Abstract
Purpose
Fast helical free-breathing CT (FHFBCT) scans are widely used for 5DCT and 5D Cone Beam imaging protocols. For quantitative analysis of lung physiology and function, it is important to segment the lung lobes in these scans. Since the 5DCT protocols use up to 25 FHFBCT scans, it is important that this segmentation task be automated. In this paper, we present a deep neural network (DNN) framework for segmenting the lung lobes in near real time.
Methods
A total of 22 patient datasets (550 3D CT scans) were used for the study. Each of the lung lobes was manually segmented and considered ground-truth. A supervised and constrained generative adversarial network (CGAN) was employed for learning each set of lobe segmentations for each patient with 12 patients designated for training data. The resulting generator DNNs represented the lobe segmentations for each training dataset. A quorum-based algorithm was then implemented to test validation data consisting of 10 separate patient datasets (250 3D CTs). Each of the DNNs predicted their corresponding lobes for the validation data, and equal weights were given to the 12 generator CGANs. The quorum process worked by selecting the weighted average result of all 12 CGAN results for each lobe.
Results
When evaluated against ground-truth segmentations, the quorum-based lobe segmentation was observed to have average structural similarity index, normalized cross-correlation coefficient, and dice coefficient values of 0.929, 0.806, and 0.814, respectively, compared to values of 0.911, 0.698, and 0.696, respectively, using a conventional strategy.
Conclusion
The proposed quorum-based approach computed segmentations with clinically acceptable accuracy in near real time using a multi-GPU-based computing setup. This method is scalable as more patient-specific CGANs can be added to the quorum over time.
Similar content being viewed by others
References
O’Connell DP, Thomas DH, Dou TH, Lamb JM, Feingold F, Low DA, Fuld MK, Sieren JP, Sloan CM, Shirk MA, Hoffman EA, Hofmann C (2015) Comparison of breathing gated CT images generated using a 5DCT technique and a commercial clinical protocol in a porcine model. Med Phys 42(7):4033–4042. https://doi.org/10.1118/1.4922201
O’Connell D, Shaverdian N, Kishan AU, Thomas DH, Dou TH, Lewis JH, Lamb JM, Cao M, Tenn S, Percy LP, Low DA (2018) Comparison of lung tumor motion measured using a model-based 4DCT technique and a commercial protocol. Pract Radiat Oncol 8(3):e175–e183. https://doi.org/10.1016/j.prro.2017.11.003
Howington JA, Blum MG, Chang AC, Balekian AA, Murthy SC (2013) Treatment of stage I and II non-small cell lung cancer: diagnosis and management of lung cancer, 3rd edn. American college of chest physicians evidence-based clinical practice
Taylor MD, LaPar DJ, Isbell JM, Kozower BD, Lau CL, Jones DR (2014) Marginal pulmonary function should not preclude lobectomy in selected patients with non-small cell lung cancer. J Thorac Cardiovasc Surg 147(2):738–744. https://doi.org/10.1016/j.jtcvs.2013.09.064 (Discussion 744–736)
Baldi S, Ruffini E, Harari S, Roviaro GC, Nosotti M, Bellaviti N, Venuta F, Diso D, Rea F, Schiraldi C, Durigato A, Pavanello M, Carretta A, Zannini P (2005) Does lobectomy for lung cancer in patients with chronic obstructive pulmonary disease affect lung function? A multicenter national study. J Thorac Cardiovasc Surg 130(6):1616–1622. https://doi.org/10.1016/j.jtcvs.2005.06.049
Duman IE, Cimsit C, Yildizeli SO, Cimsit NC (2017) Parenchymal density changes in acute pulmonary embolism: can quantitative CT be a diagnostic tool? A preliminary study. Clin Imaging 41:157–163. https://doi.org/10.1016/j.clinimag.2016.11.005
Disease GIfCOL (2017) Pocket guide to COPD diagnosis, management, and prevention. http://goldcopd.org/wp-content/uploads/2016/12/wms-GOLD-2017-Pocket-Guide.pdf
Dou TH, Thomas DH, O’Connell DP, Lamb JM, Lee P, Low DA (2015) A method for assessing ground-truth accuracy of the 5DCT technique. Int J Radiat Oncol Biol Phys 93(4):925–933. https://doi.org/10.1016/j.ijrobp.2015.07.2272
Tang H, Zhang C, Xie X (2019) Automatic pulmonary lobe segmentation using deep learning. In: 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019), 8–11 April 2019, pp 1225–1228. https://doi.org/10.1109/ISBI.2019.8759468
Doel T, Matin TN, Gleeson FV, Gavaghan DJ, Grau V (2012) Pulmonary lobe segmentation from CT images using fissureness, airways, vessels and multilevel B-Splines. In: 2012 9th IEEE international symposium on biomedical imaging (Isbi), pp 1491–1494
Doel T, Gavaghan DJ, Grau V (2015) Review of automatic pulmonary lobe segmentation methods from CT. Comput Med Imaging Graph 40:13–29. https://doi.org/10.1016/j.compmedimag.2014.10.008
Low DA, White BM, Lee PP, Thomas DH, Gaudio S, Jani SS, Wu X, Lamb JM (2013) A novel CT acquisition and analysis technique for breathing motion modeling. Phys Med Biol 58(11):L31-36. https://doi.org/10.1088/0031-9155/58/11/l31
O’Connell D, Ruan D, Thomas DH, Dou TH, Lewis JH, Santhanam A, Lee P, Low DA (2018) A prospective gating method to acquire a diverse set of free-breathing CT images for model-based 4DCT. Phys Med Biol 63(4):04NT03. https://doi.org/10.1088/1361-6560/aaa90f
Rintoul RC, Atherton R, Tweed K, Yates S, Chilvers ER (2017) Exposure of patients to ionising radiation during lung cancer diagnostic work-up. Thorax. https://doi.org/10.1136/thoraxjnl-2016-209641
Heinrich MP, Jenkinson M, Bhushan M, Matin T, Gleeson FV, Brady SM, Schnabel JA (2012) MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration. Med Image Anal 16(7):1423–1435. https://doi.org/10.1016/j.media.2012.05.008
Heinrich MP, Jenkinson M, Brady M, Schnabel JA (2013) MRF-based deformable registration and ventilation estimation of lung CT. IEEE Trans Med Imaging 32(7):1239–1248. https://doi.org/10.1109/TMI.2013.2246577
Santhanam AP, Stiehl B, Lauria M, Hasse K, Barjaktarevic I, Goldin J, Low DA (2020) An adversarial machine learning framework and biomechanical model-guided approach for computing 3D lung tissue elasticity from end-expiration 3DCT. Med Phys. https://doi.org/10.1002/mp.14252
Isola P, Zhu J, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), 21–26 July 2017, pp 5967–5976. https://doi.org/10.1109/CVPR.2017.632
Kingma D, Ba J (2014) Adam: a method for stochastic optimization. In: International conference on learning representations
Neylon J, Min Y, Low DA, Santhanam A (2017) A neural network approach for fast, automated quantification of DIR performance. Med Phys 44(8):4126–4138. https://doi.org/10.1002/mp.12321
Zhou W, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612. https://doi.org/10.1109/TIP.2003.819861
Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302. https://doi.org/10.2307/1932409
Funding
This work supported by the Tobacco Related Disease Research Program 27IR‐0056, NIH R56 1R56HL139767‐01A1, Ken and Wendy Ruby Foundation, and the UCLA Department of Radiation Oncology.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethics approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.
Informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Stiehl, B., Lauria, M., Singhrao, K. et al. Scalable quorum-based deep neural networks with adversarial learning for automated lung lobe segmentation in fast helical free-breathing CTs. Int J CARS 16, 1775–1784 (2021). https://doi.org/10.1007/s11548-021-02454-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-021-02454-6