Safa Naraghi1, Tinashe Mutsvangwa1, René Goliath2, Molebogeng X Rangaka3, Tania S Douglas4. 1. Medical Imaging Research Unit, Division of Biomedical Engineering, University of Cape Town, Cape Town, South Africa. 2. Wellcome Centre for Infectious Diseases Research in Africa, Institute of Infectious Diseases and Molecular Medicine, University of Cape Town, Cape Town, South Africa. 3. Wellcome Centre for Infectious Diseases Research in Africa, Institute of Infectious Diseases and Molecular Medicine, University of Cape Town, Cape Town, South Africa; Institute for Global Health, University College London, London, United Kingdom. 4. Medical Imaging Research Unit, Division of Biomedical Engineering, University of Cape Town, Cape Town, South Africa. Electronic address: tania.douglas@uct.ac.za.
Abstract
BACKGROUND: The tuberculin skin test is the most widely used method for detecting latent tuberculosis infection in adults and active tuberculosis in children. We present the development of a mobile-phone based screening tool for measuring the tuberculin skin test induration. METHOD: The tool makes use of a mobile application developed on the Android platform to capture images of an induration, and photogrammetric reconstruction using Agisoft PhotoScan to reconstruct the induration in 3D, followed by 3D measurement of the induration with the aid of functions from the Python programming language. The system enables capture of images by the person being screened for latent tuberculosis infection. Measurement precision was tested using a 3D printed induration. Real-world use of the tool was simulated by application to a set of mock skin indurations, created by a make-up artist, and the performance of the tool was evaluated. The usability of the application was assessed with the aid of a questionnaire completed by participants. RESULTS: The tool was found to measure the 3D printed induration with greater precision than the current ruler and pen method, as indicated by the lower standard deviation produced (0.3 mm versus 1.1 mm in the literature). There was high correlation between manual and algorithm measurement of mock skin indurations. The height of the skin induration and the definition of its margins were found to influence the accuracy of 3D reconstruction and therefore the measurement error, under simulated real-world conditions. Based on assessment of the user experience in capturing images, a simplified user interface would benefit wide-spread implementation. CONCLUSIONS: The mobile application shows good agreement with direct measurement. It provides an alternative method for measuring tuberculin skin test indurations and may remove the need for an in-person follow-up visit after test administration, thus improving latent tuberculosis infection screening throughput.
BACKGROUND: The tuberculin skin test is the most widely used method for detecting latent tuberculosis infection in adults and active tuberculosis in children. We present the development of a mobile-phone based screening tool for measuring the tuberculin skin test induration. METHOD: The tool makes use of a mobile application developed on the Android platform to capture images of an induration, and photogrammetric reconstruction using Agisoft PhotoScan to reconstruct the induration in 3D, followed by 3D measurement of the induration with the aid of functions from the Python programming language. The system enables capture of images by the person being screened for latent tuberculosis infection. Measurement precision was tested using a 3D printed induration. Real-world use of the tool was simulated by application to a set of mock skin indurations, created by a make-up artist, and the performance of the tool was evaluated. The usability of the application was assessed with the aid of a questionnaire completed by participants. RESULTS: The tool was found to measure the 3D printed induration with greater precision than the current ruler and pen method, as indicated by the lower standard deviation produced (0.3 mm versus 1.1 mm in the literature). There was high correlation between manual and algorithm measurement of mock skin indurations. The height of the skin induration and the definition of its margins were found to influence the accuracy of 3D reconstruction and therefore the measurement error, under simulated real-world conditions. Based on assessment of the user experience in capturing images, a simplified user interface would benefit wide-spread implementation. CONCLUSIONS: The mobile application shows good agreement with direct measurement. It provides an alternative method for measuring tuberculin skin test indurations and may remove the need for an in-person follow-up visit after test administration, thus improving latent tuberculosis infection screening throughput.
Authors: Marco Pappalardo; Umberto Fanelli; Vincenzo Chiné; Cosimo Neglia; Andrea Gramegna; Alberto Argentiero; Susanna Esposito Journal: Children (Basel) Date: 2021-03-28
Authors: Filipe Ferreira; Ivan Miguel Pires; Vasco Ponciano; Mónica Costa; María Vanessa Villasana; Nuno M Garcia; Eftim Zdravevski; Petre Lameski; Ivan Chorbev; Martin Mihajlov; Vladimir Trajkovik Journal: Sensors (Basel) Date: 2021-08-26 Impact factor: 3.576