Street images classification according to COVID-19 risk in Lima, Peru: a convolutional neural networks feasibility analysis

Carrillo Larco, Rodrigo M, Castillo Cara, Manuel y Hernández Santa Cruz , Jose Francisco . (2022) Street images classification according to COVID-19 risk in Lima, Peru: a convolutional neural networks feasibility analysis. BMJ Open

Ficheros (Some files may be inaccessible until you login with your e-spacio credentials)
Nombre Descripción Tipo MIME Size
Castillo-Cara_JM_Street.pdf Castillo-Cara_JM_Street.pdf application/pdf 373.29KB

Título Street images classification according to COVID-19 risk in Lima, Peru: a convolutional neural networks feasibility analysis
Autor(es) Carrillo Larco, Rodrigo M
Castillo Cara, Manuel
Hernández Santa Cruz , Jose Francisco
Materia(s) Informática
Abstract Objectives During the COVID-19 pandemic, convolutional neural networks (CNNs) have been used in clinical medicine (eg, X-rays classification). Whether CNNs could inform the epidemiology of COVID-19 classifying street images according to COVID-19 risk is unknown, yet it could pinpoint high-risk places and relevant features of the built environment. In a feasibility study, we trained CNNs to classify the area surrounding bus stops (Lima, Peru) into moderate or extreme COVID-19 risk. Design CNN analysis based on images from bus stops and the surrounding area. We used transfer learning and updated the output layer of five CNNs: NASNetLarge, InceptionResNetV2, Xception, ResNet152V2 and ResNet101V2. We chose the best performing CNN, which was further tuned. We used GradCam to understand the classification process. Setting Bus stops from Lima, Peru. We used five images per bus stop. Primary and secondary outcome measures Bus stop images were classified according to COVID-19 risk into two labels: moderate or extreme. Results NASNetLarge outperformed the other CNNs except in the recall metric for the moderate label and in the precision metric for the extreme label; the ResNet152V2 performed better in these two metrics (85% vs 76% and 63% vs 60%, respectively). The NASNetLarge was further tuned. The best recall (75%) and F1 score (65%) for the extreme label were reached with data augmentation techniques. Areas close to buildings or with people were often classified as extreme risk. Conclusions This feasibility study showed that CNNs have the potential to classify street images according to levels of COVID-19 risk. In addition to applications in clinical medicine, CNNs and street images could advance the epidemiology of COVID-19 at the population level.
Editor(es) BMJ Publishing Group
Fecha 2022-09-19
Formato application/pdf
Identificador bibliuned:557-Jmcastillo-0011
http://e-spacio.uned.es/fez/view/bibliuned:557-Jmcastillo-0011
DOI - identifier https://bmjopen.bmj.com/content/12/9/e063411
ISSN - identifier 2044-6055
Nombre de la revista BMJ Open
Número de Volumen 12
Número de Issue 9
Publicado en la Revista BMJ Open
Idioma eng
Versión de la publicación publishedVersion
Tipo de recurso Article
Derechos de acceso y licencia http://creativecommons.org/licenses/by-nc-nd/4.0
info:eu-repo/semantics/openAccess
Tipo de acceso Acceso abierto
Notas adicionales La versión registrada de este artículo, publicado por primera vez en BMJ Open (2022) 12, está disponible en línea en el sitio web del editor: BMJ Publishing Group https://bmjopen.bmj.com/content/12/9/e063411
Notas adicionales The registered version of this article, first published in BMJ Open (2022) 12, is available online at the publisher's website: BMJ Publishing Group https://bmjopen.bmj.com/content/12/9/e063411

 
Versiones
Versión Tipo de filtro
Contador de citas: Google Scholar Search Google Scholar
Estadísticas de acceso: 28 Visitas, 6 Descargas  -  Estadísticas en detalle
Creado: Wed, 28 Feb 2024, 22:23:47 CET