Lung Segmentation on HRCT and Volumetric CT for Diffuse Interstitial Lung Disease Using Deep Convolutional Neural Networks
A robust lung segmentation method using a deep convolutional neural network (CNN) was developed and evaluated on high-resolution computed tomography (HRCT) and volumetric CT of various types of diffuse interstitial lung disease (DILD). Chest CT images of 617 patients with various types of DILD, including cryptogenic organizing pneumonia (COP), usual interstitial pneumonia (UIP), and nonspecific interstitial pneumonia (NSIP), were scanned using HRCT (1–2-mm slices, 5–10-mm intervals) and volumetric CT (sub-millimeter thickness without intervals). Each scan was segmented using a conventional image processing method and then manually corrected by an expert thoracic radiologist to create gold standards. The lung regions in the HRCT images were then segmented using a two-dimensional U-Net architecture with the deep CNN, using separate training, validation, and test sets. In addition, 30 independent volumetric CT images of UIP patients were used to further evaluate the model. The segmentation results for both conventional and deep-learning methods were compared quantitatively with the gold standards using four accuracy metrics: the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). The mean and standard deviation values of those metrics for the HRCT images were 98.84 ± 0.55%, 97.79 ± 1.07%, 0.27 ± 0.18 mm, and 25.47 ± 13.63 mm, respectively. Our deep-learning method showed significantly better segmentation performance (p < 0.001), and its segmentation accuracies for volumetric CT were similar to those for HRCT. We have developed an accurate and robust U-Net-based DILD lung segmentation method that can be used for patients scanned with different clinical protocols, including HRCT and volumetric CT.
KeywordsChest CT Deep learning Diffuse interstitial lung disease Lung segmentation U-net
This work was supported by the Industrial Strategic technology development program (10072064) funded by the Ministry of Trade Industry and Energy (MI, Korea) and by Kakao and Kakao Brain corporations.
Compliance with Ethical Standards
Conflict of Interest
The authors declare that they have no conflicts of interest.
- 3.Jun S, Park B, Seo JB, Lee S, Kim N: Development of a Computer-Aided Differential Diagnosis System to Distinguish Between Usual Interstitial Pneumonia and Non-specific Interstitial Pneumonia Using Texture-and Shape-Based Hierarchical Classifiers on HRCT mages. Journal of Digital Imaging 31(2):235–244, 2018CrossRefGoogle Scholar
- 5.Kalinovsky A, Kovalev V. Lung image segmentation using deep learning methods and convolutional neural networks. International Conference on Pattern Recognition and Information Processing (PRIP-2016), Minsk, Belarus, 2016Google Scholar
- 6.Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, NIPS 2012, http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf. Accessed 5 May 2018
- 8.Deng J, Dong W, Socher R, Li L, Li, K, Fei-Fei L. ImageNet: A Large-Scale Hierarchical Image Database. Proc of IEEE Computer Vision and Pattern Recognition, 2009. 2009, http://www.image-net.org/papers/imagenet_cvpr09.pdf. Accessed 5 May 2018
- 9.Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. Citeseer, 2009Google Scholar
- 11.Raghu G, Collard HR, Egan JJ, Martinez FJ, Behr J, Brown KK, Colby TV, Cordier JF, Flaherty KR, Lasky JA, Lynch DA, Ryu JH, Swigris JJ, Wells AU, Ancochea J, Bouros D, Carvalho C, Costabel U, Ebina M, Hansell DM, Johkoh T, Kim DS, King te Jr, Kondoh Y, Myers J, Müller NL, Nicholson AG, Richeldi L, Selman M, Dudden RF, Griss BS, Protzko SL, Schünemann HJ, ATS/ERS/JRS/ALAT Committee on Idiopathic Pulmonary Fibrosis: An official ATS/ERS/JRS/ALAT statement: idiopathic pulmonary fibrosis: evidence-based guidelines for diagnosis and management. American Journal of Respiratory and Critical Care Medicine 183(6):788–824, 2011CrossRefGoogle Scholar
- 12.McCormick M, Johnson H, Ibanez L. The ITK Software Guide: The insight segmentation and registration toolkit, 2015, https://itk.org/. Accessed 5 May 2018
- 15.Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. arXiv preprint arXiv:1505.04597, 2015Google Scholar
- 16.Long J, Shelhamer E, Darrell T, editors. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence Archive 39(4)640–651, 2017Google Scholar
- 17.Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O, editors. 3D U-Net: learning dense volumetric segmentation from sparse annotation. International Conference on Medical Image Computing and Computer-Assisted Intervention: Springer, 2016Google Scholar
- 18.Milletari F, Navab N, Ahmadi S-A, editors. V-net: Fully convolutional neural networks for volumetric medical image segmentation. 3D Vision (3DV), 2016 Fourth International Conference on; IEEE, 2016Google Scholar
- 19.Kingma DP, Ba J: Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014.Google Scholar
- 20.Van Ginneken B, Heimann T, Styner M. 3D segmentation in the clinic: A grand challenge. 3D segmentation in the clinic: a grand challenge. 7–15, 2007, http://sliver07.org/p7.pdf. Accessed 5 May 2018
- 21.Jones E, Oliphant T, Peterson P. SciPy: Open source scientific tools for Python. 2001, http://www.scipy.org/. Accessed 5 May 2018