Deep Convolutional Neural Networks for Endotracheal Tube Position and X-ray Image Classification: Challenges and Opportunities
Paras Lakhani, Paras Lakhani
Abstract
The goal of this study is to evaluate the efficacy of deep convolutional neural networks (DCNNs) in differentiating subtle, intermediate, and more obvious image differences in radiography. Three different datasets were created, which included presence/absence of the endotracheal (ET) tube (n = 300), low/normal position of the ET tube (n = 300), and chest/abdominal radiographs (n = 120). The datasets were split into training, validation, and test. Both untrained and pre-trained deep neural networks were employed, including AlexNet and GoogLeNet classifiers, using the Caffe framework. Data augmentation was performed for the presence/absence and low/normal ET tube datasets. Receiver operating characteristic (ROC), area under the curves (AUC), and 95% confidence intervals were calculated. Statistical differences of the AUCs were determined using a non-parametric approach. The pre-trained AlexNet and GoogLeNet classifiers had perfect accuracy (AUC 1.00) in differentiating chest vs. abdominal radiographs, using only 45 training cases. For more difficult datasets, including the presence/absence and low/normal position endotracheal tubes, more training cases, pre-trained networks, and data-augmentation approaches were helpful to increase accuracy. The best-performing network for classifying presence vs. absence of an ET tube was still very accurate with an AUC of 0.99. However, for the most difficult dataset, such as low vs. normal position of the endotracheal tube, DCNNs did not perform as well, but achieved a reasonable AUC of 0.81.
Keywords: Artificial intelligence; Artificial neural networks (ANNs); Classification; Machine learning; Radiography.
Figures
References
- Goodman LR, Conrardy PA, Laing F, Singer MM: Radiographic evaluation of endotracheal tube position. Am J Roentgenol 127(3):433–4,1976
- Brunel W, Coleman DL, Schwartz DE, Peper E, Cohen NH: Assessment of routine chest roentgenograms and the physical examination to confirm endotracheal tube position. Chest 96(5):1043–5,1989
- Zwillich CW, Pierson DJ, Creagh CE, Sutton FD, Schatz E, Petty TL: Complications of assisted ventilation: a prospective study of 354 consecutive episodes. Am J Med 57(2):161–70,1974
- Ramakrishna B, Brown M, Goldin J, Cagnon C, Enzmann D: An improved automatic computer aided tube detection and labeling system on chest radiographs. Proc. SPIE 8315, Medical Imaging 2012: Computer-Aided Diagnosis, 83150R (February 23, 2012); doi:10.1117/12.911839
- Kao EF, Jaw TS, Li CW, Chou MC, Liu GC: Automated detection of endotracheal tubes in paediatric chest radiographs. Comput Methods Prog Biomed 118(1):1–10,2015
- Chen S, Zhang M, Yao L, Xu W: Endotracheal tubes positioning detection in adult portable chest radiography for intensive care unit. Int J Comput Assist Radiol Surg 11(11):2049–57,2016
- Krizhevsky A, Sutskever I, Hinton GE: Imagenet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst 1097–1105, 2012
- Szegedy C, Liu W, Jia Y, et al.: Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: 1–9, 2015
- Russakovsky O, Deng J, Su H, et al.: Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252,2015
- Bar Y, Diamant I, Wolf L, Greenspan H: Deep learning with non-medical training used for chest pathology identification. Proc.SPIE Medical Imaging, International Society for Optics and Photonics: 9414, 2015
- Rajkomar A, Lingam S, Taylor AG, Blum M, Mongan J. High-throughput classification of radiographs using deep convolutional neural networks. J Digit Imaging. 2016;11:1–7.
- Zhang W, Li R, Deng H, Wang L, Lin W, Ji S, Shen D. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage. 2015;108:214–224. doi: 10.1016/j.neuroimage.2014.12.061.
- Shin HC, Roth HR, Gao M, et al.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35(5):1285–1298,2016
- Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, Venugopalan S, Widner K, Madams T, Cuadros J, Kim R: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22):2402–10,2016
- Cho J, Lee K, Shin E, Choy G, Do S: How much data is needed to train a medical image deep learning system to achieve necessary high accuracy? arXiv preprint arXiv:1511.06348, 2015
- Jia Y, Shelhamer E, Donahue J, et al.: Caffe: convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia 2014. ACM, 2014
- Hastie T, Tishirani R, Friedman J. Model assessment and selection. In: The Elements of Statistical Learning, 2nd ed. Berlin: Springer; 2009. pp. 219–257.
- Steyerberg EW, Vickers AJ, Cook NR et al.: Assessing the performance of prediction models: a framework for some traditional and novel measures. Epidemiology 21(1):128–138,2010
- Bradley AP: The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30(7):1145–1159,1997
- Fawcett T.: ROC graphs: notes and practical considerations for researchers. Mach Learn 31(1):1–38,2004
- Delrue L, Gosselin R, Ilsen B, Van Landeghem A, de Mey J, Duyck P. Difficulties in the interpretation of chest radiography. In Comparative Interpretation of CT and Standard Radiography of the Chest. Berlin Heidelberg: Springer; 2011. pp. 27–49.
- Yosinski J, Clune J, Bengio Y, Lipson H: How transferable are features in deep neural networks? In Advances in neural information processing systems, 2014, pp. 3320–3328
- Simonyan K, Vedaldi A, Zisserman A: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034, 2013
Source: PubMed