Lung HRCT pattern classification for cystic fibrosis using convolutional neural network
- 20 Downloads
Cystic fibrosis (CF) is one of the most prevalent autosomal recessive disorders among whites. It mostly affects lungs which causes infection and inflammation leading to 90% of deaths among CF patients. Due to wide variability in its clinical presentation and organ involvement, studying responses to therapy and evaluation of pulmonary changes over time is crucial in progress prevention of CF. Serial high-resolution computed tomography (HRCT) scans significantly facilitate the assessment of the pulmonary abnormalities evolution in CF patients. Recently, artificial intelligence is being employed for analyzing thoracic CT scans acquired from CF patients. In this paper, we propose a convolutional neural network (CNN) approach for classifying CF lung patterns in HRCT images. The proposed network consists of two convolutional layers with 3 × 3 kernels and max-pooling in each layer followed by two dense layers of 1024 and 10 neurons, respectively. The softmax layer prepares a probabilistic distribution of predicted output among classes. This layer has three outputs, equivalent to the classes corresponding to normal (healthy), bronchiectasis, and inflammation. To train and evaluate the network, we built up a patch-based dataset extracted from more than 1100 lung HRCT slices which were acquired from 45 CF patients. A comparative evaluation proved the effectiveness of the proposed CNN with respect to its close counterparts. The classification accuracy, mean sensitivity, and specificity of 93.64%, 93.47%, and 96.61% were achieved which demonstrated the potential of CNNs in analyzing lung CF patterns and following up the lungs’ status. In addition, the visual features extracted by our proposed method might be helpful for automatic measurement and eventually scoring the severity of CF patterns in lung HRCT images.
KeywordsCystic fibrosis High-resolution computed tomography Lung pattern classification Convolutional neural network Image augmentation
This research was partially supported by Iranian National Science Foundation (Grant No. 95-45194).
Compliance with ethical standards
The ethical permission for retrospective use of HRCT lung images was provided by the local ethics committee of Tehran University of Medical Sciences, Tehran, Iran (Approval Number: TR.TUMS.MEDICINE.REC.1396.4599).
- 2.Amin, R.: Inhaled Hypertonic Saline (7%) Improves the Lung Clearance Index in CF Paediatric Patients with FEV1% Predicted ≥ 80%. Master Thesis, Department of Health Policy, University of Toronto, Toronto (2009)Google Scholar
- 3.State of Lung Disease in Diverse Communities, New York: Association, American Lung (2010)Google Scholar
- 5.Servidoni, M., Sousa, M., Vinagre, A., Cardoso, S., Ribeiro, M., Meirelles, L., Carvalho, R., Kunzelmann, K., Ribeiro, A., Ribeiro, J., Amaral, M.: Rectal forceps biopsy procedure in cystic fibrosis: technical aspects and patients perspective for clinical trials feasibility. BMC Gastroenterol. 13(1), 91 (2013)CrossRefGoogle Scholar
- 6.Sequeiros, I., Jarad, N.: Radiological features of cystic fibrosis. In: Cystic Fibrosis—Renewed Hopes Through Research, InTech, pp. 31–50 (2012)Google Scholar
- 7.Ciompi, F., Palaioroutas, A., Loeve, M., Pujol, O., Radeva, P., Tiddens, H., Bruijne, M.: Lung tissue classification in severe advanced cystic fibrosis from CT scans. In: Fourth International Workshop on Pulmonary Image Analysis, Toronto, CanadaGoogle Scholar
- 9.Schapire, R.: The boosting approach to machine learning: an overview. In: Nonlinear Estimation and Classification. Lecture Notes in Statistics, vol. 71, pp. 149–171 (2003)Google Scholar
- 11.Marques, F., Dubost, F., Kemner-van de Corput, M., Tiddens, H.A.W., de Bruijne, M.: Quantification of lung abnormalities in cystic fibrosis using deep networks. In: Medical Imaging 2018: Image Processing; 105741G (2018)Google Scholar
- 13.Li, Q., Cai, W., Wang, X., Zhou, Y., Feng, D., Chen, M.: Medical image classification with convolutional neural network. In: 13th International Conference on Control Automation Robotics and Vision (ICARCV), Singapore (2014)Google Scholar
- 17.Jiang, H., Ma, H., Qian, W., Gao, M., Li, Y.: An automatic detection system of lung nodule based on multi-group patch-based deep learning network. IEEE J. Biomed. Health Inform. 99 (2017)Google Scholar
- 18.Gao, M., Bagci, U., Lu, L., Wu, A., Buty, M., Shin, H.C., Roth, H., Papadakis, G.Z., Depeursinge, A., Summers, R., Xu, Z., Mollura, D.J.: Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks. In: 1st Workshop on Deep Learning in Medical Image Analysis (2015)Google Scholar
- 19.Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (NIPS) (2012)Google Scholar
- 20.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR), Boston, Massachusetts (2015)Google Scholar
- 21.van Tulder, G., de Bruijne, M.: Learning features for tissue classification with the classification restricted boltzmann machine. In: Medical Computer Vision: Algorithms for Big Data, Cambridge, Springer, pp. 47–58 (2014)Google Scholar
- 23.Garnavi, R., Baraani-Dastjerdi, A., Moghaddam, H.A., Giti, M., Rad, A.: A new segmentation method for lung HRCT images. In: Digital Image Computing: Techniques and Applications, 2005. DICTA ‘05. Proceedings 2005, Queensland, Australia (2005)Google Scholar
- 24.Kingma, D.P., Jimmy, B.: Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations, San Diego (2015)Google Scholar
- 25.Tieleman, T., Hinton, G.: Divide the gradient by a running average of its recent magnitude. Lecture 6.5-RMSProp (2012)Google Scholar
- 28.Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision (2014)Google Scholar