Shelda Sajeev

ORCID: 0000-0002-7428-4435
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • AI in cancer detection
  • Image Retrieval and Classification Techniques
  • Artificial Intelligence in Healthcare
  • Gene expression and cancer classification
  • Machine Learning in Healthcare
  • Advanced Image Fusion Techniques
  • Brain Tumor Detection and Classification
  • Cardiac Health and Mental Health
  • Conferences and Exhibitions Management
  • Image Processing Techniques and Applications
  • Music and Audio Processing
  • Medical Image Segmentation Techniques
  • Phonocardiography and Auscultation Techniques
  • Geriatric Care and Nursing Homes
  • Diabetes, Cardiovascular Risks, and Lipoproteins
  • Image Enhancement Techniques
  • Ocular Diseases and Behçet’s Syndrome
  • Evolutionary Algorithms and Applications
  • Hospitality and Tourism Education
  • Ocular Infections and Treatments
  • Medication Adherence and Compliance
  • Nutrition and Health in Aging
  • Advanced Image and Video Retrieval Techniques
  • Technology and Data Analysis
  • Cardiovascular Health and Risk Factors

Vellore Institute of Technology University
2025

Flinders University
2015-2023

Torrens University Australia
2020-2023

Flinders Medical Centre
2018

New WHO research indicates that there are an increasing number of chest-related illnesses. This results in the deaths 17.9 million people annually. It gets harder to identify problems and start therapy at early age as population grows. However, new developments technology, such deep learning machine methods, have sped up medical profession. The creation a model for heart disease prediction based on pertinent features is goal this study. chest's X-ray images kept cloud public access suggested...

10.47857/irjms.2025.v06i01.01943 article EN International Research Journal of Multidisciplinary Scope 2025-01-01

Abstract Background There is increasing evidence that pre-frailty manifests as early middle age. Understanding the factors contributing to an trajectory from good health in aged and older adults needed inform timely preventive primary care interventions mitigate decline future frailty. Methods A cohort of 656 independent community dwelling adults, 40–75 years, living South Australia, undertook a comprehensive assessment part Inspiring Health cross-sectional observational study. Secondary...

10.1186/s12877-022-03475-9 article EN cc-by BMC Geriatrics 2022-10-12

Many researchers have analysed various aspects of the Medical Tourism (MT) phenomenon. However, most them considered only a specific country for their study. This study explores both beneficial and adverse effects medical tourism systematically. It also studies critical success factors (CSF) MT using multi-case dominant countries. A qualitative approach has been used in this survey to generate theoretical category. For that, “Grounded Theory” research method selected by which collected data...

10.34105/j.kmel.2023.15.003 article EN cc-by Knowledge Management & E-Learning An International Journal 2023-03-15

Effective cardiovascular disease (CVD) prevention relies on timely identification and intervention for individuals at risk. Conventional formula-based techniques have been demonstrated to over- or under-predict the risk of CVD in Australian population. This study assessed ability machine learning models predict mortality population compare performance with well-established Framingham model. Data is drawn from three cohort studies: North West Adelaide Health Study (NWAHS), Diabetes, Obesity,...

10.3390/ijerph18063187 article EN International Journal of Environmental Research and Public Health 2021-03-19

Mass segmentation in mammograms is a challenging task if the mass located local dense background. It can be due to similarity of intensities between overlapped normal breast tissue and mass. In this paper, self- adjusted mammogram contrast enhancement solution called Adaptive Clip Limit CLAHE (ACL-CLAHE) developed, aiming improve regions mammograms. An optimization algorithm based on entropy used optimize clip limit window size standard CLAHE. The proposed method tested 89 images with 41...

10.1109/dicta.2015.7371305 article EN 2015-11-01

Finding masses in dense background is a difficult task for even experienced radiologist. It due to the similarity of intensity between and overlapped normal tissues. A novel method classification localised breast proposed. Nine structured superpixel patterns were generated using local binary pattern technique on superpixels. Analysis these nine revealed most prominent ones, allowing successful malignant regions. Two mammographic databases used evaluate proposed approach: publicly available...

10.1049/iet-cvi.2017.0586 article EN IET Computer Vision 2018-03-22

Background: The prevention of cardiovascular disease is a public health priority as it associated with increasing morbidity and mortality worldwide.

10.1145/3290688.3290725 article EN Proceedings of the Australasian Computer Science Week Multiconference 2019-01-14

Early diagnosis of infective keratitis is critical as it a vision-threatening condition that can lead to significant vision loss and ocular morbidity. Diagnosis done through clinical findings slit- lamp examination intricate requires high expertise. Most cases are challenging the clinicians. This paper proposes deep learning approach enabling more accurate diagnoses treatment keratitis. As first step towards developing comprehensive learning-based disease detection tool, we have classified...

10.1145/3437378.3437388 article EN 2021-02-01

Cancerous masses detection in dense background is a particularly challenging task for even experienced radiologists due to their similarity of intensity with the overlapped normal tissues, obscured boundaries and low contrast between mass surrounding regions. This paper proposes novel approach identification cancerous regions located part breast. Careful analysis nine structured micro-patterns generated using LBP technique revealed most prominent ones, allowing successful classification The...

10.1109/dicta.2017.8227493 article EN 2017-11-01

Finding mamographic masses located in a dense breast tissue is challenge even for an experienced radiologist. The difficulty comes from the similarity of intensity between and overlapped normal tissues. In this study, novel method classification localized background proposed. can identify meaningful superpixel patterns present mammograms within mass-like regions. topology patterns, captured by using spatial connectivity graphs, revealed significant differences cancerous healthy areas...

10.1117/12.2317589 article EN 2018-07-06

10.5281/zenodo.234022 article EN cc-by Zenodo (CERN European Organization for Nuclear Research) 2016-01-08

The paper proposes a novel approach for the identification of cancerous regions located in dense part breast. This task is particularly challenging even experienced radiologists due to lack clear boundaries between and normal tissue. Multi-scale analysis structured micro-patterns generated from local binary patterns (LBP) was used generate very small number features which allowed successful detection regions. proposed technique tested on two publicly available datasets: Digital Database...

10.1117/12.2564272 article EN 2020-05-22

It is crucial to improve access quality healthcare for the economically underprivileged community in order ensure that imperative illnesses may be treated quickly. In situations where medical personnel are severely lacking, a simple categorization of respiratory tones using computerized instrument can performed provide rapid diagnosis respiratory-related disorders such as Respiratory function. this paper, it presents Specification, an upgraded bi-ResNet deep learning architecture employs...

10.1109/icwite57052.2022.10176205 article EN 2022-12-01
Coming Soon ...