Abstract
Head movement during long scan sessions degrades the quality of reconstruction in positron emission tomography (PET) and introduces artifacts, which limits clinical diagnosis and treatment. Recent deep learning-based motion correction work utilized raw PET list-mode data and hardware motion tracking (HMT) to learn head motion in a supervised manner. However, motion prediction results were not robust to testing subjects outside the training data domain. In this paper, we integrate a cross-attention mechanism into the supervised deep learning network to improve motion correction across test subjects. Specifically, cross-attention learns the spatial correspondence between the reference images and moving images to explicitly focus the model on the most correlative inherent information - the head region the motion correction. We validate our approach on brain PET data from two different scanners: HRRT without time of flight (ToF) and mCT with ToF. Compared with traditional and deep learning benchmarks, our network improved the performance of motion correction by 58% and 26% in translation and rotation, respectively, in multi-subject testing in HRRT studies. In mCT studies, our approach improved performance by 66% and 64% for translation and rotation, respectively. Our results demonstrate that cross-attention has the potential to improve the quality of brain PET image reconstruction without the dependence on HMT. All code will be released on GitHub: https://github.com/OnofreyLab/dl_hmc_attention_mlcn2023.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahn, S.S., et al.: Co-attention spatial transformer network for unsupervised motion tracking and cardiac strain analysis in 3D echocardiography. Med. Image Anal. 84, 102711 (2023)
Cai, Z., Xin, J., Liu, S., Wu, J., Zheng, N.: Architecture and factor design of fully convolutional neural networks for retinal vessel segmentation. In: 2018 Chinese Automation Congress (CAC), pp. 3076–3080. IEEE (2018)
Cai, Z., Xin, J., Shi, P., Wu, J., Zheng, N.: DSTUnet: Unet with efficient dense Swin transformer pathway for medical image segmentation. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp. 1–5. IEEE (2022)
Cai, Z., Xin, J., Shi, P., Zhou, S., Wu, J., Zheng, N.: Meta pixel loss correction for medical image segmentation with noisy labels. In: Zamzmi, G., Antani, S., Bagci, U., Linguraru, M.G., Rajaraman, S., Xue, Z. (eds.) Medical Image Learning with Limited and Noisy Data. MILLanD 2022. LNCS, vol. 13559, pp. 32–41. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16760-7_4
Cai, Z., Xin, J., Wu, J., Liu, S., Zuo, W., Zheng, N.: Triple multi-scale adversarial learning with self-attention and quality loss for unpaired fundus fluorescein angiography synthesis. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 1592–1595. IEEE (2020)
Carson, R.E., Barker, W.C., Liow, J.S., Johnson, C.A.: Design of a motion-compensation OSEM list-mode algorithm for resolution-recovery reconstruction for the HRRT. In: 2003 IEEE Nuclear Science Symposium. Conference Record (IEEE CAT. No. 03CH37515), vol. 5, pp. 3281–3285. IEEE (2003)
Chen, X., et al.: Dual-branch squeeze-fusion-excitation module for cross-modality registration of cardiac Spect and CT. In: Wang, L., Dou, ., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention. MICCAI 2022. LNCS, vol. 13436 pp. 46–55. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16446-0_5
Fischl, B.: FreeSurfer. Neuroimage 62(2), 774–781 (2012)
Jin, X., Mulnix, T., Gallezot, J.D., Carson, R.E.: Evaluation of motion correction methods in human brain pet imaging-a simulation study based on human motion data. Med. Phys. 40(10), 102503 (2013)
Kuang, Z., et al.: Progress of SIAT bPET: an MRI compatible brain PET scanner with high spatial resolution and high sensitivity (2022)
Kuang, Z., et al.: Design and performance of SIAT aPET: a uniform high-resolution small animal pet scanner using dual-ended readout detectors. Phys. Med. Biol. 65(23), 235013 (2020)
Kyme, A.Z., Fulton, R.R.: Motion estimation and correction in SPECT PET and CT. Phys. Med. Biol. 66(18), 18TR02 (2021)
Lieffrig, E.V., et al.: Multi-task deep learning and uncertainty estimation for PET head motion correction. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI 2023), pp. 1–4, April 2023
Lu, Y., et al.: Data-Driven motion detection and event-by-event correction for brain PET: comparison with Vicra. J. Nucl. Med. 61(9), 1397–1403 (2020)
Papademetris, X., Jackowski, M.P., Rajeevan, N., DiStasio, M., Okuda, H., Constable, R.T., Staib, L.H.: Bioimage suite: an integrated medical image analysis suite: an update. Insight J. 2006, 209 (2006)
Revilla, E.M., et al.: Adaptive data-driven motion detection and optimized correction for brain pet. Neuroimage 252, 119031 (2022)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Spangler-Bickell, M.G., Deller, T.W., Bettinardi, V., Jansen, F.: Ultra-fast list-mode reconstruction of short pet frames and example applications. J. Nucl. Med. 62(2), 287–292 (2021)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
You, C., Dai, W., Min, Y., Staib, L., Duncan, J.S.: Implicit anatomical rendering for medical image segmentation with stochastic experts. arXiv preprint arXiv:2304.03209 (2023)
You, C., et al.: Incremental learning meets transfer learning: application to multi-site prostate MRI segmentation. In: Albarqouni, S., et al. (eds.) Distributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global Health. DeCaF FAIR 2022 2022. LNCS, vol. 13573, pp. 3–16. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-18523-6_1
You, C., et al.: Class-aware adversarial transformers for medical image segmentation. In: Advances in Neural Information Processing Systems (2022)
Zeng, T., et al.: A GPU-accelerated fully 3d Osem image reconstruction for a high-resolution small animal pet scanner using dual-ended readout detectors. Phys. Med. Biol. 65(24), 245007 (2020)
Zeng, T., et al.: Supervised deep learning for head motion correction in pet. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention-MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part IV, pp. 194–203. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16440-8_19
Zeng, T., et al.: Design and system evaluation of a dual-panel portable pet (DP-PET). EJNMMI Phys. 8(1), 1–16 (2021)
Acknowledgements
This work was supported by the National Key Research and Development Program of China 2017YFA0700800 and the National Institute of Health (NIH) R21 EB028954.
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
Cai, Z. et al. (2023). Cross-Attention for Improved Motion Correction in Brain PET. In: Abdulkadir, A., et al. Machine Learning in Clinical Neuroimaging. MLCN 2023. Lecture Notes in Computer Science, vol 14312. Springer, Cham. https://doi.org/10.1007/978-3-031-44858-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-44858-4_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44857-7
Online ISBN: 978-3-031-44858-4
eBook Packages: Computer ScienceComputer Science (R0)