A5079995648- AI in cancer detection
- Sepsis Diagnosis and Treatment
- Neonatal and Maternal Infections
- Digital Imaging for Blood Diseases
- Artificial Intelligence in Healthcare and Education
- ICT in Developing Communities
- Neonatal and fetal brain pathology
- Artificial Intelligence in Healthcare
- Cervical Cancer and HPV Research
- Medical Imaging Techniques and Applications
- Cell Image Analysis Techniques
- Machine Learning in Healthcare
- Image Retrieval and Classification Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray Imaging Techniques
- Shoulder Injury and Treatment
- Ethics in Clinical Research
- Digital Radiography and Breast Imaging
- FinTech, Crowdfunding, Digital Finance
- Healthcare Systems and Reforms
- 3D Shape Modeling and Analysis
- AI in Service Interactions
- Human Mobility and Location-Based Analysis
- Innovative Approaches in Technology and Social Development
- Explainable Artificial Intelligence (XAI)
Mbarara University of Science and Technology
2016-2024
University of California System
2024
Software (Spain)
2024
World Health Organization Regional Office for Africa
2022-2023
Harvard Affiliated Emergency Medicine Residency
2021
University of Cape Town
2016
Hong Kong University of Science and Technology
2002
With the rapid growth of interest in and use large language models (LLMs) across various industries, we are facing some crucial profound ethical concerns, especially medical field. The unique technical architecture purported emergent abilities LLMs differentiate them substantially from other artificial intelligence (AI) natural processing techniques used, necessitating a nuanced understanding LLM ethics. In this Viewpoint, highlight concerns stemming perspectives users, developers,...
Cervical cancer is preventable if effective screening measures are in place. Pap-smear the commonest technique used for early and diagnosis of cervical cancer. However, manual analysis pap-smears error prone due to human mistake, moreover, process tedious time-consuming. Hence, it beneficial develop a computer-assisted tool make pap-smear test more accurate reliable. This paper describes development automated classification from images. Scene segmentation was achieved through Trainable Weka...
Large language models (LLMs) have shown significant promise related to their application in medical research, education, and clinical tasks. While acknowledging capabilities, we face the challenge of striking a balance between defining holding ethical boundaries driving innovation LLM technology for medicine. We herein propose framework, grounded four bioethical principles, promote responsible use LLMs. This model requires LLMs by three parties — patient, clinician, systems that govern...
Globally, cervical cancer ranks as the fourth most prevalent affecting women. However, it can be successfully treated if detected at an early stage. The Pap smear is a good tool for initial screening of cancer, but there possibility error due to human mistake. Moreover, process tedious and time-consuming. objective this study was mitigate risk mistake by automating classification from images. In research, contrast local adaptive histogram equalization used image enhancement. Cell...
Abstract Background Deep learning has proved to very vital in numerous applications recent years. However, the development of a model may require access datasets. Training models on datasets impose challenges terms computational constraints, making it inefficient for limited environments and this study local dataset from Kigezi Uganda will be used. The also explore strategies optimizing MobilenetV2 through transfer hyper-tuning. Main Objective: This explored MobileNetV2 performance...
Without careful dissection of the ways in which biases can be encoded into artificial intelligence (AI) health technologies, there is a risk perpetuating existing inequalities at scale. One major source bias data that underpins such technologies. The STANDING Together recommendations aim to encourage transparency regarding limitations datasets and proactive evaluation their effect across population groups. Draft recommendation items were informed by systematic review stakeholder survey....
Globally, cervical cancer ranks as the fourth most prevalent affecting women. However, can be treated if detected at an early stage. Pap-smear is a good tool for screening of but manual analysis error-prone, tedious and time-consuming. The objective this study was to rule out these limitations by automating process classification from pap-smear images using enhanced fuzzy c-means algorithm. Simulated annealing coupled with wrapper filter used feature selection. evaluation results showed that...
The COVID-19 pandemic led to a global surge of health care innovations aimed at curbing the pandemic. Some were newly developed whereas others modifications existing technologies suit response. With world achieving some level normalcy, question is what will become these innovations. This study reviewed and analysed 1003 that utilised for response assess if they are still being strengthen systems. paper goes on identify, profile showcase 48 trace their evolution support Primary Health Care....
Cervical cancer ranks as the fourth most prevalent affecting women worldwide and its early detection provides opportunity to help save life. Automated diagnosis of cervical from pap-smear images enables accurate, reliable timely analysis condition's progress. Cell segmentation is a fundamental aspect successful automated analysis. In this paper, potent approach for cells image into nucleus, cytoplasm background using pixel level information proposed. A number pixels nuclei, are extracted 100...
We report on an interactive tool for patientspecific 3D approximation of scapula bone shape from 2D X-ray images using landmark-constrained statistical model (SSM) fitting. The localization points the was done through stereophotogrammetry. inferior angle, acromion and coracoid process were identified as reliable landmarks anteroposterior (AP) oblique lateral views in a landmark selection study. surface approximated fitting SSM to reconstructed coordinates selected landmarks. point yielded...
Background Digital storytelling (DST) is a participatory, arts-based methodology that facilitates the creation of short films called digital stories. Both DST process and resulting stories can be used for education, research, advocacy, therapeutic purposes in public health. widely Europe North America, becoming increasingly common Africa. In East Africa, there currently limited in-country facilitation capacity, which restricts scope use. Through Ugandan-Canadian partnership, six Ugandan...
Online platforms promote community change, from challenge to commercialization.
Mortality rates in sub-Saharan Africa remains unacceptably high, and disproportionately affecting economically disadvantaged communities. And healthcare delivery which is considered a major contributor to this challenged by the limited resources high service costs, prompting many patients opt for outpatient department services. This study addresses need data-driven approach policy formulation proposing model implementation of data warehousing system that integrates outpatients into national...