Sanjeev SOFAT, Rahul HOODA, Ajay MITTAL

Lung segmentation in chest radiographs using fully convolutional networks

Automated segmentation of medical images that aims at extracting anatomical boundaries is a fundamentalstep in any computer-aided diagnosis (CAD) system. Chest radiographic CAD systems, which are used to detectpulmonary diseases, first segment the lung field to precisely define the region-of-interest from which radiographic patternsare sought. In this paper, a deep learning-based method for segmenting lung fields from chest radiographs has beenproposed. Several modifications in the fully convolutional network, which is used for segmenting natural images to date,have been attempted and evaluated to finally evolve a network fine-tuned for segmenting lung fields. The testing accuracyand overlap of the evolved network are 98.75% and 96.10%, respectively, which exceeds the state-of-the-art results.

PDF

___

[1] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE 1998; 86: 2278-2324.
[2] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems; 2012; Lake Tahoe, NV, USA. pp. 1097-1105.
[3] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint, arXiv:1409.1556, 2014.
[4] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015. pp. 1-9.
[5] Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. In: European Conference on Computer Vision; 6 September 2014. pp. 818-833.
[6] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015. pp. 3431-3440.
[7] Badrinarayanan V, Kendall A, Cipolla R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE T Pattern Anal 2017; 39: 2481-2495.
[8] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention; 5 October 2015. pp. 234-241.
[9] Li L, Zheng Y, Kallergi M, Clark RA. Improved method for automatic identification of lung regions on chest radiographs. Acad Radiol 2001; 8: 629-38.
[10] Duryea J, Boone JM. A fully automated algorithm for the segmentation of lung fields on digital chest radiographic images. Med Phys 1995; 22: 183-91.
[11] Ahmad WS, Zaki WM, Fauzi MF. Lung segmentation on standard and mobile chest radiographs using oriented Gaussian derivatives filter. Biomed Eng Online 2015; 14: 1-26.
[12] McNitt-Gray MF, Sayre JW, Huang HK, Razavi M. Pattern classification approach to segmentation of chest radiographs. In: Proceedings of SPIE Medical Imaging, International Society for Optics and Photonics; 1993. pp. 160-171.
[13] Tsujii O, Freedman MT, Mun SK. Automated segmentation of anatomic regions in chest radiographs using an adaptive sized hybrid neural network. Med Phys 1998; 25: 998-1007.
[14] Van Ginneken B, Stegmann MB, Loog M. Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med Image Anal 2006; 10: 19-40.
[15] Shi Z, Zhou P, He L, Nakamura T, Yao Q, Itoh H. Lung segmentation in chest radiographs by means of Gaussian kernel-based FCM with spatial constraints. In: Sixth International Conference on Fuzzy Systems and Knowledge Discovery; 14 August 2009. pp. 428-432.
[16] Kalinovsky A, Kovalev, V. Lung image segmentation using deep learning methods and convolutional neural networks. In: 13th International Conference on Pattern Recognition and Information Processing; 2016; Minsk, Belarus.
[17] Arbabshirani MR, Dallal AH, Agarwal C, Patel A, Moore G. Accurate segmentation of lung fields on chest radiographs using deep convolutional networks. In: Proceedings of SPIE Medical Imaging, International Society for Optics and Photonics; 24 February 2017. p. 10133051-6.
[18] Novikov AA, Lenis D, Major D, Hladůvka J, Wimmer M, Bühler K. Fully convolutional architectures for multi-class segmentation in chest radiographs. IEEE T Med Imaging (in press).
[19] Van Ginneken B, Frangi AF, Staal JJ, ter Haar Romeny BM, Viergever MA. Active shape model segmentation with optimal features. IEEE T Med Imaging 2002; 21: 924-33.
[20] Shi Y, Qi F, Xue Z, Chen L, Ito K, Matsuo H, Shen D. Segmenting lung fields in serial chest radiographs using both population-based and patient-specific shape statistics. IEEE T Med Imaging 2008; 27: 481-94.
[21] Annangi P, Thiruvenkadam S, Raja A, Xu H, Sun X, Mao L. A region based active contour method for x-ray lung segmentation using prior shape and low level features. In: International Symposium on Biomedical Imaging: From Nano to Macro; 14 April 2010. pp. 892-895.
[22] Candemir S, Jaeger S, Palaniappan K, Musco JP, Singh RK, Xue Z, Karargyris A, Antani S, Thoma G, McDonald CJ. Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE T Med Imaging 2014; 33: 577-590.
[23] Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M. Striving for simplicity: the all convolutional net. arXiv preprint, arXiv:1412.6806, 2014.
[24] Shiraishi J, Katsuragawa S, Ikezoe J, Matsumoto T, Kobayashi T, Komatsu KI, Matsui M, Fujita H, Kodera Y, Doi K. Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am J Roentgenol 2000; 174: 71-74.
[25] Jaeger S, Candemir S, Antani S, Wáng YX, Lu PX, Thoma G. Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quant Imag Med Surg 2014; 4: 475-477.