Performance of a fully‐automated system on a WHO malaria microscopy evaluation slide set

Malaria Journal

Jane Y. Carter¹  Samantha Janko²  Ken Lilley³  Thomas R. Burkot⁴  Earl G. Long⁵  Clay M. Thompson⁶  Kyaw Tun⁷  Benjamin K. Wilson⁸  Sourabh Kulhare⁸  Liming Hu⁸  Christine M. Bachman⁸  Travis Ostbye⁸  Courosh Mehanian⁸  Martha Mehanian⁸  Matthew P. Horning⁸  Charles B. Delahunt⁹  Peter L. Chiodini^1,10  David Bell^1,11  Ranitha Vongpromek^1,12  Bernhards Ogutu^1,13  Dionicia Gamboa^1,14  Christian Luna^1,15  Jennifer Luchavez^1,15  Stephane Proux^1,16  Wellington Oyibo^1,17  Mehul Dhorda^1,18  Mayoore S. Jaiswal^1,19  Grace Yun^1,19  Roman Gebrehiwot^1,19 

[1] Amref Health Africa, Nairobi, Kenya;Arizona State University, Tempe, AZ, USA;Australian Defence Force Malaria and Infectious Disease Institute, Enoggera, Australia;Australian Institute of Tropical Health and Medicine, James Cook University, Cairns, Australia;Centers for Disease Control and Prevention, Atlanta, GA, USA;Creative Creek LLC, Camano Island, WA, USA;Defence Services Medical Academy, Mingaladon, Myanmar;Global Health Labs (formerly at Intellectual Ventures Laboratory/Global Good), 14360 SE Eastgate Way, 98007, Bellevue, WA, USA;Global Health Labs (formerly at Intellectual Ventures Laboratory/Global Good), 14360 SE Eastgate Way, 98007, Bellevue, WA, USA;Applied Math Department, University of Washington, 98195, Seattle, WA, USA;Hospital for Tropical Diseases and the London School of Hygiene and Tropical Medicine, London, UK;Independent Consultant, Issaquah, WA, USA;Infectious Diseases Data Observatory and World Wide Antimalarial Resistance Network, Asia- Pacific Regional Centre, Bangkok, Thailand;Kenya Medical Research Institute, Nairobi, Kenya;Laboratorios de Investigacion y Desarrollo, Facultad de Ciencias y Filosofia, Universidad Peruana Cayetano Heredia, Lima, Peru;Research Institute for Tropical Medicine, Muntinlupa, Philippines;Shoklo Malaria Research Unit, Mahidol Oxford Tropical Medicine Research Unit, Faculty of Tropical Medicine, Mahidol University, Mae Sot, Thailand;University of Lagos, Lagos, Nigeria;World Wide Antimalarial Resistance Network and Mahidol-Oxford Tropical Medicine Research Unit, Bangkok, Thailand;formerly Intellectual Ventures Laboratory, 3150 139th AVE SE, 98005, Bellevue, WA, USA;

关键词: Malaria;    Automated diagnosis;    Machine learning;    Microscopy;    WHO;   

DOI  :  10.1186/s12936-021-03631-3

来源: Springer

【 摘 要 】

BackgroundManual microscopy remains a widely-used tool for malaria diagnosis and clinical studies, but it has inconsistent quality in the field due to variability in training and field practices. Automated diagnostic systems based on machine learning hold promise to improve quality and reproducibility of field microscopy. The World Health Organization (WHO) has designed a 55-slide set (WHO 55) for their External Competence Assessment of Malaria Microscopists (ECAMM) programme, which can also serve as a valuable benchmark for automated systems. The performance of a fully-automated malaria diagnostic system, EasyScan GO, on a WHO 55 slide set was evaluated.MethodsThe WHO 55 slide set is designed to evaluate microscopist competence in three areas of malaria diagnosis using Giemsa-stained blood films, focused on crucial field needs: malaria parasite detection, malaria parasite species identification (ID), and malaria parasite quantitation. The EasyScan GO is a fully-automated system that combines scanning of Giemsa-stained blood films with assessment algorithms to deliver malaria diagnoses. This system was tested on a WHO 55 slide set.ResultsThe EasyScan GO achieved 94.3 % detection accuracy, 82.9 % species ID accuracy, and 50 % quantitation accuracy, corresponding to WHO microscopy competence Levels 1, 2, and 1, respectively. This is, to our knowledge, the best performance of a fully-automated system on a WHO 55 set.ConclusionsEasyScan GO’s expert ratings in detection and quantitation on the WHO 55 slide set point towards its potential value in drug efficacy use-cases, as well as in some case management situations with less stringent species ID needs. Improved runtime may enable use in general case management settings.

【 授权许可】

CC BY