Multimedia Tools and Applications

, Volume 78, Issue 1, pp 1017–1033 | Cite as

A deep CNN based transfer learning method for false positive reduction

  • Zhenghao ShiEmail author
  • Huan Hao
  • Minghua Zhao
  • Yaning Feng
  • Lifeng HeEmail author
  • Yinghui Wang
  • Kenji SuzukiEmail author


A low false positive (FP) rate is of great importance for the use of a Computer Aided Detection (CAD) system to detect pulmonary nodules in thoracic Computed Tomography (CT). However, due to the variations of nodules in appear and size, it is still a very challenging task to obtain a low FP rate. In this paper, we propose a deep Convolutional Neural Network (CNN) based transfer learning method for FP reduction in pulmonary nodule detection on CT slices. We utilized one of the state-of-the-art CNN models, VGG-16 [4], as a feature extractor to obtain nodule features, and used a support vector machine (SVM) for nodule classification. Firstly we transferred all the layers from a pre-trained VGG-16 model in ImageNet to our target networks. Then, we tuned the last fully connected layers to adjust the computer-vision-task-trained CNN model to pulmonary nodule classification task. The initial CNN filter weights were then optimized using the training data, i.e., the pulmonary nodule patch images and corresponding labels through back-propagation so that they better reflected the modalities in the pulmonary nodule image dataset. Finally, features learned in the fine-tuned CNN were used to train a SVM classifier. The output of the trained SVM was used for final classification. Experimental results show that the overall sensitivity of the proposed method was 87.2% with 0.39 FPs per scan, which is higher than 85.4% with 4 FPs per scan obtained by other state of art method.


False positive reduction Nodule detection Deep convolutional network Support vector machine 



This work was supported in part by a grant from the National Natural Science Foundation of China (No. 61202198, No.61401355), a grant from the China Scholarship Council (No.201608610048) and the Nature Science Foundation of Science Department of PeiLin count at Xi’an(GX1619), the Key Laboratory Foundation of Shaanxi Education Department, China (No.14JS072). The authors gratefully acknowledge the helpful comments and suggestions of the reviewers.


  1. 1.
    Bar Y, Diamant I, Wolf L, and Greenspan H (2015) Deep learning with non-medical training used for chest pathology identification, in Proc. SPIE Med Imag, 94 140V–94 140VGoogle Scholar
  2. 2.
    Camarlinghi N (2013) Automatic detection of lung nodules in computed tomography images: training and validation of algorithms using public research databases. Eur Phys JPlus 128(9):21Google Scholar
  3. 3.
    Dhara AK, Mukhopadhyay S, Khandelwal N (2012) Computer-aided detection and analysis of pulmonary nodule from CT images: a survey. IETE Techn Rev 29(4):265–275CrossRefGoogle Scholar
  4. 4.
    Farag A, Ali A, Graham J, Farag A, Elshazly S, Falk R (2011) Evaluation of geometric feature descriptors for detection and classification of lung nodules in low dose CT scans of the chest. In: 2011 I.E. international symposium on biomedical imaging: from nano to macro. IEEE, 169–172Google Scholar
  5. 5.
    Gao M et al. (2015) Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks. In: 1st Workshop Deep Learn. Med. Image Anal., Int. Conf. Med. Image Comput. Comput. Assist. Intervent., Munich, Germany, [Online]. Available:
  6. 6.
    Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 I.E. Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 580–587Google Scholar
  7. 7.
    Girshick R, Donahue J, Darrell T, Malik J (2016) Region-based convolutional networks for accurate object detection and semantic segmentation. IEEE Trans Pattern Anal Mach Intell 38(1):142–158CrossRefGoogle Scholar
  8. 8.
    Jiang H, Ma H, Qian W, Gao M, Li Y (2017) An automatic detection system of lung nodule based on multi-group patch-based deep learning network. IEEE J Biomed Health Inform.
  9. 9.
    Khan A, ElDaly H, Rajpoot N (2013) A gamma-gaussian mixture model for detection of mitotic cells in breast cancer histopathology images. J Pathol Inf 4(1)Google Scholar
  10. 10.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst:1097–1105Google Scholar
  11. 11.
    Kumar D, Wong A, Clausi DA (2015) Lung nodule classification using deep features in CT images[C]// conference on computer and robot vision. IEEE Comput Soc 133–138Google Scholar
  12. 12.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444CrossRefGoogle Scholar
  13. 13.
    Li F, Arimura H, Suzuki K, Shiraishi J, Li Q, Abe H, Engelmann R, Sone S, MacMahon H, Doi K (2005) Computer-aided detection of peripheral lung cancers missed at CT: ROC analyses without and with localization. Radiology 237:684–690CrossRefGoogle Scholar
  14. 14.
    Liang MZ, Tang W, Xu DM, Jirapatnakul AC, Reeves AP, Henschke CI, Yankelevitz D (2016) Low-dose CT screening for lung Cancer: computer-aided detection of missed lung cancers. Radiology 281(1):279–288CrossRefGoogle Scholar
  15. 15.
    Liu J-K et al (2017) An Assisted Diagnosis System for Detection of Early Pulmonary Nodule in Computed Tomography Images. J Med Syst 41:30CrossRefGoogle Scholar
  16. 16.
    Lu L, Tan Y, Schwartz LH et al (2015) Hybrid detection of lung nodules on CT scan images. Med Phys 42(9):5042–5054 20CrossRefGoogle Scholar
  17. 17.
    Margeta J, Criminisi A, Lozoya RC, Lee DC, and Ayache N (2015) Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition. Comput Methods Biomech Biomed Eng, Imag Vis 1–11Google Scholar
  18. 18.
    Roth H et al. (2014) A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. In: proc. MICCAI, P. Goll, N. Hata, C. Barillot, J. Hornegger, and R. Howe, (eds.), vol. 8673, LNCS, pp. 520–527,Google Scholar
  19. 19.
    Setio A et al (2016) Pulmonary nodule detection in CT images using multi-view convolutional networks. IEEE Trans Med Imag 35(5):1160–1169CrossRefGoogle Scholar
  20. 20.
    Simonyan K, Zisserman A (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition ArXiv, [Online]. Available:arXiv:14091556Google Scholar
  21. 21.
    Sivakumar S, Chandrasekar C (2013) Lung nodule detection using fuzzy clustering and support vector machines. Int J Eng Technol 5(11):179–185Google Scholar
  22. 22.
    Society, AC (2016) February 8, 2016 [cited 2016 February 28, 2016]; Available from:
  23. 23.
    Song Y, Cai W, Zhou Y, Feng DD (2013) Feature-based image patch approximation for lung tissue classification. IEEE Trans Med Imaging 32(4):797–808CrossRefGoogle Scholar
  24. 24.
    Sorensen L, Shaker SB, De Bruijne M (2010) Quantitative analysis of pulmonary emphysema using local binary patterns. IEEE Trans Med Imaging 29(2):559–569CrossRefGoogle Scholar
  25. 25.
    Suzuki K (2012) Pixel-based machine-learning in medical imaging. Int J Biomed Imaging 2012: article ID 792079, 18 pagesGoogle Scholar
  26. 26.
    Suzuki K (2013) Machine learning in computer-aided diagnosis of the thorax and Colon in CT: a survey. IEICE Trans Inf Syst E96-D:772–783CrossRefGoogle Scholar
  27. 27.
    Suzuki K (2017) Overview of deep learning in medical imaging. Radiol Phys Technol 10(3):257–273CrossRefGoogle Scholar
  28. 28.
    Suzuki K (2017) Machine learning in medical imaging before and after introduction of deep learning. J Med Imaging Inform Sci 34(2):14–24Google Scholar
  29. 29.
    Suzuki K (2017) Survey of deep learning applications to medical image analysis. Med Imaging Technol 35(4):212–226Google Scholar
  30. 30.
    Suzuki K, Armato SG III, Li F, Sone S, Doi K (2003) Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography. Med Phys 30(7):1602–1617CrossRefGoogle Scholar
  31. 31.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: IEEE, CVPR pp. 1Google Scholar
  32. 32.
    Tajbakhsh N, Lian J (2015) Computer-aided pulmonary embolism detection using a novel vessel-aligned multi-planar image representation and convolutional neural networks. In: Proc MICCAIGoogle Scholar
  33. 33.
    Tajbakhsh N, Suzuki K (2017) Comparing two classes of end-to-end learning Machines for Lung Nodule Detection and Classification: MTANNs vs. CNNs. Pattern Recogn 63:476–486CrossRefGoogle Scholar
  34. 34.
    Tajbakhsh N, Gurudu SR, and Liang J (2015) A comprehensive computer-aided polyp detection system for colonoscopy videos. In: Information processing in medical imaging. New York: Springer, pp. 327–338Google Scholar
  35. 35.
    Tajbakhsh N, Gurudu SR, and Liang J (2015) Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks. In; Proc. IEEE 12th Int Symp O Biomed Imag, pp. 79–83Google Scholar
  36. 36.
    Valente IRS, Cortez PC, Neto EC, Soares JM, de Albuquerque VHC, Tavares JMR (2016) Automatic 3D pulmonary nodule detection in CT images: a survey. Comput Methods Prog Biomed 124:91–107CrossRefGoogle Scholar
  37. 37.
    Vedaldi A and Lenc K (2014) Matconvnet – convolutional neural networks for matlab. CoRR, abs/14124564Google Scholar
  38. 38.
    Xu Z, Mei L, Liu Y, Hu C, Chen L (2016) Semantic enhanced cloud environment for surveillance data management using video structural description. Computing 98(1–2):35–54MathSciNetCrossRefGoogle Scholar
  39. 39.
    Ye J, Ding Y (2018) Controllable keyword search scheme supporting multiple users. Future Generation Comp Syst 81:433–442CrossRefGoogle Scholar
  40. 40.
    Zhang J, Xia Y, Xie Y, Fulham M, Feng DD (2017) Classification of medical images in the biomedical literature by jointly using deep and handcrafted visual features," IEEE journal of biomedical and health informatics, available online 20 November 2017.
  41. 41.
    Zhang J, Xia Y, Cui H, Zhang Y (2018) Pulmonary nodule detection in medical images: a survey. Biomed Signal Process Control 43:138–147CrossRefGoogle Scholar
  42. 42.
    Zheng Y, Liu D, Georgescu B, Nguyen H, and Comaniciu D (2015) 3D deep learning for efficient and robust landmark detection in volumetric data. In: Proc. MICCAI, pp. 565–572Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringXi’an University of TechnologyXi’anChina
  2. 2.School of Information Science and TechnologyAichi Prefectural UniversityNagakuteJapan
  3. 3.Department of Electrical and Computer EngineeringIllinois Institute of TechnologyChicagoUSA
  4. 4.World Research Hub InitiativeInstitute of Innovative Research, Tokyo Institute of TechnologyYokohamaJapan

Personalised recommendations