Abstract
Catheter Digital Subtraction Angiography (DSA) is markedly degraded by all voluntary, respiratory, or cardiac motion artifact that occurs during the exam acquisition. Prior efforts directed toward improving DSA images with machine learning have focused on extracting vessels from individual, isolated 2D angiographic frames. In this work, we introduce improved 2D + t deep learning models that leverage the rich temporal information in angiographic timeseries. A total of 516 cerebral angiograms were collected with 8784 individual series. We utilized feature-based computer vision algorithms to separate the database into “motionless” and “motion-degraded” subsets. Motion measured from the “motion degraded” category was then used to create a realistic, but synthetic, motion-augmented dataset suitable for training 2D U-Net, 3D U-Net, SegResNet, and UNETR models. Quantitative results on a hold-out test set demonstrate that the 3D U-Net outperforms competing 2D U-Net architectures, with substantially reduced motion artifacts when compared to DSA. In comparison to single-frame 2D U-Net, the 3D U-Net utilizing 16 input frames achieves a reduced RMSE (35.77 ± 15.02 vs 23.14 ± 9.56, p < 0.0001; mean ± std dev) and an improved Multi-Scale SSIM (0.86 ± 0.08 vs 0.93 ± 0.05, p < 0.0001). The 3D U-Net also performs favorably in comparison to alternative convolutional and transformer-based architectures (U-Net RMSE 23.20 ± 7.55 vs SegResNet 23.99 ± 7.81, p < 0.0001, and UNETR 25.42 ± 7.79, p < 0.0001, mean ± std dev). These results demonstrate that multi-frame temporal information can boost performance of motion-resistant Background Subtraction Deep Learning algorithms, and we have presented a neuroangiography domain-specific synthetic affine motion augmentation pipeline that can be utilized to generate suitable datasets for supervised training of 3D (2d + t) architectures.
Similar content being viewed by others
Data Availability
Due to the risk of an inadvertent leak of Private Health Information, our Institutional Review Board has not allowed us to make the raw angiographic data publicly available
Abbreviations
- RMSE:
-
Root Mean Squared Error
- SSIM:
-
Structural Similarity Index Measure
- MS-SSIM:
-
Multi-Scale Structural Similarity Index Measure
- ORB:
-
Oriented FAST and Rotated BRIEF
- DSA:
-
Digital Subtraction Angiography
- BSA:
-
Background Subtraction Angiography
- GAN:
-
Generative Adversarial Network
- NIFTI:
-
Neuroimaging Informatics Technology Initiative
- RELU:
-
Rectified Linear Unit
References
Pelz, D.M., A.J. Fox, and F. Vinuela, Digital subtraction angiography: current clinical applications. Stroke, 1985. 16(3): p. 528-536.
Crummy, A.B., C.M. Strother, and C.A. Mistretta, The history of digital subtraction angiography. J Vasc Interv Radiol, 2018. 29(8): p. 1138-1141.
Ronneberger, O., P. Fischer, and T. Brox U-Net: convolutional networks for biomedical image segmentation. 2015. http://arxiv.org/abs/1505.04597.
Çiçek, Ö., et al., 3D U-Net: learning dense volumetric segmentation from sparse annotation. ArXiv, 2016. https://arxiv.org/abs/1606.06650.
Ellis, D. and M. Aizenberg, Trialing U-Net training modifications for segmenting gliomas using open source deep learning framework. 2021. p. 40–49.
Isensee, F., et al. Brain tumor segmentation and radiomics survival prediction: contribution to the BRATS 2017 challenge. in Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries. 2018. Cham: Springer International Publishing.
Isensee, F., et al., nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature Methods, 2021. 18(2): p. 203-211.
Kayalibay, B., G. Jensen, and P.V.D. Smagt, CNN-based segmentation of medical imaging data. ArXiv, 2017. https://arxiv.org/abs/1701.03056.
Wu, C., Y. Zou, and Z. Yang. U-GAN: generative adversarial networks with U-Net for retinal vessel segmentation. in 2019 14th International Conference on Computer Science & Education (ICCSE). 2019.
Dorta, G., et al. The GAN that warped: semantic attribute editing with unpaired data. in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020.
Isola, P., et al. Image-to-image translation with conditional adversarial networks. 2016. http://arxiv.org/abs/1611.07004.
Dong, X., et al., Automatic multiorgan segmentation in thorax CT images using U-net-GAN. Med Phys, 2019. 46(5): p. 2157-2168.
Gao, Y., et al., Deep learning-based digital subtraction angiography image generation. Int J Comput Assist Radiol Surg, 2019. 14(10): p. 1775-1784.
Ueda, D., et al., Deep learning-based angiogram generation model for cerebral angiography without misregistration artifacts. Radiology, 2021. 299(3): p. 675-681.
Yonezawa, H., et al., Maskless 2-dimensional digital subtraction angiography generation model for abdominal vasculature using deep learning. Journal of Vascular and Interventional Radiology, 2022. 33(7): p. 845-851. e8.
Wang, L., et al., Coronary artery segmentation in angiographic videos utilizing spatial-temporal information. BMC Med Imaging, 2020. 20(1): p. 110.
Hao, D., et al., Sequential vessel segmentation via deep channel attention network. Neural Netw, 2020. 128: p. 172-187.
Rublee, E., et al. An efficient alternative to SIFT or SURF. in Proceedings of international conference on computer vision.
Lowe, D.G., Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004. 60(2): p. 91-110.
Myronenko, A. 3D MRI brain tumor segmentation using autoencoder regularization. in Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4. 2019. Springer.
Hatamizadeh, A., et al. Unetr: transformers for 3d medical image segmentation. in Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2022.
Dosovitskiy, A., et al., An image is worth 16x16 words: transformers for image recognition at scale. 2020.
Xiao, T., et al., Early convolutions help transformers see better. Advances in Neural Information Processing Systems, 2021. 34: p. 30392-30400.
Wang, Z., et al., Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process, 2004. 13(4): p. 600-12.
Wang, Z., E.P. Simoncelli, and A.C. Bovik. Multiscale structural similarity for image quality assessment. in The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003. 2003.
Zhang, L., et al., FSIM: a feature similarity index for image quality assessment. IEEE Trans Image Process, 2011. 20(8): p. 2378-86.
Huang, Z., et al., Revisiting nnU-Net for Iterative pseudo labeling and efficient sliding window inference, in Fast and low-resource semi-supervised abdominal organ segmentation: MICCAI 2022 Challenge, FLARE 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings. 2023, Springer. p. 178-189.
Baid, U., et al., The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv preprint http://arxiv.org/abs/2107.02314, 2021.
Crabb, B.T., et al., Deep learning subtraction angiography: improved generalizability with transfer learning. (1535–7732 (Electronic)).
Meijering, E.H., K.J. Zuiderveld, and M.A. Viergever, Image registration for digital subtraction angiography. International Journal of Computer Vision, 1999. 31: p. 227-246.
Song, S., et al., Inter/intra-frame constrained vascular segmentation in X-ray angiographic image sequence. BMC Medical Informatics and Decision Making, 2019. 19(6): p. 270.
Nejati, M., S. Sadri, and R. Amirfattahi, Nonrigid image registration in digital subtraction angiography using multilevel B-spline. BioMed research international, 2013. 2013: p. 236315.
Jaubert, O., et al., Real-time deep artifact suppression using recurrent U-Nets for low-latency cardiac MRI. Magnetic Resonance in Medicine, 2021. 86(4): p. 1904-1916.
Azizmohammadi, F., et al., Model-free cardiorespiratory motion prediction from X-ray angiography sequence with LSTM network. Annu Int Conf IEEE Eng Med Biol Soc, 2019. 2019: p. 7014-7018.
Funding
We are grateful for funding and support from the American Heart Association Career Development Award 933248, from the NVIDIA Academic Hardware Grant and Applied Research Accelerator Program, and from the NIH National Heart, Lung, and Blood Institute under Award Number 1R41HL164298.
Author information
Authors and Affiliations
Contributions
All authors contributed to study design, manuscript preparation, and editing. Angiographic data collection and deidentification were performed by DRC. Software development and data analysis were performed by DRC and LC.
Corresponding author
Ethics declarations
Ethics Approval
This work was performed on retrospective data obtained and managed in compliance with the Northwestern University Institutional Review Board (STU00212923).
Consent to Participate
Informed consent was waived. Consent to participate was not applicable based on Institutional Review Board determinations.
Consent for Publication
Consent for publication was not applicable based on Institutional Review Board determinations.
Competing Interests
Portions of the work described in this article have been included in a related patent filed by Northwestern University (PCT/US2021/037936), with DR Cantrell, SA Ansari, and L Cho listed as co-inventors. DR Cantrell, SA Ansari, and L Cho are founders and have shares in Cleavoya, LLC, which was awarded a Phase 1 Small Business Technology Transfer Grant from the NIH (1R41HL164298) to further develop portions of the work described in this article.
Disclaimer
The content of this report is solely the responsibility of the authors and does not necessarily represent the official views of the funding agencies.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Supplementary file1 (AVI 31700 KB)
Supplementary file2 (MP4 14141 KB)
Supplementary file3 (AVI 35390 KB)
Supplementary file4 (AVI 32493 KB)
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cantrell, D.R., Cho, L., Zhou, C. et al. Background Subtraction Angiography with Deep Learning Using Multi-frame Spatiotemporal Angiographic Input. J Digit Imaging. Inform. med. 37, 134–144 (2024). https://doi.org/10.1007/s10278-023-00921-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-023-00921-x