A5050050882- Retinal Imaging and Analysis
- Retinal Diseases and Treatments
- Smart Agriculture and AI
- Digital Imaging for Blood Diseases
- Leaf Properties and Growth Measurement
- Glaucoma and retinal disorders
- Remote Sensing in Agriculture
- Cell Image Analysis Techniques
- Retinal and Optic Conditions
- Spectroscopy and Chemometric Analyses
- Advanced machining processes and optimization
- Intraocular Surgery and Lenses
- Advanced Surface Polishing Techniques
- Computer Graphics and Visualization Techniques
- Urological Disorders and Treatments
- Advanced Measurement and Metrology Techniques
- Pelvic floor disorders treatments
- AI in cancer detection
- Plant Pathogens and Fungal Diseases
- Plant Disease Management Techniques
- Cancer Cells and Metastasis
- Medical Image Segmentation Techniques
- Artificial Intelligence in Healthcare
- Radiomics and Machine Learning in Medical Imaging
- Ureteral procedures and complications
Birla Institute of Technology and Science, Pilani
2016-2023
Sankara Nethralaya
2021-2022
St. Elizabeth Healthcare
2021
St. Elizabeth Hospital in Enumclaw
2021
Institut Teknologi dan Sains Mandala
2019
Derriford Hospital
2018
Women & Infants Hospital of Rhode Island
2015
Brown University
2015
The Ohio State University
1991-2012
Royal Devon and Exeter Hospital
2006-2008
With the increasing incidence rate of lung cancer patients, early diagnosis could help in reducing mortality rate. However, accurate recognition cancerous lesions is immensely challenging owing to factors such as low contrast variation, heterogeneity and visual similarity between benign malignant nodules. Deep learning techniques have been very effective performing natural image segmentation with robustness previously unseen situations, reasonable scale invariance ability detect even minute...
Tomatoes are one of the major horticulture crops in world. Early Blight is most widespread tomato diseases India, often causing a significant reduction produce. Agricultural produce tomatoes utmost importance, making it necessary for timely recognition Blight. Using self-collected images, we first explore classification diseased leaves using ResNet and Xception networks, achieving accuracy 99.952%. However, focus has already been dedicated to disease crops. Additionally, lack spatial...
Abstract The Marching Cubes Algorithm may return degenerate, zero area isosurface triangles, and often returns triangles with small areas, edges or angles. We show how to avoid both problems using an extended lookup table. As opposed the conventional table, table differentiates scalar values equal isovalue from greater than isovalue. has 3 8 = 6561 entries, based on three possible labels, ‘−’ ‘=’ ‘+’, of each cube vertex. present algorithm this which close isosurface, but without any degenerate
Infectious keratitis, especially viral keratitis (VK), in resource-limited settings, can be a challenge to diagnose and carries high risk of misdiagnosis contributing significant ocular morbidity.employ study the application artificial intelligence-based deep learning (DL) algorithms VK.A single-center retrospective was conducted tertiary care center from January 2017 December 2019 employing DL algorithm VK slit-lamp (SL) photographs. Three hundred seven diffusely illuminated SL photographs...
This paper discusses the importance of investigating DR using machine learning and a computational method to rank risk factors by different models. The dataset was collected from four large population-based studies conducted in India between 2001 2010 on prevalence its factors. We deployed models variables (risk factors). study uses t-test Shapely additive explanations (SHAP) Then, it five (K-Nearest Neighbor, Decision Tree, Support Vector Machines, Logistic Regression, Naive Bayes) identify...
Unilateral, dilated unresponsive pupil may be secondary to a wide range of ocular and neurological disorders. "Gardener’s pupil" is pharmacological mydriasis caused by exposure plants containing alkaloids. We report case related <i>Datura inoxia</i>, detail number that have toxic effects. This emphasises the importance accurate history taking when evaluating fixed pupil. recommend labelling such poisonous should local systemic effects accidental exposure, rather than merely fact they are poisonous.
This paper describes different approaches for detection and identification of diseases in apples using computer vision. Our proposed algorithms analyze surface appearance apple defects image features, viz. color texture. For segmentation Region Of Interest (ROI), K-means clustering is performed over the pixels based on their intensity values. creation feature vector, combinations Gabor Wavelets with descriptors were explored. Comparative study has been carried out between Haralick Local...
We present a new deformable model technique following snake-like approach and using complex Fourier shape descriptors parameterization to efficiently formulate the forces that constrain contour deformation. The method was successfully applied track left ventricle's (LV) endocardial epicardial boundaries in sequences of shortaxis magnetic resonance images depicting complete cardiac cycles. extracted shapes show method's robustness weak contrast, noisy edge maps papillary muscle anatomy. Our...
<h3>Backgound/aims:</h3> The aim of this study was to compare the efficacy and safety 4% articaine with a mixture containing equal volumes 2% lidocaine 0.5% levobupivacaine without hyaluronidase for sub-Tenon's anaesthesia in phacoemulsification cataract surgery. <h3>Methods:</h3> prospective, randomised double-masked clinical trial 65 patients allocated receive either or parts levobupivacaine. All had pre- postoperative Hess charting document ocular motility dysfunction. Ocular eyelid...
Myopic Choroidal neovascularization (mCNV) is one of the most common vision-threatening com- plications pathological myopia among many retinal diseases. Optical Coherence Tomography Angiography (OCTA) an emerging newer non-invasive imaging technique and recently being included in investigation treatment mCNV. However, there exists no standard tool for time-efficient dependable analysis OCTA images In this study, we propose a customizable ImageJ macro that automates image processing lets...
An algorithm for computationally focusing the tissue boundaries detected from magnetic resonance images is presented. The proposed approach a novel, whole-contour-based technique tracing edges selected at coarse scale into successively finer scales to recover needed precision. builds consensus through fast pixel voting scheme. Also presented rigorous method determining appropriate itinerary when traversing space, beginning premise of maximum migration per unit change in parameter. This leads...
Abstract The rise of non‐invasive, rapid, and widely accessible quantitative high‐resolution imaging methods, such as modern retinal photography optical coherence tomography (OCT), has significantly impacted ophthalmology. These techniques offer remarkable accuracy resolution in assessing ocular diseases are increasingly recognized for their potential identifying biomarkers systemic diseases. application artificial intelligence (AI) been demonstrated to have promising results age, gender,...
To compare the effectiveness of Optos P200dTx and Zeiss Clarus 500 fundus cameras in detecting diabetic retinopathy (DR) lesions.A cross-sectional study was conducted among 243 patients with clinically diagnosed diabetes mellitus who were referred for an eye examination from two tertiary care centers Chennai, India. Patients underwent DR screening based on mydriatic fundal images acquired by both cameras. Fundal separate devices each compared accurately identified pathological retinal...
A multi-layer volume rendering framework is presented. The final image obtained by compositing a number of renderings, each being represented as separate layer. This layer-centric provides rich set 2D operators and interactions, allowing both greater freedom more intuitive 2D-based user interaction. We extend the concept which traditionally thought pertaining to Porter Duff general flexible functions. In addition developing new functional operators, can control individual layer's attributes,...