Advertisement

Learning to Recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks

  • Sebastian GündelEmail author
  • Sasa Grbic
  • Bogdan Georgescu
  • Siqi Liu
  • Andreas Maier
  • Dorin Comaniciu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11401)

Abstract

Chest X-ray is the most common medical imaging exam used to assess multiple pathologies. Automated algorithms and tools have the potential to support the reading workflow, improve efficiency, and reduce reading errors. With the availability of large scale data sets, several methods have been proposed to classify pathologies on chest X-ray images. However, most methods report performance based on random image based splitting, ignoring the high probability of the same patient appearing in both training and test set. In addition, most methods fail to explicitly incorporate the spatial information of abnormalities or utilize the high resolution images. We propose a novel approach based on location aware Dense Networks (DNetLoc), whereby we incorporate both high-resolution image data and spatial information for abnormality classification. We evaluate our method on the largest data set reported in the community, containing a total of 86,876 patients and 297,541 chest X-ray images. We achieve (i) the best average AUC score for published training and test splits on the single benchmarking data set (ChestX-Ray14 [1]), and (ii) improved AUC scores when the pathology location information is explicitly used. To foster future research we demonstrate the limitations of the current benchmarking setup [1] and provide new reference patient-wise splits for the used data sets. This could support consistent and meaningful benchmarking of future methods on the largest publicly available data sets.

References

  1. 1.
    Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.: Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of CVPR, pp. 3462–3471 (2017)Google Scholar
  2. 2.
    Kamel, S.I., Levin, D.C., Parker, L., Rao, V.M.: Utilization trends in noncardiac thoracic imaging, 2002–2014. JACR 14(3), 337–42 (2017)Google Scholar
  3. 3.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770–778 (2016)Google Scholar
  4. 4.
    Rajpurkar, P., et al.: CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv:1711.05225 (2017)
  5. 5.
    Yao, L., Poblenz, E., Dagunts, D., Covington, B., Bernard, D., Lyman, K.: Learning to diagnose from scratch by exploiting dependencies among labels. arXiv:1710.10501 (2017)
  6. 6.
    Guan, Q., Huang, Y., Zhong, Z., Zheng, Z., Zheng, L., Yang, Y.: Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification. ArXiv e-prints, January 2016Google Scholar
  7. 7.
    Gohagan, J.K., Prorok, P.C., Hayes, R.B., Kramer, B.S.: The prostate, lung, colorectal and ovarian (PLCO) cancer screening trial of the national cancer institute: history, organization, and status. Control. Clin. Trials 21(6), 251S–272S (2000)CrossRefGoogle Scholar
  8. 8.
    Huang, G., Zhang, L., van der Maaten, L., Weinberger, K.Q.: Densely Connected Convolutional Networks. ArXiv e-prints, August 2016Google Scholar
  9. 9.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. ArXiv e-prints, December 2014Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Sebastian Gündel
    • 1
    • 2
    Email author
  • Sasa Grbic
    • 1
  • Bogdan Georgescu
    • 1
  • Siqi Liu
    • 1
  • Andreas Maier
    • 1
  • Dorin Comaniciu
    • 1
  1. 1.Siemens Imaging Technologies, Siemens HealthineersPrincetonUSA
  2. 2.Pattern Recognition Lab, Friedrich-Alexander-UniversitätErlangenGermany

Personalised recommendations