A robust convolutional neural network for lung nodule detection in the presence of foreign bodies
Open Access
- 31 July 2020
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 10 (1) , 1-9
Abstract
Lung cancer is a major cause of death worldwide. As early detection can improve outcome, regular screening is of great interest, especially for certain risk groups. Besides low-dose computed tomography, chest X-ray is a potential option for screening. Convolutional network (CNN) based computer aided diagnosis systems have proven their ability of identifying nodules in radiographies and thus may assist radiologists in clinical practice. Based on segmented pulmonary nodules, we trained a CNN based one-stage detector (RetinaNet) with 257 annotated radiographs and 154 additional radiographs from a public dataset. We compared the performance of the convolutional network with the performance of two radiologists by conducting a reader study with 75 cases. Furthermore, the potential use for screening on patient level and the impact of foreign bodies with respect to false-positive detections was investigated. For nodule location detection, the architecture achieved a performance of 43 true-positives, 26 false-positives and 22 false-negatives. In comparison, performance of the two readers was 42 ± 2 true-positives, 28 ± 0 false-positives and 23 ± 2 false-negatives. For the screening task, we retrieved a ROC AUC value of 0.87 for the reader study test set. We found the trained RetinaNet architecture to be only slightly prone to foreign bodies in terms of misclassifications: out of 59 additional radiographs containing foreign bodies, false-positives in two radiographs were falsely detected due to foreign bodies.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (Research Training Group GRK 2274)
This publication has 32 references indexed in Scilit:
- Computer-aided detection of pulmonary nodules: a comparative study using the public LIDC/IDRI databaseEuropean Radiology, 2015
- Computer-Aided Nodule Detection SystemAcademic Radiology, 2015
- Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic ScreeningNew England Journal of Medicine, 2011
- Epidemiology of Lung Cancer Prognosis: Quantity and Quality of Life2009
- Effective Doses in Radiology and Diagnostic Nuclear Medicine: A CatalogRadiology, 2008
- Variations in orthodontic treatment planning decisions of Class II patients between virtual 3-dimensional models and traditional plaster study modelsAmerican Journal of Orthodontics and Dentofacial Orthopedics, 2006
- Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public databaseMedical Image Analysis, 2006
- Lighting and Sustained PerformanceJournal of the Illuminating Engineering Society, 2000
- Development of a Digital Image Database for Chest Radiographs With and Without a Lung NoduleAmerican Journal of Roentgenology, 2000
- Bootstrap Methods: Another Look at the JackknifeThe Annals of Statistics, 1979