- Advanced Image Fusion Techniques
- Radiomics and Machine Learning in Medical Imaging
- Optical Coherence Tomography Applications
- Cardiovascular Health and Disease Prevention
- Glaucoma and retinal disorders
- Digital Imaging for Blood Diseases
- Cerebrovascular and Carotid Artery Diseases
- Brain Tumor Detection and Classification
- Sparse and Compressive Sensing Techniques
- Retinal Diseases and Treatments
- COVID-19 diagnosis using AI
- Acute Ischemic Stroke Management
- Advanced MRI Techniques and Applications
- Anomaly Detection Techniques and Applications
- Photoacoustic and Ultrasonic Imaging
- Video Surveillance and Tracking Methods
- Epilepsy research and treatment
National Institute of Technology Karnataka
2015-2024
Indira Gandhi Centre for Atomic Research
2023
Sardar Vallabhbhai National Institute of Technology Surat
2013-2016
iMinds
2013-2014
University of Antwerp
2009-2014
Abstract Purpose: To study, from a machine learning perspective, the performance of several classifiers that use texture analysis features extracted soft‐tissue tumors in nonenhanced T1‐MRI images to discriminate between malignant and benign tumors. Materials Methods: Texture were tumor regions clinically proven cases 49 86 Three conventional trained tested. The best classifier was compared radiologists by means McNemar's statistical test. Results: SVM performs better than neural network...
Optical coherence tomography (OCT) is an imaging modality that used extensively for ophthalmic diagnosis, near-histological visualization, and quantification of retinal abnormalities such as cysts, exudates, layer disorganization, etc. Intra-retinal cysts (IRCs) occur in several macular disorders as, diabetic edema, vascular disorders, age-related degeneration, inflammatory disorders. Automated segmentation IRCs poses challenges owing to variations the acquisition system scan intensities,...
During the last decade, many approaches have been proposed for improving estimation of diffusion measures. These techniques already shown an increase in accuracy based on theoretical considerations, such as incorporating prior knowledge data distribution. The increased metric estimators is typically observed well‐defined simulations, where assumptions regarding properties distribution are known to be valid. In practice, however, correcting subject motion and geometric eddy current...
In this note, we address the estimation of noise level in magnitude magnetic resonance (MR) images absence background data. Most methods proposed earlier exploit Rayleigh distributed region MR to estimate level. These methods, however, cannot be used for where no information is available. propose two different approaches image background. The first method based on local variance using maximum likelihood and second skewness data distribution. Experimental results synthetic real datasets show...
In this work, we have focused on the segmentation of Focal Cortical Dysplasia (FCD) regions from MRI images. FCD is a congenital malformation brain development that considered as most common causative intractable epilepsy in adults and children. To our knowledge, latest work concerning automatic was proposed using fully convolutional neural network (FCN) model based UNet. While there no doubt outperformed conventional image processing techniques by considerable margin, it suffers several...
Retinal Fluids (fluid collections) develop because of the accumulation fluid in retina, which may be caused by several retinal disorders, and can lead to loss vision. Optical coherence tomography (OCT) provides non-invasive cross-sectional images retina enables visualization different abnormalities. The identification segmentation cysts from OCT scans is gaining immense attention since manual analysis data time consuming requires an experienced ophthalmologist. Identification categorization...
In this paper, we propose a method to denoise magnitude magnetic resonance (MR) images, which are Rician distributed. Conventionally, maximum likelihood methods incorporate the Rice distribution estimate true, underlying signal from local neighborhood within is assumed be constant. However, if assumption not met, such filtering will lead blurred edges and loss of fine structures. As solution problem, put forward concept restricted neighborhoods where true intensity for each noisy pixel...
Separation of the vascular tree into arteries and veins is a fundamental prerequisite in automatic diagnosis retinal biomarkers associated with systemic neurodegenerative diseases. In this paper, we present novel graph search metaheuristic approach for separation arteries/veins (A/V) from color fundus images. Our method exploits local information to disentangle complex multiple subtrees, global label these vessel subtrees veins. Given binary map, representation network constructed...
Molecular subtyping is an important procedure for prognosis and targeted therapy of breast carcinoma, the most common type malignancy affecting women. Immunohistochemistry (IHC) analysis widely accepted method molecular subtyping. It involves assessment four biomarkers namely estrogen receptor (ER), progesterone (PR), human epidermal growth factor 2 (HER2), antigen Ki67 using appropriate antibody reagents. Conventionally, these are assessed manually by a pathologist, who finally combines...