Classification of chest diseases using deep learning

Silva J.; Zilberman J.; Patiño Y.P.; Varela N.; Lezama O.B.P. · Advances in Intelligent Systems and Computing (2021) · DOI: 10.1007/978-3-030-53036-5_16

Resumen

The field of computer vision has had exponential progress in a wide range of applications due to the use of deep learning and especially the existence of large annotated image data sets [1]. Significant improvements have been shown in the performance of problems previously considered difficult, such as object recognition, detection and segmentation over approaches based on obtaining the characteristics of the image by hand [2]. This article presents a novel method for the classification of chest diseases in the standard and widely used data set ChestX-ray8, which contains more than 100,000 front view images with 8 diseases. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Instituciones: Universidad Peruana de Ciencias Aplicadas