Skip to main content
SpringerLink
Log in

Conditional Training with Bounding Map for Universal Lesion Detection

  • Conference paper
  • First Online:
Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 (MICCAI 2021)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12905))

Abstract

Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis. Promising ULD results have been reported by coarse-to-fine two-stage detection approaches, but such two-stage ULD methods still suffer from issues like imbalance of positive v.s. negative anchors during object proposal and insufficient supervision problem during localization regression and classification of the region of interest (RoI) proposals. While leveraging pseudo segmentation masks such as bounding map (BM) can reduce the above issues to some degree, it is still an open problem to effectively handle the diverse lesion shapes and sizes in ULD. In this paper we propose a BM-based conditional training for two-stage ULD, which can (i) reduce positive vs. negative anchor imbalance via a BM-based conditioning (BMC) mechanism for anchor sampling instead of traditional IoU-based rule; and (ii) adaptively compute size-adaptive BM (ABM) from lesion bounding-box, which is used for improving lesion localization accuracy via ABM-supervised segmentation. Experiments with four state-of-the-art methods show that the proposed approach can bring an almost free detection accuracy improvement without requiring expensive lesion mask annotations.

This research was supported in part by the Natural Science Foundation of China (grant 61732004), Youth Innovation Promotion Association CAS (grant 2018135) and Alibaba Group through Alibaba Innovative Research Program.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 99.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 129.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Zlocha, M., Dou, Q., Glocker, B.: Improving RetinaNet for CT lesion detection with dense masks from weak RECIST labels. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 402–410. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_45

    Chapter  Google Scholar 

  2. Tao, Q., Ge, Z., Cai, J., Yin, J., See, S.: Improving deep lesion detection using 3D contextual and spatial attention. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 185–193. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_21

    Chapter  Google Scholar 

  3. Zhang, N., et al.: 3d anchor-free lesion detector on computed tomography scans. arXiv:1908.11324 (2019)

  4. Zhang, N., Cao, Y., Liu, B., Luo, Y.: 3d aggregated faster R-CNN for general lesion detection. arXiv:2001.11071 (2020)

  5. Tang, Y., Yan, K., Tang, Y., Liu, J., Xiao, J., Summers, R.M.: Uldor: a universal lesion detector for ct scans with pseudo masks and hard negative example mining. In: IEEE ISBI, pp. 833–836 (2019)

    Google Scholar 

  6. Yan, K., Bagheri, M., Summers, R.M.: 3D context enhanced region-based convolutional neural network for end-to-end lesion detection. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 511–519. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_58

    Chapter  Google Scholar 

  7. Li, Z., Zhang, S., Zhang, J., Huang, K., Wang, Y., Yu, Y.: MVP-Net: multi-view FPN with position-aware attention for deep universal lesion detection. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 13–21. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_2

    Chapter  Google Scholar 

  8. Yan, K., et al.: MULAN: multitask universal lesion analysis network for joint lesion detection, tagging, and segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 194–202. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_22

    Chapter  Google Scholar 

  9. Yang, J., et al.: AlignShift: bridging the gap of imaging thickness in 3D anisotropic volumes. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 562–572. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_55

    Chapter  Google Scholar 

  10. Cai, J., et al.: Deep volumetric universal lesion detection using light-weight pseudo 3D convolution and surface point regression. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 3–13. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_1

    Chapter  Google Scholar 

  11. Li, H., Han, H., Zhou, S.K.: Bounding maps for universal lesion detection. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 417–428. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_41

    Chapter  Google Scholar 

  12. Zhang, S., et al.: Revisiting 3D context modeling with supervised pre-training for universal lesion detection in CT slices. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 542–551. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_53

    Chapter  Google Scholar 

  13. Yan, K., et al.: Learning from multiple datasets with heterogeneous and partial labels for universal lesion detection in CT. IEEE Trans. Med. Imaging (2020)

    Google Scholar 

  14. Li, H., et al.: High-resolution chest x-ray bone suppression using unpaired CT structural priors. IEEE Trans. Med. Imaging 39(10), 3053–3063 (2020)

    Google Scholar 

  15. Liao, F., Liang, M., Li, Z., Hu, X., Song, S.: Evaluate the malignancy of pulmonary nodules using the 3-d deep leaky noisy-or network. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3484–3495 (2019)

    Article  Google Scholar 

  16. Lin, Y., et al.: Automated pulmonary embolism detection from CTPA images using an end-to-end convolutional neural network. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 280–288. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_31

    Chapter  Google Scholar 

  17. Wang, X., Han, S., Chen, Y., Gao, D., Vasconcelos, N.: Volumetric attention for 3D medical image segmentation and detection. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 175–184. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_20

    Chapter  Google Scholar 

  18. Astaraki, M., Toma-Dasu, I., Smedby, Ö., Wang, C.: Normal appearance autoencoder for lung cancer detection and segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 249–256. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_28

    Chapter  Google Scholar 

  19. Tang, H., Zhang, C., Xie, X.: NoduleNet: decoupled false positive reduction for pulmonary nodule detection and segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 266–274. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_30

    Chapter  Google Scholar 

  20. Shao, Q., Gong, L., Ma, K., Liu, H., Zheng, Y.: Attentive CT lesion detection using deep pyramid inference with multi-scale booster. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 301–309. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_34

    Chapter  Google Scholar 

  21. Liu, J., Cao, L., Akin, O., Tian, Y.: 3DFPN-HS\(^2\): 3D feature pyramid network based high sensitivity and specificity pulmonary nodule detection. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 513–521. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_57

    Chapter  Google Scholar 

  22. Boot, T., Irshad, H.: Diagnostic assessment of deep learning algorithms for detection and segmentation of lesion in mammographic images. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 56–65. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_6

    Chapter  Google Scholar 

  23. Yu, X., et al.: Deep attentive panoptic model for prostate cancer detection using biparametric MRI scans. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 594–604. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_58

    Chapter  Google Scholar 

  24. Yao, Q., Xiao, L., Liu, P., Zhou, S.K.: Label-free segmentation of covid-19 lesions in lung CT. IEEE Trans. Med. Imaging (2021)

    Google Scholar 

  25. Yao, Q., He, Z., Han, H., Zhou, S.K.: Miss the point: targeted adversarial attack on multiple landmark detection. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12264, pp. 692–702. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59719-1_67

    Chapter  Google Scholar 

  26. Yao, Q., Quan, Q., Xiao, L., Zhou, S.K.: One-shot medical landmark detection. arXiv preprint arXiv:2103.04527 (2021)

  27. Zhou, S.K., et al.: A review of deep learning in medical imaging: imaging traits, technology trends, case studies with progress highlights, and future promises. In: Proceedings of the IEEE (2021)

    Google Scholar 

  28. Zhou, S.K., Rueckert, D., Fichtinger, G.:Handbook of Medical Image Computing and Computer Assisted Intervention. Academic Press, London (2019)

    Google Scholar 

  29. He, K., Gkioxari, G., Dollár, P., Girshick, R.: MASK R-CNN. In: IEEE ICCV, pp. 2961–2969 (2017)

    Google Scholar 

  30. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)

    Google Scholar 

  31. Oksuz, K., Cam, B.C., Kalkan, S., Akbas, E.: Imbalance problems in object detection: a review. Trans. Pattern Anal. Mach. Intell. 43(10), 3388–3415 (2020)

    Google Scholar 

  32. Yan, K., et al.: Deep lesion graphs in the wild: relationship learning and organization of significant radiology image findings in a diverse large-scale lesion database. In: IEEE CVPR, pp. 9261–9270 (2018)

    Google Scholar 

  33. Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv:1904.07850 (2019)

  34. Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: IEEE ICCV, pp. 9627–9636 (2019)

    Google Scholar 

  35. Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)

Download references

Author information

Authors and Affiliations

  1. Medical Imaging, Robotics, Analytic Computing Laboratory/Engineering (MIRACLE), School of Biomedical Engineering & Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China

    Han Li & S. Kevin Zhou

  2. Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China

    Han Li, Long Chen, Hu Han & S. Kevin Zhou

  3. School of Electronic, Electrical and Communication Engineering, University of the Chinese Academy of Science, Beijing, China

    Long Chen

  4. Healthcare Intelligence, AIC, DAMO Academy, Alibaba Group, Hangzhou, China

    Ying Chi

Authors
  1. Han Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Long Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hu Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ying Chi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. S. Kevin Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hu Han .

Editor information

Editors and Affiliations

  1. Erasmus MC - University Medical Center Rotterdam, Rotterdam, The Netherlands

    Marleen de Bruijne

  2. University of Basel, Allschwil, Switzerland

    Philippe C. Cattin

  3. Inria Nancy Grand Est, Villers-lès-Nancy, France

    Stéphane Cotin

  4. ICube, Université de Strasbourg, CNRS, Strasbourg, France

    Nicolas Padoy

  5. National Center for Tumor Diseases (NCT/UCC), Dresden, Germany

    Stefanie Speidel

  6. Tencent Jarvis Lab, Shenzhen, China

    Yefeng Zheng

  7. ICube, Université de Strasbourg, CNRS, Strasbourg, France

    Caroline Essert

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 298 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Li, H., Chen, L., Han, H., Chi, Y., Zhou, S.K. (2021). Conditional Training with Bounding Map for Universal Lesion Detection. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12905. Springer, Cham. https://doi.org/10.1007/978-3-030-87240-3_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-87240-3_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-87239-7

  • Online ISBN: 978-3-030-87240-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation