Skip to main content
SpringerLink
Log in

Semi-Supervised Intracranial Aneurysm Segmentation from CTA Images via Weight-Perceptual Self-Ensembling Model

  • Regular Paper
  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

Segmentation of intracranial aneurysm (IA) from computed tomography angiography (CTA) images is of significant importance for quantitative assessment of IA and further surgical treatment. Manual segmentation of IA is a labor-intensive, time-consuming job and suffers from inter- and intra-observer variabilities. Training deep neural networks usually requires a large amount of labeled data, while annotating data is very time-consuming for the IA segmentation task. This paper presents a novel weight-perceptual self-ensembling model for semi-supervised IA segmentation, which employs unlabeled data by encouraging the predictions of given perturbed input samples to be consistent. Considering that the quality of consistency targets is not comparable to each other, we introduce a novel sample weight perception module to quantify the quality of different consistency targets. Our proposed module can be used to evaluate the contributions of unlabeled samples during training to force the network to focus on those well-predicted samples. We have conducted both horizontal and vertical comparisons on the clinical intracranial aneurysm CTA image dataset. Experimental results show that our proposed method can improve at least 3% Dice coefficient over the fully-supervised baseline, and at least 1.7% over other state-of-the-art semi-supervised methods.

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

References

  1. Vlak M H M, Algra A, Brandenburg R, Rinkel G J. Prevalence of unruptured intracranial aneurysms, with emphasis on sex, age, comorbidity, country, and time period: A systematic review and meta-analysis. The Lancet Neurology, 2011, 10(7): 626–636. https://doi.org/10.1016/S1474-4422(11)70109-0.

    Article  Google Scholar 

  2. Rincon F, Rossenwasser R H, Dumont A. The epidemiology of admissions of nontraumatic subarachnoid hemorrhage in the United States. Neurosurgery, 2013, 73(2): 217–223. https://doi.org/10.1227/01.neu.0000430290.93304.33.

    Article  Google Scholar 

  3. Ingall T, Asplund K, Mahonen M, Bonita R. A multinational comparison of subarachnoid hemorrhage epidemiology in the WHO MONICA stroke study. Stroke, 2000, 31(5): 1054–1061. https://doi.org/10.1161/01.str.31.5.1054.

    Article  Google Scholar 

  4. De Rooij N K, Linn F H H, Van Der Plas J A, Algra A, Rinkel G J E. Incidence of subarachnoid haemorrhage: A systematic review with emphasis on region, age, gender and time trends. Journal of Neurology, Neurosurgery & Psychiatry, 2007, 78(12): 1365–1372. https://doi.org/10.1136/jnnp.2007.117655.

    Article  Google Scholar 

  5. Franklin B, Gasco J, Uribe T, Vonritschl R H A, Hauck E. Diagnostic accuracy and inter-rater reliability of 64-multislice 3D-CTA compared to intra-arterial DSA for intracranial aneurysms. Journal of Clinical Neuroscience, 2010, 17(5): 579–583. https://doi.org/10.1016/j.jocn.2009.09.015.

    Article  Google Scholar 

  6. Colombo F, Cavedon C, Francescon P, Casentini L, Fornezza U, Castellan L, Causin F, Perini S. Three-dimensional angiography for radiosurgical treatment planning for arteriovenous malformations. Journal of Neurosurgery, 2003, 98(3): 536–543. https://doi.org/10.3171/jns.2003.98.3.0536.

    Article  Google Scholar 

  7. Lauric A, Miller E, Frisken S, Malek A M. Automated detection of intracranial aneurysms based on parent vessel 3D analysis. Medical Image Analysis, 2010, 14(2): 149–159. https://doi.org/10.1016/j.media.2009.10.005.

    Article  Google Scholar 

  8. Sichtermann T, Faron A, Sijben R, Teichert N, Freiherr J, Wiesmann M. Deep learning-based detection of intracranial aneurysms in 3D TOF-MRA. American Journal of Neuroradiology, 2019, 40(1): 25–32. https://doi.org/10.3174/ajnr.A5911.

    Article  Google Scholar 

  9. Kamnitsas K, Ledig C, Newcombe V F J, Simpson J P, Kane A D, Menon D K, Rueckert D, Glocker B. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Medical Image Analysis, 2017, 36: 61–78. https://doi.org/10.1016/j.media.2016.10.004.

    Article  Google Scholar 

  10. Shi Z, Miao C C, Schoepf U J, Savage R H, Dargis D M, Pan C W, Chai X, Li X L, Xia S, Zhang X, Gu Y, Zhang Y G, Hu B, Xu W D, Zhou C S, Luo S, Wang H, Mao L, Liang K M, Wen L L, Zhou L J, Yu Y Z, Lu G M, Zhang L J. A clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images. Nature Communications, 2020, 11(1): Article No. 6090. https://doi.org/10.1038/s41467-020-19527-w.

  11. Shahzad R, Pennig L, Goertz L, Thiele F, Kabbasch C, Schlamann M, Krischek B, Maintz D, Perkuhn M, Borggrefe J. Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning. Scientific Reports, 2020, 10(1): Article No. 21799. https://doi.org/10.1038/s41598-020-78384-1.

  12. Yang X, Xia D, Kin T, Igarashi T. Surface-based 3D deep learning framework for segmentation of intracranial aneurysms from TOF-MRA images. arXiv: 2006.16161, 2020. https://arxiv.org/abs/2006.16161v1, Apr. 2023.

  13. Laine S, Aila T. Temporal ensembling for semi-supervised learning. arXiv: 1610.02242, 2016. https://arxiv.org/abs/1610.02242, Apr. 2023.

  14. Tarvainen A, Valpola H. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Proc. the 31st International Conference on Neural Information Processing Systems, Dec. 2017, pp.1195–1204. https://doi.org/10.5555/3294771.3294885.

  15. Cui W H, Liu Y L, Li Y X, Guo M H, Li Y M, Li X L, Wang T L, Zeng X Z, Ye C Y. Semi-supervised brain lesion segmentation with an adapted mean teacher model. In Proc. the 26th International Conference on Information Processing in Medical Imaging, Jun. 2019, pp.554–565. https://doi.org/10.1007/978-3-030-20351-1_43.

  16. Perone C S, Cohen-Adad J. Deep semi-supervised segmentation with weight-averaged consistency targets. In Proc. the 8th International Workshop on Multimodal Learning for Clinical Decision Support, Sept. 2018, pp.12–19. https://doi.org/10.1007/978-3-030-00889-5_2.

  17. Sohn K, Berthelot D, Li C L, Zhang Z Z, Carlini N, Cubuk E D, Kurakin A, Zhang H, Raffel C. FixMatch: Simplifying semi-supervised learning with consistency and confidence. arXiv: 2001.07685, 2020. https://arxiv.org/abs/2001.07685, Apr. 2023.

  18. Ouali Y, Hudelot C, Tami M. Semi-supervised semantic segmentation with cross-consistency training. In Proc. the 33rd IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp.12671–12681. https://doi.org/10.1109/CVPR42600.2020.01269.

  19. Hung W C, Tsai Y H, Liou Y T, Lin Y Y, Yang M H. Adversarial learning for semi-supervised semantic segmentation. arXiv: 1802.07934, 2018. https://arxiv.org/abs/1802.07934, Apr. 2023.

  20. Huang Z J, Huang L C, Gong Y C, Huang C, Wang X G. Mask scoring R-CNN. In Proc. the 32nd IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2019, pp.6402–6411. https://doi.org/10.1109/CVPR.2019.00657.

  21. Gu L, Zheng Y Q, Bise R, Sato I, Imanishi N, Aiso S. Semi-supervised learning for biomedical image segmentation via forest oriented super pixels (voxels). In Proc. the 20th International Conference on Medical Image Computing and Computer Assisted Intervention, Sept. 2017, pp.702–710. https://doi.org/10.1007/978-3-319-66182-7_80.

  22. Bai W J, Chen C, Tarroni G, Duan J M, Guitton F, Petersen S E, Guo Y K, Matthews P M, Rueckert D. Self-supervised learning for cardiac MR image segmentation by anatomical position prediction. In Proc. the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention, Oct. 2019, pp.541–549. https://doi.org/10.1007/978-3-030-32245-8_60.

  23. Chartsias A, Joyce T, Papanastasiou G, Semple S, Williams M, Newby D, Dharmakumar R, Tsaftaris S A. Factorised spatial representation learning: Application in semi-supervised myocardial segmentation. In Proc. the 21st International Conference on Medical Image Computing and Computer Assisted Intervention, Sept. 2018, pp. 490–498. https://doi.org/10.1007/978-3-030-00934-2_55.

  24. Nie D, Gao Y Z, Wang L, Shen D G. ASDNet: Attention based semi-supervised deep networks for medical image segmentation. In Proc. the 21st International Conference on Medical Image Computing and Computer Assisted Intervention, Sept. 2018, pp.370–378. https://doi.org/10.1007/978-3-030-00937-3_43.

  25. Diaz-Pinto A, Colomer A, Naranjo V, Morales S, Xu Y W, Frangi A F. Retinal image synthesis and semi-supervised learning for glaucoma assessment. IEEE Trans. Medical Imaging, 2019, 38(9): 2211–2218. https://doi.org/10.1109/TMI.2019.2903434.

    Article  Google Scholar 

  26. Yu L Q, Wang S J, Li X M, Fu C W, Heng P A. Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. In Proc. the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention, Oct. 2019, pp.605–613. https://doi.org/10.1007/978-3-030-32245-8_67.

  27. Li X M, Yu L Q, Chen H, Fu C W, Heng P A. Semi-supervised skin lesion segmentation via transformation consistent self-ensembling model. arXiv: 1808.03887, 2018. https://arxiv.org/abs/1808.03887, Apr. 2023.

  28. Li X M, Yu L Q, Chen H, Fu C W, Xing L, Heng P A. Transformation-consistent self-ensembling model for semisupervised medical image segmentation. IEEE Trans. Neural Networks and Learning Systems, 2021, 32(2): 523–534. https://doi.org/10.1109/TNNLS.2020.2995319.

    Article  Google Scholar 

  29. Liu Q D, Yu L Q, Luo L Y, Dou Q, Heng P A. Semi-supervised medical image classification with relation-driven self-ensembling model. IEEE Trans. Medical Imaging, 2020, 39(11): 3429–3440. https://doi.org/10.1109/TMI.2020.2995518.

    Article  Google Scholar 

  30. Firouzian A, Manniesing R, Flach Z H, Risselada R, Van Kooten F, Sturkenboom M C J M, Van Der Lugt A, Niessen W J. Intracranial aneurysm segmentation in 3D CT angiography: Method and quantitative validation with and without prior noise filtering. European Journal of Radiology, 2011, 79(2): 299–304. https://doi.org/10.1016/j.ejrad.2010.02.015.

    Article  Google Scholar 

  31. Wang Y, Zhang Y, Navarro L, Eker O F, Corredor Jerez R A, Chen Y, Zhu Y M, Courbebaisse G. Multilevel segmentation of intracranial aneurysms in CT angiography images. Medical Physics, 2016, 43(4): 1777–1786. https://doi.org/10.1118/1.4943375.

    Article  Google Scholar 

  32. Milletari F, Navab N, Ahmadi S A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In Proc. the 4th International Conference on 3D Vision (3DV), Oct. 2016, pp.565–571. https://doi.org/10.1109/3DV.2016.79.

  33. Çiçek Ö, Abdulkadir A, Lienkamp S S, Brox T, Ronneberger O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Proc. the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, Oct. 2016, pp.424–432. https://doi.org/10.1007/978-3-319-46723-8_49.

  34. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z M, Gimelshein N, Antiga L, Desmaison A, Köpf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J J, Chintala S. PyTorch: An imperative style, high-performance deep learning library. arXiv: 1912.01703, 2019. https://arxiv.org/abs/1912.01703, Apr. 2023.

  35. Zhang Y Z, Yang L, Chen J X, Fredericksen M, Hughes D P, Chen D Z. Deep adversarial networks for biomedical image segmentation utilizing unannotated images. In Proc. the 20th International Conference on Medical Image Computing and Computer Assisted Intervention, Sept. 2017, pp.408–416. https://doi.org/10.1007/978-3-319-66179-7_47.

  36. French G, Laine S, Aila T, Mackiewicz M, Finlayson G. Semi-supervised semantic segmentation needs strong, varied perturbations. arXiv: 1906.01916, 2019. https://arxiv.org/abs/1906.01916, Apr. 2023.

Download references

Author information

Authors and Affiliations

  1. Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China

    Cai-Zi Li, Rui-Qiang Liu, Jun-Ming Fan & Wei-Xin Si

  2. University of Chinese Academy of Sciences, Beijing, 100049, China

    Cai-Zi Li & Rui-Qiang Liu

  3. Shantou University, Shantou, 515063, China

    Huan-Xin Zhong

  4. Shenzhen Second People’s Hospital, Shenzhen, 518035, China

    Huan-Xin Zhong & Meng Zhang

  5. Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, 999077, China

    Pheng-Ann Heng

Authors
  1. Cai-Zi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rui-Qiang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Huan-Xin Zhong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jun-Ming Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wei-Xin Si
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Meng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Pheng-Ann Heng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Wei-Xin Si or Meng Zhang.

Additional information

Wei-Xin Si contributed the original idea and participated in polishing the full paper, and Meng Zhang provided funds for this research and offered the labelled dataset. They both guided the work of the paper and contributed equally.

Supplementary Information

ESM 1

(PDF 324 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, CZ., Liu, RQ., Zhong, HX. et al. Semi-Supervised Intracranial Aneurysm Segmentation from CTA Images via Weight-Perceptual Self-Ensembling Model. J. Comput. Sci. Technol. 38, 674–685 (2023). https://doi.org/10.1007/s11390-022-0870-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11390-022-0870-1

Keywords

Search

Navigation