A retrospective study of deep learning generalization across two centers and multiple models of X-ray devices using COVID-19 chest-X rays

• Published in: Scientific reports 2024-06, Vol.14 (1), p.14657-12, Article 14657
• Main Authors: Fernández-Miranda, Pablo Menéndez, Fraguela, Enrique Marqués, de Linera-Alperi, Marta Álvarez, Cobo, Miriam, del Barrio, Amaia Pérez, González, David Rodríguez, Vega, José A., Iglesias, Lara Lloret
• Format: Article
• Language: English
• Subjects: 639/705/117; 692/700/1421/1770; Algorithms; Chest; COVID-19; Deep Learning; Humanities and Social Sciences; Humans; Image processing; Image Processing, Computer-Assisted - methods; multidisciplinary; Neural networks; Neural Networks, Computer; Radiography, Thoracic; Retrospective Studies; SARS-CoV-2; Science; Science (multidisciplinary); X-rays
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-64941-5

Generalization of deep learning (DL) algorithms is critical for the secure implementation of computer-aided diagnosis systems in clinical practice. However, broad generalization remains to be a challenge in machine learning. This research aims to identify and study potential factors that can affect the internal validation and generalization of DL networks, namely the institution where the images come from, the image processing applied by the X-ray device, and the type of response function of the X-ray device. For these purposes, a pre-trained convolutional neural network (CNN) (VGG16) was trained three times for classifying COVID-19 and control chest radiographs with the same hyperparameters, but using different combinations of data acquired in two institutions by three different X-ray device manufacturers. Regarding internal validation, the addition of images from an external institution to the training set did not modify the algorithm’s internal performance, however, the inclusion of images acquired by a device from a different manufacturer decreased the performance up to 8% ( p