Abstract
Magnetic Resonance Imaging (MRI) acceleration techniques using k-space sub-sampling (KS) can greatly improve the efficiency of MRI-based stroke diagnosis. Although Deep Neural Networks (DNN) have shown great potential on stroke lesion recognition tasks when the MR images are reconstructed from the full k-space, they are vulnerable to the lower quality MR images generated by KS. In this paper, we propose a Distributionally Robust Learning (DRL) approach to improve the performance of stroke recognition DNN models when the MR images are reconstructed from the sub-sampled k-space. For Convolutional Neural Network (CNN) and Vision Transformer (ViT)-based models, our methods improve the stroke classification AUROC and AUPRC by up to 11.91% and 9.32% on the KS-perturbed brain MR images, respectively, compared against Empirical Risk Minimization (ERM) and other baseline defensive methods. We further show that DRL models can successfully recognize the stroke cases from highly perturbed MR images where clinicians may fail, which provides a solution for improved diagnosis in an accelerated MRI setting.
This work was supported by the Rajen Kilachand Fund for Integrated Life Science and Engineering and by the NSF under grant CCF-2200052 and IIS-1914792.
Ruidi Chen contributed to this work while at Boston University, before moving to her current position at Amazon SCOT.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Supplement and source code are available at https://github.com/noc-lab/drl_mri.
References
IXI dataset. https://brain-development.org/ixi-dataset/
Akhtar, N., Mian, A.: Threat of adversarial attacks on deep learning in computer vision: a survey. IEEE Access 6, 14410–14430 (2018)
Alberts, M.J., Horner, J., Gray, L., Brazer, S.R.: Aspiration after stroke: lesion analysis by brain mri. Dysphagia 7, 170–173 (1992)
Chen, R., Hao, B., Paschalidis, I.C.: Distributionally robust multiclass classification and applications in deep image classifiers. In: ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 1–2. IEEE (2023)
Chen, R., Paschalidis, I.C.: A robust learning approach for regression models based on distributionally robust optimization. J. Mach. Learn. Res. 19(1), 517–564 (2018)
Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
Gu, Y., Piao, Z., Yoo, S.J.: SthardNet: swin transformer with HarDNet for MRI segmentation. Appl. Sci. 12(1), 468 (2022)
He, K., Chen, X., Xie, S., Li, Y., Dollár, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 16000–16009 (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770–778 (2016)
Hyun, C.M., Kim, H.P., Lee, S.M., Lee, S., Seo, J.K.: Deep learning for undersampled MRI reconstruction. Phy. Med. Bio. 63(13), 135007 (2018)
Liu, L., Chen, S., Zhang, F., Wu, F.X., Pan, Y., Wang, J.: Deep convolutional neural network for automatically segmenting acute ischemic stroke lesion in multi-modality MRI. Neural Comput. Appl. 32, 6545–6558 (2020)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)
Montalt-Tordera, J., Muthurangu, V., Hauptmann, A., Steeden, J.A.: Machine learning in magnetic resonance imaging: image reconstruction. Physica Medica 83, 79–87 (2021)
Plein, S., Ryf, S., Schwitter, J., Radjenovic, A., Boesiger, P., Kozerke, S.: Dynamic contrast-enhanced myocardial perfusion MRI accelerated with k-t sense. Magnetic Resonance in Medicine. Official J. Int. Soc. Magn. Reson. Med. 58(4), 777–785 (2007)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Stahl, R., et al.: Assessment of cartilage-dedicated sequences at ultra-high-field MRI: comparison of imaging performance and diagnostic confidence between 3.0 and 7.0 t with respect to osteoarthritis-induced changes at the knee joint. Skeletal Radiol. 38, 771–783 (2009)
Toh, K.C., Todd, M.J., Tütüncü, R.H.: SDPT3 - a MATLAB software package for semidefinite programming, version 1.3. Optim. Methods Softw. 11(1–4), 545–581 (1999)
Wang, H., Peng, H., Chang, Y., Liang, D.: A survey of GPU-based acceleration techniques in MRI reconstructions. Quant. Imaging Med. Surg. 8(2), 196 (2018)
Yushkevich, P.A., et al.: User-guided 3d active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31(3), 1116–1128 (2006)
Zbontar, J., et al.: FastMRI: an open dataset and benchmarks for accelerated MRI. arXiv preprint arXiv:1811.08839 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hao, B. et al. (2023). Distributionally Robust Image Classifiers for Stroke Diagnosis in Accelerated MRI. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14224. Springer, Cham. https://doi.org/10.1007/978-3-031-43904-9_74
Download citation
DOI: https://doi.org/10.1007/978-3-031-43904-9_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43903-2
Online ISBN: 978-3-031-43904-9
eBook Packages: Computer ScienceComputer Science (R0)
