Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 149 tok/s
Gemini 2.5 Pro 48 tok/s Pro
GPT-5 Medium 35 tok/s Pro
GPT-5 High 35 tok/s Pro
GPT-4o 92 tok/s Pro
Kimi K2 196 tok/s Pro
GPT OSS 120B 425 tok/s Pro
Claude Sonnet 4.5 35 tok/s Pro
2000 character limit reached

Generating Synthetic Computed Tomography for Radiotherapy: SynthRAD2023 Challenge Report (2403.08447v3)

Published 13 Mar 2024 in physics.med-ph

Abstract: Radiation therapy plays a crucial role in cancer treatment, necessitating precise delivery of radiation to tumors while sparing healthy tissues over multiple days. Computed tomography (CT) is integral for treatment planning, offering electron density data crucial for accurate dose calculations. However, accurately representing patient anatomy is challenging, especially in adaptive radiotherapy, where CT is not acquired daily. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast. Still, it lacks electron density information while cone beam CT (CBCT) lacks direct electron density calibration and is mainly used for patient positioning. Adopting MRI-only or CBCT-based adaptive radiotherapy eliminates the need for CT planning but presents challenges. Synthetic CT (sCT) generation techniques aim to address these challenges by using image synthesis to bridge the gap between MRI, CBCT, and CT. The SynthRAD2023 challenge was organized to compare synthetic CT generation methods using multi-center ground truth data from 1080 patients, divided into two tasks: 1) MRI-to-CT and 2) CBCT-to-CT. The evaluation included image similarity and dose-based metrics from proton and photon plans. The challenge attracted significant participation, with 617 registrations and 22/17 valid submissions for tasks 1/2. Top-performing teams achieved high structural similarity indices (>0.87/0.90) and gamma pass rates for photon (>98.1%/99.0%) and proton (>97.3%/97.0%) plans. However, no significant correlation was found between image similarity metrics and dose accuracy, emphasizing the need for dose evaluation when assessing the clinical applicability of sCT. SynthRAD2023 facilitated the investigation and benchmarking of sCT generation techniques, providing insights for developing MRI-only and CBCT-based adaptive radiotherapy.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (92)
  1. Dosimetric Impact of MRI Distortions: A Study on Head and Neck Cancers. International Journal of Radiation Oncology*Biology*Physics 103, 994–1003. doi:10.1016/j.ijrobp.2018.11.037.
  2. Making on-line adaptive radiotherapy possible using artificial intelligence and machine learning for efficient daily re-planning. Med Phys Intl J 8.
  3. Validation of dose distribution computation on sct images generated from mri scans by philips mrcat. Reports of Practical Oncology and Radiotherapy 24, 245–250.
  4. Monai: An open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701 .
  5. Contemporary radiotherapy: present and future. The Lancet 398, 171–184. doi:10.1016/s0140-6736(21)00233-6.
  6. ShuffleUNet: Super resolution of diffusion-weighted MRIs using deep learning, in: 2021 29th European Signal Processing Conference (EUSIPCO), IEEE. pp. 940–944.
  7. Glfa-net: A hybrid network for mr-to-ct synthesis via global and local feature aggregation, in: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp. 1–5. doi:10.1109/ISBI53787.2023.10230486.
  8. Mri only radiotherapy planning using the transfer function estimation algorithm.
  9. Deep learning based synthesis of mri, ct and pet: Review and analysis. Medical Image Analysis , 103046.
  10. An image is worth 16x16 words: Transformers for image recognition at scale. doi:10.48550/ARXIV.2010.11929.
  11. A review of substitute ct generation for mri-only radiation therapy. Radiation Oncology 12. URL: http://dx.doi.org/10.1186/s13014-016-0747-y, doi:10.1186/s13014-016-0747-y.
  12. Taming transformers for high-resolution image synthesis, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 12873–12883.
  13. IMRT commissioning: multiple institution planning and dosimetry comparisons, a report from AAPM Task Group 119. Medical physics 36, 5359–5373. doi:10.1118/1.3238104.
  14. Temporal bone ct synthesis for mr-only cochlear implant preoperative planning, in: Medical Imaging 2023: Image-Guided Procedures, Robotic Interventions, and Modeling, SPIE. pp. 358–363.
  15. Deep learning–based MR-to-CT synthesis: the influence of varying gradient echo–based MR images as input channels. Magnetic resonance in medicine 83, 1429–1441.
  16. Stereo-correlation and noise-distribution aware ResVoxGAN for dense slices reconstruction and noise reduction in thick low-dose CT, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2019, Springer. pp. 328–338.
  17. Generative Adversarial Nets, in: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (Eds.), Advances in Neural Information Processing Systems, Curran Associates, Inc. URL: https://proceedings.neurips.cc/paper_files/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf.
  18. State of the art on dose prescription, reporting and recording in intensity-modulated radiation therapy (icru report no. 83). Cancer/Radiothérapie 15, 555–559. doi:10.1016/j.canrad.2011.04.003.
  19. NRG oncology updated international consensus atlas on pelvic lymph node volumes for intact and postoperative prostate cancer. International Journal of Radiation Oncology* Biology* Physics 109, 174–185.
  20. Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images, in: International MICCAI Brainlesion Workshop, Springer. pp. 272–284.
  21. Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp. 16000–16009.
  22. Deep Residual Learning for Image Recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  23. Denoising Diffusion Probabilistic Models. arXiv preprint arxiv:2006.11239 .
  24. A simple sequentially rejective multiple test procedure. Scandinavian journal of statistics , 65–70.
  25. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18, 203–211.
  26. Automated design of deep learning methods for biomedical image segmentation. arXiv preprint arXiv:1904.08128 .
  27. Image-to-Image Translation with Conditional Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 1125–1134.
  28. Perceptual losses for real-time style transfer and super-resolution, in: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14, Springer. pp. 694–711.
  29. Msg-gan: Multi-scale gradients for generative adversarial networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  30. A style-based generator architecture for generative adversarial networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  31. A new measure of rank correlation. Biometrika 30, 81–93. doi:10.1093/biomet/30.1-2.81.
  32. Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region. Physics in Medicine & Biology 63, 145007. doi:10.1088/1361-6560/aacb65.
  33. Elastix: a toolbox for intensity-based medical image registration. IEEE Transactions on Medical Imaging 29, 196–205. doi:10.1109/TMI.2009.2035616.
  34. A criterion for the reliable use of MRI-only radiotherapy. Radiation Oncology 9. doi:10.1186/1748-717x-9-16.
  35. Artifacts in magnetic resonance imaging. Polish journal of radiology 80, 93.
  36. CT to MR registration of complex deformations in the knee joint through dual quaternion interpolation of rigid transforms. Physics in Medicine & Biology 66, 175024.
  37. MR-only simulation for radiotherapy planning – Whitepaper: Philips MRCAT for prostate dose calculations using only MRI data. White Paper. Philips.
  38. MR guidance in radiotherapy. Physics in Medicine and Biology 59, R349–R369. doi:10.1088/0031-9155/59/21/r349.
  39. Radiation dose constraints for organs at risk in neuro-oncology; the European Particle Therapy Network consensus. Radiotherapy and Oncology 128, 26–36.
  40. SwinIR: Image Restoration Using Swin Transformer, in: Proceedings of the IEEE/CVF international conference on computer vision, pp. 1833–1844.
  41. Moddrop++: A dynamic filter network with intra-subject co-training for multiple sclerosis lesion segmentation with missing modalities, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2022, Springer. pp. 444–453.
  42. Review of cone beam computed tomography based online adaptive radiotherapy: Current trend and future direction. Radiation Oncology 18, 144.
  43. Synthetic CT skull generation for transcranial MR imaging–guided focused ultrasound interventions with conditional adversarial networks, in: Medical Imaging 2022: Image-Guided Procedures, Robotic Interventions, and Modeling, SPIE. pp. 135–143. doi:10.1117/12.2612946.
  44. Deep learning to segment pelvic bones: large-scale CT datasets and baseline models. International Journal of Computer Assisted Radiology and Surgery 16, 749–756.
  45. Swin transformer v2: Scaling up capacity and resolution, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 12009–12019.
  46. Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE/CVF international conference on computer vision, pp. 10012–10022.
  47. A convnet for the 2020s, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11976–11986.
  48. A technique for the quantitative evaluation of dose distributions. Medical physics 25, 656–661.
  49. Edge-preserving mri image synthesis via adversarial network with iterative multi-scale fusion. Neurocomputing 452, 63–77.
  50. On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics 18, 50–60. doi:10.1214/aoms/1177730491.
  51. Least squares generative adversarial networks, in: Proceedings of the IEEE international conference on computer vision, pp. 2794–2802.
  52. Deep learning-based synthetic CT generation for paediatric brain MR-only photon and proton radiotherapy. Radiotherapy and Oncology 153, 197–204. doi:10.1016/j.radonc.2020.09.029.
  53. Feasibility of MR-only proton dose calculations for prostate cancer radiotherapy using a commercial pseudo-CT generation method. Physics in Medicine & Biology 62, 9159.
  54. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 .
  55. The rationale for fractionation in radiotherapy. Clinical Journal of Oncology Nursing 17, 412–417. doi:10.1188/13.cjon.412-417.
  56. Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 .
  57. Adaptive Radiotherapy for Prostate Cancer Using Kilovoltage Cone-Beam Computed Tomography: First Clinical Results. International Journal of Radiation Oncology*Biology*Physics 70, 75–82. doi:10.1016/j.ijrobp.2007.05.046.
  58. Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis. Physica Medica 112, 102642. doi:10.1016/j.ejmp.2023.102642.
  59. Synthetic CT reconstruction using a deep spatial pyramid convolutional framework for MR-only breast radiotherapy. Medical Physics 46, 4135–4147. doi:https://doi.org/10.1002/mp.13716.
  60. MRI-Related Geometric Distortions in Stereotactic Radiotherapy Treatment Planning: Evaluation and Dosimetric Impact. Technology in Cancer Research &; Treatment 16, 1120–1129. doi:10.1177/1533034617735454.
  61. Implementation of the structural SIMilarity (SSIM) index as a quantitative evaluation tool for dose distribution error detection. Medical Physics 47, 1907–1919. doi:10.1002/mp.14010.
  62. Generative ai for medical imaging: extending the monai framework. arXiv preprint arXiv:2307.15208 .
  63. High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 10684–10695.
  64. 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, Springer International Publishing, Cham. pp. 234–241.
  65. Attention gated networks: Learning to leverage salient regions in medical images. Medical Image Analysis 53, 197–207. doi:10.1016/j.media.2019.01.012.
  66. Radiotherapy planning using MRI. Physics in Medicine & Biology 60, R323.
  67. Assessing the effect of electron density in photon dose calculations. Medical Physics 33, 540–552. doi:10.1118/1.2161407.
  68. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 .
  69. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 .
  70. Deep learning based synthetic-CT generation in radiotherapy and PET: a review. Medical physics 48, 6537–6566.
  71. Deep convolution neural network (dcnn) multiplane approach to synthetic ct generation from mr images—application in brain proton therapy. International Journal of Radiation Oncology*Biology*Physics 105, 495–503. doi:10.1016/j.ijrobp.2019.06.2535.
  72. The proof and measurement of association between two things. The American Journal of Psychology 15, 72–101. doi:10.2307/1412159.
  73. How to train your vit? data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 .
  74. BoneMRI of the cervical spine: Deep learning-based radiodensity contrast generation for selective visualization of osseous structures, in: ISMRM 27th Annual Meeting, Montreal, Canada.
  75. Double U-Net CycleGAN for 3D MR to CT image synthesis. International Journal of Computer Assisted Radiology and Surgery 18, 149–156. doi:10.1007/s11548-022-02732-x.
  76. Efficientnet: Rethinking model scaling for convolutional neural networks, in: International conference on machine learning, PMLR. pp. 6105–6114.
  77. Improving Deep Learning with Generic Data Augmentation, in: 2018 IEEE Symposium Series on Computational Intelligence (SSCI), IEEE. doi:10.1109/ssci.2018.8628742.
  78. SynthRAD2023 Grand Challenge dataset: Generating synthetic CT for radiotherapy. Medical Physics 50, 4664–4674. doi:https://doi.org/10.1002/mp.16529.
  79. SynthRAD2023 Challenge design: Synthesizing computed tomography for radiotherapy. URL: https://doi.org/10.5281/zenodo.7781049, doi:10.5281/zenodo.7781049.
  80. Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance. Radiotherapy and Oncology 153, 55–66.
  81. Attention is All you Need, in: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (Eds.), Advances in Neural Information Processing Systems, Curran Associates, Inc. URL: https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf.
  82. Methods and open-source toolkit for analyzing and visualizing challenge results. Scientific reports 11, 2369.
  83. Development of the open-source dose calculation and optimization toolkit matRad. Medical Physics 44, 2556–2568. doi:https://doi.org/10.1002/mp.12251.
  84. Individual comparisons by ranking methods. Biometrics Bulletin 1, 80–83. doi:10.2307/3001968.
  85. GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation. arXiv preprint arXiv:2212.06795 .
  86. Dodnet: Learning to segment multi-organ and tumors from multiple partially labeled datasets, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 1195–1204.
  87. Adding conditional control to text-to-image diffusion models, in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 3836–3847.
  88. The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  89. Road extraction by deep residual U-net. IEEE Geoscience and Remote Sensing Letters 15, 749–753.
  90. Multi-scale tokens-aware transformer network for multi-region and multi-sequence mr-to-ct synthesis in a single model. IEEE Transactions on Medical Imaging , 1–1doi:10.1109/TMI.2023.3321064.
  91. Unet++: A nested u-net architecture for medical image segmentation, in: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, Springer. pp. 3–11.
  92. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV).
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 3 tweets and received 9 likes.

Upgrade to Pro to view all of the tweets about this paper:

Start a free 7-day Pro trial