Multi-level 3D Densenets for False-positive Reduction in Lung Nodule Detection Based on Chest Computed Tomography

Author(s): Xiaoqi Lu, Yu Gu*, Lidong Yang, Baohua Zhang, Ying Zhao, Dahua Yu, Jianfeng Zhao, Lixin Gao, Tao Zhou, Yang Liu, Wei Zhang

Journal Name: Current Medical Imaging
Formerly: Current Medical Imaging Reviews

Volume 16 , Issue 8 , 2020

Become EABM
Become Reviewer
Call for Editor

Graphical Abstract:


Objective: False-positive nodule reduction is a crucial part of a computer-aided detection (CADe) system, which assists radiologists in accurate lung nodule detection. In this research, a novel scheme using multi-level 3D DenseNet framework is proposed to implement false-positive nodule reduction task.

Methods: Multi-level 3D DenseNet models were extended to differentiate lung nodules from falsepositive nodules. First, different models were fed with 3D cubes with different sizes for encoding multi-level contextual information to meet the challenges of the large variations of lung nodules. In addition, image rotation and flipping were utilized to upsample positive samples which consisted of a positive sample set. Furthermore, the 3D DenseNets were designed to keep low-level information of nodules, as densely connected structures in DenseNet can reuse features of lung nodules and then boost feature propagation. Finally, the optimal weighted linear combination of all model scores obtained the best classification result in this research.

Results: The proposed method was evaluated with LUNA16 dataset which contained 888 thin-slice CT scans. The performance was validated via 10-fold cross-validation. Both the Free-response Receiver Operating Characteristic (FROC) curve and the Competition Performance Metric (CPM) score show that the proposed scheme can achieve a satisfactory detection performance in the falsepositive reduction track of the LUNA16 challenge.

Conclusion: The result shows that the proposed scheme can be significant for false-positive nodule reduction task.

Keywords: Lung nodule detection, false-positive reduction, multi-level 3D DenseNets, computer-aided detection, convolutional neural networks.

Chen W, Zheng R, Baade PD, et al. Cancer statistics in China, 2015. CA Cancer J Clin 2016; 66(2): 115-32.
[ ] [PMID: 26808342]
Zheng R, Zeng H, Zhang S, Chen T, Chen W. National estimates of cancer prevalence in China, 2011. Cancer Lett 2016; 370(1): 33-8.
[ ] [PMID: 26458996]
Zhang Y, Zheng T, Zhang W. Report of cancer incidence and mortality in China, 2012. Adv Mod Oncol Res 2018; 4(3): 1-7.
Yoshida H. Multiscale edge-guided wavelet snake model for delineation of pulmonary nodules in chest radiographs. J Electron Imaging 2003; 12(1): 69-80.
Siegel RL, Miller KD, Jemal A. Cancer statistics, 2016. CA Cancer J Clin 2016; 66(1): 7-30.
[ ] [PMID: 26742998]
Aberle DR, Adams AM, Berg CD, et al. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011; 365(5): 395-409.
[ ] [PMID: 21714641]
Gu Y, Lu X, Zhang B, et al. Automatic lung nodule detection using multi-scale dot nodule-enhancement filter and weighted support vector machines in chest computed tomography. PLoS One 2019; 14(1)e0210551
[ ] [PMID: 30629724]
Zhang JJ, Xia Y, Cui HF, Zhang YN. Pulmonary nodule detection in medical images: A survey. BIOMED SIGNAL PROCES 2018; 43: 138-47.
Bajwa UI, Shah AA, Anwar MW, Gilanie G, Bajwa AE. Computer-Aided Detection (CADe) System for Detection of Malignant Lung Nodules in CT Slices - a Key for Early Lung Cancer Detection. Curr Med Imaging Rev 2018; 14(3): 422-9.
Li Q, Li F, Doi K. Computerized detection of lung nodules in thin-section CT images by use of selective enhancement filters and an automated rule-based classifier. Acad Radiol 2008; 15(2): 165-75.
[ ] [PMID: 18206615]
Zhang W, Wang X, Li X, Chen J. 3D skeletonization feature based computer-aided detection system for pulmonary nodules in CT datasets. Comput Biol Med 2018; 92: 64-72.
[ ] [PMID: 29154123]
Zhang W, Wang X, Zhang P, Chen J. Global optimal hybrid geometric active contour for automated lung segmentation on CT images. Comput Biol Med 2017; 91: 168-80.
[ ] [PMID: 29080491]
Nithila EE, Kumar SS. Segmentation of lung from CT using various active contour models. BIOMED SIGNAL PROCES 2019; 47: 57-62.
Rehman MZU, Javaid M, Shah SIA, Gilani SO, Jamil M, Butt SI. An appraisal of nodules detection techniques for lung cancer in CT images. BIOMED SIGNAL PROCES 2018; 41: 140-51.
Naqi S, Sharif M, Yasmin M, Fernandes SL. Lung nodule detection using polygon approximation and hybrid features from CT images. Curr Med Imaging Rev 2018; 14(1): 108-17.
Setio AA, Ciompi F, Litjens G, et al. Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 2016; 35(5): 1160-9.
[ ] [PMID: 26955024]
Wang B, Si S, Zhao H, Zhu H, Dou S. False positive reduction in pulmonary nodule classification using 3D texture and edge feature in CT images. Technol Health Care 2019; 1-18.
Dou Q, Chen H, Yu L, Qin J, Heng PA. Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection. IEEE Trans Biomed Eng 2017; 64(7): 1558-67.
[ ] [PMID: 28113302]
Zheng S, Guo J, Cui X, Veldhuis RN, Oudkerk M, van Ooijen P. Automatic pulmonary nodule detection in CT scans using convolutional neural networks based on maximum intensity projection IEEE T Med Imaging 2019. Early Access
Liu J, Cao L, Akin O, Tian Y. Accurate and robust pulmonary nodule detection by 3D feature pyramid network with selfsupervised feature learning. arXiv preprint arXiv 2019.
Li Z, Tang J. Weakly supervised deep metric learning for community-contributed image retrieval. IEEE T Multimedia 2015; 17(11): 1989-99.
Zhang W, Lu X, Gu Y, Liu Y, Meng X, Li J. A Robust Iris Segmentation Scheme Based on Improved U-Net. IEEE Access 2019 7: 85082-9.
Wang J, Wang J, Wen Y, et al. Pulmonary nodule detection in volumetric chest CT scans using CNNs-based nodule-size-adaptive detection and classification. IEEE Access 2019 7: 46033-4.
da Silva GLF, Valente TLA, Silva AC, de Paiva AC, Gattass M. Convolutional neural network-based PSO for lung nodule false positive reduction on CT images. Comput Methods Programs Biomed 2018; 162: 109-18.
[ ] [PMID: 29903476]
Jin H, Li Z, Tong R, Lin L. A deep 3D residual CNN for false-positive reduction in pulmonary nodule detection. Med Phys 2018; 45(5): 2097-107.
[ ] [PMID: 29500816]
Dobrenkii A, Kuleev R, Khan A, Rivera AR, Khattak AM. Large residual multiple view 3D CNN for false positive reduction in pulmonary nodule detection. Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), 2017 IEEE Conference on 2017 August 23-25; Manchester, United kingdomUnited States: IEEE. 1-6.
Ding J, Li A, Hu Z, Wang L. Accurate pulmonary nodule detection in computed tomography images using deep convolutional neural networks. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2017 September 11-13; Quebec City, QC, Canada.Germany: Springer 2017;. pp. 559-67.
Jin H, Li Z, Tong R, Lin L. A deep 3D residual CNN for false-positive reduction in pulmonary nodule detection. Med Phys 2018; 45(5): 2097-107.
[ ] [PMID: 29500816]
Qin Y, Zheng H, Zhu Y-M, Yang J. Simultaneous accurate detection of pulmonary nodules and false positive reduction using 3D CNNs. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2018, April 15-20; Calgary, AB, Canada.United States: IEEE. 1005-9.
[ ]
Xie H, Yang D, Sun N, Chen Z, Zhang Y. Automated pulmonary nodule detection in CT images using deep convolutional neural networks. PATTERN RECOGN 2019; 85: 109-19.
Tran D, Bourdev L, Fergus R, Torresani L, Paluri M. Learning spatiotemporal features with 3D convolutional networks. Computer Vision (ICCV), 2015 IEEE International Conference on; 2015, December 11-18; Santiago, Chile. United States: IEEE;2015. pp. 4489-97.
Gu Y, Lu X, Yang L, et al. Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs. Comput Biol Med 2018; 103: 220-31.
[ ] [PMID: 30390571]
Zhang G, Jiang S, Yang Z, et al. Automatic nodule detection for lung cancer in CT images: A review. Comput Biol Med 2018; 103: 287-300.
[ ] [PMID: 30415174]
El-Regaily SA, Salem MA, Abdel Aziz MH, Roushdy MI. Survey of computer aided detection systems for lung cancer in computed tomography. Curr Med Imaging Rev 2018; 14(1): 3-18.
Sakamoto M, Nakano H, Zhao K, Sekiyama T. Multi-stage neural networks with single-sided classifiers for false positive reduction and its evaluation using lung X-ray CT images. International Conference on Image Analysis and Processing. 2017, September 11-15; Catania, Italy.Germany: Springer. 370-9.
Polat G, Halici U, Dogrusoz YS. False positive reduction in lung computed tomography images using convolutional neural networks. arXiv preprint arXiv 2018.
Sang H, Wang C, He D, Liu Q. Multi-information flow CNN and attribute-aided reranking for person reidentification.Comput Intell Neurosci 2019; 6(2019): 7028107.
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 2016; 35(5): 1285-98.
[ ] [PMID: 26886976]
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal 2017; 42: 60-88.
[ ] [PMID: 28778026]
Shen D, Wu G, Suk H-I. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017; 19: 221-48.
[ ] [PMID: 28301734]
Huang G, Liu Z, Weinberger KQ, van der Maaten L. Densely connected convolutional networks. IEEE conference on computer vision and pattern recognition 2017, July 25-30; Hawaii, United States United States: IEEE. 4700-8.
Wang B, Qi G, Tang S, Zhang L, Deng L, Zhang Y. Automated pulmonary nodule detection: High sensitivity with few candidates. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2018, September 16-20; Granada, Spain..Germany: Springer. 759-67.
Khosravan N, Bagci U. S4ND: Single-shot single-scale lung nodule detection. International Conference on Medical Image Computing and Computer-Assisted Intervention 2018; 2018, September 16-20; Granada, Spain Germany: Springer, 2018; 794-802.
Wang M, Li H, Wu Y, Bu Q, Feng J. Diagnostic Classification of Pulmonary Nodules Using a Multi-scale and Multi-input DenseNet. Chinese Conference on Image and Graphics Technologies 2019 April 19-20; Beijing, China. Germany: Springer 2019; pp. 553-64.
Setio AAA, Traverso A, de Bel T, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge. Med Image Anal 2017; 42: 1-13.
[ ] [PMID: 28732268]
Huang X, Shan J, Vaidya V. Lung nodule detection in CT using 3D convolutional neural networks 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017); 2017, April 18-21; Melbourne, VIC, Australia United States: IEEE. 379-83
Pehrson LM, Nielsen MB, Ammitzbøl Lauridsen C. Automatic pulmonary nodule detection applying deep learning or machine learning algorithms to the LIDC-IDRI database: A systematic review. Diagnostics (Basel) 2019; 9(1): 29.
[ ] [PMID: 30866425]
Zhu W, Liu C, Fan W, Xie X. Deep lung: Deep 3D dual path nets for automated pulmonary nodule detection and classification.2018 IEEE Winter Conference on Applications of Computer Vision (WACV). 2018 March 12-15; Lake Tahoe, NV, United states. United States: IEEE 673-81.
Armato SG III, McLennan G, Bidaut L, et al. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans. Med Phys 2011; 38(2): 915-31.
[ ] [PMID: 21452728]
Jacobs C, van Rikxoort EM, Murphy K, Prokop M, Schaefer-Prokop CM, van Ginneken B. Computer-aided detection of pulmonary nodules: a comparative study using the public LIDC/IDRI database. Eur Radiol 2016; 26(7): 2139-47.
[ ] [PMID: 26443601]
Zhang G, Yang Z, Gong L, Jiang S, Wang L. Classification of benign and malignant lung nodules from CT images based on hybrid features. Phys Med Biol 2019; 64(12)125011
[ ] [PMID: 31141794]
Gruetzemacher R, Gupta A, Paradice D. 3D deep learning for detecting pulmonary nodules in CT scans. J Am Med Inform Assoc 2018; 25(10): 1301-10.
[ ] [PMID: 30137371]
Traverso A, Torres EL, Fantacci ME, Cerello P. Computer-aided detection systems to improve lung cancer early diagnosis: State-of-the-art and challenges. J Phys Conf Ser 2017; 841(1): 1-6.
Murphy K, van Ginneken B, Schilham AM, de Hoop BJ, Gietema HA, Prokop M. A large-scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbour classification. Med Image Anal 2009; 13(5): 757-70.
[ ] [PMID: 19646913]
Jacobs C, van Rikxoort EM, Twellmann T, et al. Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images. Med Image Anal 2014; 18(2): 374-84.
[ ] [PMID: 24434166]
Setio AA, Jacobs C, Gelderblom J, van Ginneken B. Automatic detection of large pulmonary solid nodules in thoracic CT images. Med Phys 2015; 42(10): 5642-53.
[ ] [PMID: 26429238]
Tan M, Deklerck R, Jansen B, Bister M, Cornelis J. A novel computer-aided lung nodule detection system for CT images. Med Phys 2011; 38(10): 5630-45.
[ ] [PMID: 21992380]
Torres EL, Fiorina E, Pennazio F, et al. Large scale validation of the M5L lung CAD on heterogeneous CT datasets. Med Phys 2015; 42(4): 1477-89.
[ ] [PMID: 25832038]
Polat G. Classification of lung nodules in CT images using convolutional neural networks Ankara: Middle east technical university 2018.
LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE 1998; 86(11): 2278-324.
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv 2015.
Nair V, Hinton GE. Rectified linear units improve Restricted Boltzmann machines. 27th International Conference on Machine Learning, ICML 2010 2010, June 21-25;Haifa, Israel; United States: International Machine Learning Society 2010; pp. 807-14.
Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv 2012.
Lin M, Chen Q, Yan S. Network in network. arXiv preprint arXiv 2013.
Liu W, Wen Y, Yu Z, Yang M, Eds. Large-margin softmax loss for convolutional neural networks. 33rd International Conference on Machine Learning, ICML 2016. 2016, June 19-24; New York, United States; United States: International Machine Learning Society 2016;. pp. 1-10.
Wang F, Cheng J, Liu W, Liu H. Additive margin softmax for face verification. IEEE SIGNAL PROC LET 2018; 25(7): 926-30.
Han B, Wu Y. A novel active contour model based on modified symmetric cross entropy for remote sensing river image segmentation. PATTERN RECOGN 2017; 67: 396-409.
Xie Y, Xia Y, Zhang J, et al. Knowledge-based collaborative deep learning for benign-malignant lung nodule classification on chest CT. IEEE Trans Med Imaging 2019; 38(4): 991-1004.
[ ] [PMID: 30334786]
Dietterich TG. Ensemble methods in machine learning. International workshop on multiple classifier systems; 2000, June 21- 23; Cagliari, Italy Germany: Springer. 1-15.
Farahani FV, Ahmadi A, Zarandi MF. Lung nodule diagnosis from CT images based on ensemble learning. 2015 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). 2015, August 12-15; Niagara Falls, ON, Canada United States: IEEE. 1-7.
He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision. 2015, December 13-16; Santiago, Chile United States: IEEE Computer Society. 1026-34.
[ ]
Kumar SK. On weight initialization in deep neural networks. arXiv preprint arXiv 2017.
Zeiler MD. ADADELTA: an adaptive learning rate method. arXiv preprint arXiv 2012.
Ruder S. An overview of gradient descent optimization algorithms. arXiv preprint arXiv 2016.
Dou Q, Chen H, Jin Y, Lin H, Qin J, Heng P-A. Automated pulmonary nodule detection via 3D convNets with online sample filtering and hybrid-loss residual learning. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2017, September 11-13; Quebec City, QC, Canada. Germany: Springer. 630-8.
Moskowitz CS. Using free-response receiver operating characteristic curves to assess the accuracy of machine diagnosis of cancer. JAMA 2017; 318(22): 2250-1.
[ ] [PMID: 29234793]
Niemeijer M, Loog M, Abramoff MD, Viergever MA, Prokop M, van Ginneken B. On combining computer-aided detection systems. IEEE Trans Med Imaging 2011; 30(2): 215-23.
[ ] [PMID: 20813633]

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2020
Published on: 18 October, 2020
Page: [1004 - 1021]
Pages: 18
DOI: 10.2174/1573405615666191113122840
Price: $65

Article Metrics

PDF: 21