Advertisement

Liver Lesion Detection from Weakly-Labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector

  • Sang-gil Lee
  • Jae Seok Bae
  • Hyunjae Kim
  • Jung Hoon Kim
  • Sungroh YoonEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)

Abstract

We present a focal liver lesion detection model leveraged by custom-designed multi-phase computed tomography (CT) volumes, which reflects real-world clinical lesion detection practice using a Single Shot MultiBox Detector (SSD). We show that grouped convolutions effectively harness richer information of the multi-phase data for the object detection model, while a naive application of SSD suffers from a generalization gap. We trained and evaluated the modified SSD model and recently proposed variants with our CT dataset of 64 subjects by five-fold cross validation. Our model achieved a 53.3% average precision score and ran in under three seconds per volume, outperforming the original model and state-of-the-art variants. Results show that the one-stage object detection model is a practical solution, which runs in near real-time and can learn an unbiased feature representation from a large-volume real-world detection dataset, which requires less tedious and time consuming construction of the weak phase-level bounding box labels.

Keywords

Deep learning Liver lesions Detection Multi-phase CT 

Notes

Acknowledgements

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science and ICT) [2018R1A2B3001628], the Interdisciplinary Research Initiatives Program from College of Engineering and College of Medicine, Seoul National University (800-20170166), Samsung Research Funding Center of Samsung Electronics under Project Number SRFC-IT1601-05, the Creative Industrial Technology Development Program [No. 10053249] funded by the Ministry of Trade, Industry & Energy (MOTIE, Korea), and the Brain Korea 21 Plus Project in 2018.

References

  1. 1.
    Stewart, B.W., Wild, C.P.: World cancer report 2014. Health (2017)Google Scholar
  2. 2.
    McGlynn, K.A., London, W.T.: Epidemiology and natural history of hepatocellular carcinoma. Best Pract. Res. Clin. Gastroenterol. 19(1), 3–23 (2005)CrossRefGoogle Scholar
  3. 3.
    Bruix, J., Reig, M., Sherman, M.: Evidence-based diagnosis, staging, and treatment of patients with hepatocellular carcinoma. Gastroenterology 150(4), 835–853 (2016)CrossRefGoogle Scholar
  4. 4.
    Kim, B.R., et al.: Diagnostic performance of gadoxetic acid-enhanced liver MR imaging versus multidetector CT in the detection of dysplastic nodules and early hepatocellular carcinoma. Radiology 285(1), 134–146 (2017)CrossRefGoogle Scholar
  5. 5.
    Heimbach, J.K., et al.: AASLD guidelines for the treatment of hepatocellular carcinoma. Hepatology 67(1), 358–380 (2018)CrossRefGoogle Scholar
  6. 6.
    Christ, P.F.: Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 415–423. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_48CrossRefGoogle Scholar
  7. 7.
    Vorontsov, E., Chartrand, G., Tang, A., Pal, C., Kadoury, S.: Liver lesion segmentation informed by joint liver segmentation. arXiv preprint arXiv:1707.07734
  8. 8.
    Bi, L., Kim, J., Kumar, A., Feng, D.: Automatic liver lesion detection using cascaded deep residual networks. arXiv preprint arXiv:1704.02703
  9. 9.
    Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)Google Scholar
  10. 10.
    Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_2CrossRefGoogle Scholar
  11. 11.
    Simonyan, K., Andrew, Z.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)Google Scholar
  12. 12.
    Alex, K., et al.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  13. 13.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)Google Scholar
  14. 14.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  16. 16.
    Huang, G., Liu, Z., Weinberger, K. Q., van der Maaten, L.: Densely connected convolutional networks. In: CVPR (2017)Google Scholar
  17. 17.
    Cao, G., et al.: Feature-fused SSD: fast detection for small objects. arXiv preprint arXiv:1709.05054
  18. 18.
    Li, Z., Zhou, F.: FSSD: feature fusion single shot multibox detector. arXiv preprint arXiv:1712.00960
  19. 19.
    Soler, L., et al.: 3D image reconstruction for comparison of algorithm database: a patient-specific anatomical and medical image database (2012)Google Scholar
  20. 20.
    Christ, P.F.: LiTS: liver tumor segmentation challenge. In: ISBI and MICCAI (2017)Google Scholar
  21. 21.
    Diamant, I., Goldberger, J., Klang, E., Amitai, M., Greenspan, H.: Multi-phase liver lesions classification using relevant visual words based on mutual information. In: ISBI (2015)Google Scholar
  22. 22.
    Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)Google Scholar
  23. 23.
    Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Sang-gil Lee
    • 1
  • Jae Seok Bae
    • 2
    • 3
  • Hyunjae Kim
    • 1
  • Jung Hoon Kim
    • 2
    • 3
    • 4
  • Sungroh Yoon
    • 1
    Email author
  1. 1.Electrical and Computer EngineeringSeoul National UniversitySeoulKorea
  2. 2.RadiologySeoul National University HospitalSeoulKorea
  3. 3.RadiologySeoul National University College of MedicineSeoulKorea
  4. 4.Institute of Radiation MedicineSeoul National University Medical Research CenterSeoulKorea

Personalised recommendations