Skip to main content
SpringerLink
Log in

A feature extraction method for lung nodules based on a multichannel principal component analysis network (PCANet)

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Feature extraction of lung nodules is very important in the diagnosis of lung cancer and is the premise of feature description, target matching, recognition and benign and malignant diagnosis. The main contribution of this work is the development of a new end-to-end feature extraction method that learns effective feature representation from images to effectively establish the direct relationship between multiple features and tissue features (that is, benign or malignant). The architecture consists of three seamlessly connected functional layers. RGB multichannel can automatically extract ROI sequence images involving lung parenchyma from the lung imaging sequence. The feature extraction layers, using Principal Component Analysis Network - random binary hash (PCANet-RBH), a) extract high-level semantic features of the R/G/B channel by cascading PCA and fuse the extracted normal color patterns, and b) generate multiple binary patterns via RBH to produce richer features with color information. The connected spatial pyramid pooling (SPP) layer can extract the location features of the lung nodules and map the feature matrix to the low-dimensional space and then establish a correspondence between the image features and the organizational identity. We validate the performance of the proposed method using the public dataset LIDC. The experimental results show that the fusion features extracted by our method have high and stable classification accuracy (accuracy:93.25 ± 0.53, sensitivity:93.12 ± 0.62 specificity:91.37 ± 0.62), which is significantly better than the traditional algorithm for lung nodule feature extraction. Moreover, RGB-PCANet has a short training time, which can meet the requirements of real-time diagnosis of lung cancer. In general, the advantage of our framework is that it provides a better and more comprehensive method to establish a direct relationship between image high-level semantic features, color features, location features and tissue features, making it an attractive clinical diagnostic tool for lung cancer.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Transactions on Pattern Analysis & Machine Intelligence 35(8):1798–1828

    Article  Google Scholar 

  2. Chan TH, Jia K, Gao S et al (2015) PCANet: A Simple Deep Learning Baseline for Image Classification? IEEE Trans Image Process 24(12):5017–5032

    Article  MathSciNet  MATH  Google Scholar 

  3. Chen C, Wang D H, Wang H (2015) Scene character recognition using PCANet. International Conference on Internet Multimedia Computing and Service. ACM, pp. 1–4

  4. Chlaoua R, Meraoumia A, Aiadi KE et al (2018) Deep learning for finger-knuckle-print identification system based on PCANet and SVM classifier. Evol Syst 2:1–12

    Article  Google Scholar 

  5. Dhara AK, Mukhopadhyay S, Dutta A et al (2016) A Combination of Shape and Texture Features for Classification of Pulmonary Nodules in Lung CT Images. J Digit Imaging 29(4):466–475

    Article  Google Scholar 

  6. Han H, Li L, Han F et al (2015) Fast and Adaptive Detection of Pulmonary Nodules in Thoracic CT Images Using a Hierarchical Vector Quantization Scheme. IEEE Journal of Biomedical & Health Informatics 19(2):648

    Article  Google Scholar 

  7. Han F, Wang H, Zhang G et al (2015) Texture feature analysis for computer-aided diagnosis on pulmonary nodules. J Digit Imaging 28(1):99–115

    Article  Google Scholar 

  8. Hou C, Nie F, Zhang C et al (2014) Multiple rank multi-linear SVM for matrix data classification. Pattern Recogn 47(1):454–469

    Article  MATH  Google Scholar 

  9. Hua KL, Hsu CH, Hidayati SC et al (2015) Computer-aided classification of lung nodules on computed tomography images via deep learning technique. Oncotargets & Therapy 8:2015

    Google Scholar 

  10. Jiang M, Zhang S, Huang J, et al (2015) Joint Kernel-based supervised hashing for scalable histopathological image analysis. Medical Image Computing and Computer-Assisted Intervention — MICCAI 2015. Springer International Publishing, vol. 1, pp. 558–560

  11. Kenji S, Kunio D (2005) How can a massive training artificial neural network (MTANN) be trained with a small number of cases in the distinction between nodules and vessels in thoracic CT. Acad Radiol 12(10):1333–1341

    Article  Google Scholar 

  12. Kim YI, Ahn JM, Sung HJ et al (2016) Meta-markers for the differential diagnosis of lung cancer and lung disease. J Proteome 148:36–43

    Article  Google Scholar 

  13. Kim BC, Yu SS, Suk HI (2016) Deep feature learning for pulmonary nodule classification in a lung CT. International Winter Conference on Brain-Computer Interface. IEEE, pp. 1–3

  14. Ko JP, Betke M (2001) Chest CT: automated nodule detection and assessment of change over time. Radiology 218(1):267–273

    Article  Google Scholar 

  15. Kobayashi T (2014) Low-Rank Bilinear Classification: Efficient Convex Optimization and Extensions. Int J Comput Vis 110(3):308–327

    Article  MATH  Google Scholar 

  16. Kobayashi T, Otsu N (2012) Efficient optimization for low-rank integrated bilinear classifiers. Computer Vision–ECCV 2012. Springer, Berlin, pp 474–487

    Google Scholar 

  17. Kumar D, Wong A, Clausi DA (2015) Lung nodule classification using deep features in CT images. Conference on Computer and Robot Vision. IEEE Computer Society, pp. 133-138

  18. Lakshmi SP, Reddy AT, Banno A et al (2017) PPAR Agonists for the Prevention and Treatment of Lung Cancer. PPAR Res 2017(1):1–8

    Article  Google Scholar 

  19. Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. Proc of IEEE Computer Vision & Pattern Recognition 2(1/2):2169–2178

    Google Scholar 

  20. Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436

    Article  Google Scholar 

  21. Lin D-y, Chung-Tell Y, Tai CW (2005) Autonomous detection of pulmonary nodules on CT images with a neural network based fuzzy system. Computerized Medical Imageing and Graphics 29:447–458

    Article  Google Scholar 

  22. Lin DT, Yan CW (2005) Autonomous detection of pulmonary nodules on CT images with a neural network-based fuzzy system. Computerized Medical Imaging & Graphics the Official Journal of the Computerized Medical Imaging Society 29(6):447–458

    Article  MathSciNet  Google Scholar 

  23. Mousa WAH, Khan MAU (2002) Lung nodule classification utilizing support vector machines. Proceedings International Conference on Image Processing 3:153–156

    Google Scholar 

  24. Osicka T, Freedman M T, Ahmed F (2006) Characterization of pulmonary nodules features on computer tomography (CT) scans using wavelet coefficients and heat maps. Medical Imaging. International Society for Optics and Photonics, pp. 614463–614463-11

  25. Qiang Y, Ge L, Zhao X et al (2017) Pulmonary nodule diagnosis using dual-modal supervised autoencoder based on extreme learning machine. Expert Syst 11:e12224

    Article  Google Scholar 

  26. Ramaswamy S, Truong K (2016) Pulmonary Nodule Classification with Convolutional Neural Networks

  27. Shi J, Wu J, Li Y et al (2017) Histopathological Image Classification with Color Pattern Random Binary Hashing Based PCANet and Matrix-Form Classifier. IEEE Journal of Biomedical & Health Informatics PP(99):1

    Google Scholar 

  28. Shu-Tong L I, Xiao B, Wei-Sheng L I, et al (2018) Diagnosis of Alzheimer's Disease Based on 3D-PCANet. Computer Science

  29. Soltani T, Salari R, Ferdousi R (2015) Make a good diagnosis on clinical images by ubiquitous decision support tools. Iranian Imaging Informatics Conference. p. 37

  30. Sun W, Zheng B, Qian W (2016) Computer aided lung cancer diagnosis with deep learning algorithms. Medical Imaging: Computer-Aided Diagnosis

  31. Tarando SR, Fetita C, Faccinetto A, et al (2017) Increasing CAD system efficacy for lung texture analysis using a convolutional network. Medical Imaging 2016: Computer-Aided Diagnosis. Medical Imaging 2016: Computer-Aided Diagnosis, pp. 97850Q

  32. Wang Z, Chen S, Liu J et al (2008) Pattern Representation in Feature Extraction and Classifier Design: Matrix Versus Vector. IEEE Trans Neural Netw 19(5):758–769

    Article  Google Scholar 

  33. Xiao X, Qiang Y, Zhao J, et al (2016) A deep learning model of automatic detection of pulmonary nodules based on convolution neural networks (CNNs). Bio-Inspired Computing - Theories and Applications. Springer Singapore, pp. 349–361

  34. Xie Y, Zhang J, Liu S, et al (2016) Lung Nodule Classification by Jointly Using Visual Descriptors and Deep Features. pp. 116–125

  35. Xu XW, Doi K, Kobayashi T et al (1997) Development of an improved CAD scheme for automated detection of lung nodules in digital chest images. Med Phys 24(9):1395–1403

    Article  Google Scholar 

  36. Yu D, Wu XJ (2018) 2DPCANet: a deep leaning network for face recognition. Multimedia Tools & Applications 4:1–16

    Google Scholar 

  37. Zaidi H, Becker M (2016) The Promise of Hybrid PET/MRI: Technical advances and clinical applications. IEEE Signal Process Mag 33(3):67–85

    Article  Google Scholar 

  38. Zhao J, Ji G, Qiang Y et al (2015) A New Method of Detecting Pulmonary Nodules with PET/CT Based on an Improved Watershed Algorithm. PLoS One 10(4):e0123694

    Article  Google Scholar 

  39. Zhao J, Pan L, Zhao P et al (2017) Medical Sign Recognition of Lung Nodules Based on Image Retrieval with Semantic Feature and Supervised Hashing. J Comput Sci Technol 32(3):457–469

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of information and computer, Taiyuan University of Technology, Taiyuan, Shanxi, China

    Xiaojiao Xiao, Zilin Qiang, Juanjuan Zhao, Yan Qiang, Pan Wang & Peng Han

Authors
  1. Xiaojiao Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zilin Qiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Juanjuan Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yan Qiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Pan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Peng Han
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Juanjuan Zhao.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xiao, X., Qiang, Z., Zhao, J. et al. A feature extraction method for lung nodules based on a multichannel principal component analysis network (PCANet). Multimed Tools Appl 78, 17317–17335 (2019). https://doi.org/10.1007/s11042-018-7041-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-7041-y

Keywords

Search

Navigation