Publications by authors named "S O Adewole"
Introduction: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address.
View Article and Find Full Text PDFBackground: Globally, peripartum or puerperal infections account for about one tenth of maternal mortality, most of which occur in low income countries. Therefore, vaginal preparation with an antiseptic prior to a caesarean delivery could be considered an additional measure to prevent subsequent infectious morbidities.
Objectives: To evaluate vaginal preparation with 0.
Deep Learning Methods for Anatomical Landmark Detection in Video Capsule Endoscopy Images.
Proc Future Technol Conf (2020)
November 2021
Article Synopsis
- Video capsule endoscopy (VCE) is a minimally invasive method that allows doctors to thoroughly examine the entire gastrointestinal tract by capturing real-time images as the capsule travels through it.
- While VCE provides detailed images for diagnosis, analyzing up to eight hours of footage can be labor-intensive and costly, suggesting a need for automation.
- The study compared four deep learning models for identifying the anatomical regions in VCE images, finding that VGG-Net outperformed others like GoogLeNet, AlexNet, and ResNet in accuracy and other performance metrics.
Background: Women in low- and middle-income countries (LMIC) remain at high risk of developing cervical cancer and have limited access to screening programs. The limits include geographical barriers related to road network characteristics and travel behaviors but these have neither been well studied in LMIC nor have methods to overcome them been incorporated into cervical cancer screening delivery programs.
Methods: To identify and evaluate spatial barriers to cervical cancer prevention services in Ondo State, Nigeria, we applied a Multi-Mode Enhanced Two-Step Floating Catchment Area model to create a spatial access index for cervical cancer screening services in Ondo City and the surrounding region.