Designing Chest X-ray Datasets for Improving Lung Nodules Detection through Convolutional Neural Networks
Ver/ Abrir
Impacto
Scholar |
Otros documentos de la autoría: Aceñero Eixarch, Raúl Pedro; Díaz-Usechi Laplaza, Raúl; Berlanga Llavori, Rafael
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7038
comunitat-uji-handle3:10234/159830
comunitat-uji-handle4:
INVESTIGACIONMetadatos
Título
Designing Chest X-ray Datasets for Improving Lung Nodules Detection through Convolutional Neural NetworksFecha de publicación
2021Editor
IOS PressISBN
9781643682105Cita bibliográfica
Aceñero Eixarch, Raúl ;Díaz-Usechi Laplaza, Raúl ; Berlanga Llavori, Rafael. Designing Chest X-ray Datasets for Improving Lung Nodules Detection. ARTIFICIAL INTELLIGENCE RESEARCH AND DEVELOPMENT, 2021, 345.Tipo de documento
info:eu-repo/semantics/conferenceObjectVersión
info:eu-repo/semantics/publishedVersionPalabras clave / Materias
Resumen
In this paper, we propose a method for building alternative training
datasets for lung nodule detection from plain chest X-ray images. Our aim is to improve the classification quality of a state-of-the-art CNN by ... [+]
In this paper, we propose a method for building alternative training
datasets for lung nodule detection from plain chest X-ray images. Our aim is to improve the classification quality of a state-of-the-art CNN by just selecting appropriate samples from the existing datasets. The hypothesis of this research is that high
quality models need to learn by contrasting very clean images with those containing nodules, specially those difficult to identify by non-expert clinicians. Current
chest X-ray datasets mostly include images where more than one pathology exist
and/or contain devices like catheters. This is because most samples come from old
people which are the usual patients subject to X-ray examinations. In this paper, we
evaluate several combinations of samples from existing datasets in the literature.
Results show a great gain in performance for some of the evaluated combinations,
confirming our hypothesis. The achieved performance of these models allows a
considerable speed-up in the screening of patients by radiologist. [-]
Descripción
23rd International Conference of the Catalan Association for Artificial Intelligence, CCIA 2021Virtual.held in Lleida, in October 2021
Publicado en
Libro de actas de ponencias :Artificial Intelligence Research and Development. Proceedings of the 23rd edition of the CCIA, held in Lleida, in October 2021Derechos de acceso
info:eu-repo/semantics/openAccess