Papers
Topics
Authors
Recent
2000 character limit reached

Scout-Net: Prospective Personalized Estimation of CT Organ Doses from Scout Views (2312.15354v1)

Published 23 Dec 2023 in cs.CV

Abstract: Purpose: Estimation of patient-specific organ doses is required for more comprehensive dose metrics, such as effective dose. Currently, available methods are performed retrospectively using the CT images themselves, which can only be done after the scan. To optimize CT acquisitions before scanning, rapid prediction of patient-specific organ dose is needed prospectively, using available scout images. We, therefore, devise an end-to-end, fully-automated deep learning solution to perform real-time, patient-specific, organ-level dosimetric estimation of CT scans. Approach: We propose the Scout-Net model for CT dose prediction at six different organs as well as for the overall patient body, leveraging the routinely obtained frontal and lateral scout images of patients, before their CT scans. To obtain reference values of the organ doses, we used Monte Carlo simulation and 3D segmentation methods on the corresponding CT images of the patients. Results: We validate our proposed Scout-Net model against real patient CT data and demonstrate the effectiveness in estimating organ doses in real-time (only 27 ms on average per scan). Additionally, we demonstrate the efficiency (real-time execution), sufficiency (reasonable error rates), and robustness (consistent across varying patient sizes) of the Scout-Net model. Conclusions: An effective, efficient, and robust Scout-Net model, once incorporated into the CT acquisition plan, could potentially guide the automatic exposure control for balanced image quality and radiation dose.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. M. M. Lell and M. Kachelrieß, “Recent and upcoming technological developments in computed tomography: high speed, low dose, deep learning, multienergy,” Investigative radiology 55(1), 8–19 (2020).
  2. P. J. Withers, C. Bouman, S. Carmignato, et al., “X-ray computed tomography,” Nature Reviews Methods Primers 1(1), 1–21 (2021).
  3. M. J. Willemink, M. Persson, A. Pourmorteza, et al., “Photon-counting CT: technical principles and clinical prospects,” Radiology 289(2), 293–312 (2018).
  4. M. Kachelrieß and M. M. Rehani, “Is it possible to kill the radiation risk issue in computed tomography?,” Physica Medica: European Journal of Medical Physics 71, 176–177 (2020).
  5. A.-A.-Z. Imran, D. Pal, B. Patel, et al., “SSIQA: Multi-task learning for non-reference CT image quality assessment with self-supervised noise level prediction,” in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 1962–1965 (2021).
  6. A.-A.-Z. Imran, D. Pal, S. Wang, et al., “Personalized ct organ noise estimation from scout images,” in Medical Imaging 2022: Physics of Medical Imaging, 12031, 186–192, SPIE (2022).
  7. J. Damilakis, “CT Dosimetry: what has been achieved and what remains to be done,” Investigative Radiology 56(1), 62–68 (2021).
  8. J. VALENTIN, “The 2007 recommendations of the international commission on radiological protection. icrp publication 103,” Ann ICRP 37(2), 1–332 (2007).
  9. E. E. Furhang, C.-S. Chui, and G. Sgouros, “A Monte Carlo approach to patient-specific dosimetry,” Medical physics 23(9), 1523–1529 (1996).
  10. A. Badal and A. Badano, “Accelerating Monte Carlo simulations of photon transport in a voxelized geometry using a massively parallel graphics processing unit,” Medical physics 36(11), 4878–4880 (2009).
  11. X. Jia, H. Yan, X. Gu, et al., “Fast monte carlo simulation for patient-specific ct/cbct imaging dose calculation,” Physics in Medicine & Biology 57(3), 577 (2012).
  12. X. G. Xu, T. Liu, L. Su, et al., “Archer, a new monte carlo software tool for emerging heterogeneous computing environments,” Annals of Nuclear Energy 82, 2–9 (2015).
  13. A. Wang, A. Maslowski, T. Wareing, et al., “A fast, linear boltzmann transport equation solver for computed tomography dose calculation (acuros ctd),” Medical physics 46(2), 925–933 (2019).
  14. S. Principi, A. Wang, A. Maslowski, et al., “Deterministic linear boltzmann transport equation solver for patient-specific ct dose estimation: Comparison against a monte carlo benchmark for realistic scanner configurations and patient models,” Medical Physics 47(12), 6470–6483 (2020).
  15. S. Principi, Y. Lu, Y. Liu, et al., “Validation of a deterministic linear boltzmann transport equation solver for rapid ct dose computation using physical dose measurements in pediatric phantoms,” Medical Physics (2021).
  16. J. Fan, L. Xing, P. Dong, et al., “Data-driven dose calculation algorithm based on deep U-Net,” Physics in Medicine & Biology 65(24), 245035 (2020).
  17. T. I. Götz, C. Schmidkonz, S. Chen, et al., “A deep learning approach to radiation dose estimation,” Physics in Medicine & Biology 65(3), 035007 (2020).
  18. F. Guerreiro, E. Seravalli, G. Janssens, et al., “Deep learning prediction of proton and photon dose distributions for paediatric abdominal tumours,” Radiotherapy and Oncology 156, 36–42 (2021).
  19. C. Kontaxis, G. Bol, J. Lagendijk, et al., “DeepDose: towards a fast dose calculation engine for radiation therapy using deep learning,” Physics in Medicine & Biology 65(7), 075013 (2020).
  20. M. S. Lee, D. Hwang, J. H. Kim, et al., “Deep-dose: a voxel dose estimation method using deep convolutional neural network for personalized internal dosimetry,” Scientific reports 9(1), 1–9 (2019).
  21. J. Maier, L. Klein, E. Eulig, et al., “Real-time estimation of patient-specific dose distributions for medical ct using the deep dose estimation,” Medical Physics 49(4), 2259–2269 (2022).
  22. J. Zhu, X. Liu, and L. Chen, “A preliminary study of a photon dose calculation algorithm using a convolutional neural network,” Physics in Medicine & Biology 65(20), 20NT02 (2020).
  23. Z. Peng, X. Fang, P. Yan, et al., “A method of rapid quantification of patient-specific organ doses for CT using deep-learning-based multi-organ segmentation and GPU-accelerated Monte Carlo dose computing,” Medical physics 47(6), 2526–2536 (2020).
  24. W. Fu, S. Sharma, E. Abadi, et al., “iphantom: a framework for automated creation of individualized computational phantoms and its application to ct organ dosimetry,” IEEE Journal of Biomedical and Health Informatics (2021).
  25. M. Offe, D. Fraley, P. M. Adamson, et al., “Evaluation of deep learning segmentation for rapid, patient-specific CT organ dose estimation using an lbte solver,” in Medical Imaging 2020: Physics of Medical Imaging, 11312, 113124O, International Society for Optics and Photonics (2020).
  26. L. Klein, C. Liu, J. Steidel, et al., “Patient-specific radiation risk-based tube current modulation for diagnostic ct,” Medical Physics (2022).
  27. X. Tian, X. Li, W. P. Segars, et al., “Prospective estimation of organ dose in CT under tube current modulation,” Medical physics 42(4), 1575–1585 (2015).
  28. Y. Gao, U. Mahmood, T. Liu, et al., “Patient-specific organ and effective dose estimates in adult oncologic CT,” American Journal of Roentgenology 214(4), 738–746 (2020).
  29. J. C. Montoya, C. Zhang, Y. Li, et al., “Reconstruction of three-dimensional tomographic patient models for radiation dose modulation in ct from two scout views using deep learning,” Medical Physics 49(2), 901–916 (2022).
  30. L. Shen, W. Zhao, and L. Xing, “Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning,” Nature biomedical engineering 3(11), 880–888 (2019).
  31. N. Shapira, S. Bharthulwar, and P. B. Noël, “Convolutional encoder-decoder networks for volumetric computed tomography surviews from single-and dual-view topograms,” medRxiv (2022).
  32. X. Ying, H. Guo, K. Ma, et al., “X2ct-gan: reconstructing ct from biplanar x-rays with generative adversarial networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 10619–10628 (2019).
  33. D. F. Almeida, P. Astudillo, and D. Vandermeulen, “Three-dimensional image volumes from two-dimensional digitally reconstructed radiographs: A deep learning approach in lower limb ct scans,” Medical Physics 48(5), 2448–2457 (2021).
  34. O. R. Brook, L. Guralnik, and A. Engel, “CT scout view as an essential part of CT reading,” Australasian radiology 51(3), 211–217 (2007).
  35. M. Kortesniemi, E. Salli, and R. Seuri, “Organ dose calculation in CT based on scout image data and automatic image registration,” Acta Radiologica 53(8), 908–913 (2012).
  36. X. Duan, J. Wang, J. A. Christner, et al., “Dose reduction to anterior surfaces with organ-based tube-current modulation: evaluation of performance in a phantom study,” American journal of roentgenology 197(3), 689–695 (2011).
  37. J. Wang, X. Duan, J. A. Christner, et al., “Bismuth shielding, organ-based tube current modulation, and global reduction of tube current for dose reduction to the eye at head ct,” Radiology 262(1), 191–198 (2012).
  38. D. Gandhi, D. J. Crotty, G. M. Stevens, et al., “Phantom study to evaluate the dose and image quality effects of a computed tomography organ-based tube current modulation technique,” Medical physics 42(11), 6572–6578 (2015).
  39. A.-A.-Z. Imran, S. Wang, D. Pal, et al., “Personalized CT organ dose estimation from scout images,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 488–498, Springer (2021).
  40. K. He, X. Zhang, S. Ren, et al., “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778 (2016).
  41. S. Sharma, A. Kapadia, W. Fu, et al., “A real-time Monte Carlo tool for individualized dose estimations in clinical CT,” Physics in Medicine & Biology 64(21), 215020 (2019).
  42. F. Liu, G. Wang, W. Cong, et al., “Dynamic bowtie for fan-beam CT,” Journal of X-ray Science and Technology 21(4), 579–590 (2013).
  43. N. Mail, D. Moseley, J. Siewerdsen, et al., “The influence of bowtie filtration on cone-beam CT image quality,” Medical physics 36(1), 22–32 (2009).
  44. M. W. Kusk, J. M. Jensen, E. H. Gram, et al., “Anode heel effect: Does it impact image quality in digital radiography? a systematic literature review,” Radiography (2021).
  45. A. Wang, A. Maslowski, P. Messmer, et al., “Acuros CTS: A fast, linear Boltzmann transport equation solver for computed tomography scatter–part ii: System modeling, scatter correction, and optimization,” Medical physics 45(5), 1914–1925 (2018).
  46. Z. Gu, J. Cheng, H. Fu, et al., “Ce-net: Context encoder network for 2d medical image segmentation,” IEEE Transactions on Medical Imaging 38(10), 2281–2292 (2019).
  47. Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, et al., “3D U-Net: learning dense volumetric segmentation from sparse annotation,” in International conference on medical image computing and computer-assisted intervention, 424–432, Springer (2016).
  48. L.-C. Chen, G. Papandreou, F. Schroff, et al., “Rethinking atrous convolution for semantic image segmentation,” ArXiv abs/1706.05587 (2017).
  49. S. Dutta, B. Das, and S. Kaushik, “Assessment of optimal deep learning configuration for vertebrae segmentation from CT images,” in Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications, 10954, 298 – 305, SPIE (2019).
  50. T.-Y. Lin, P. Goyal, R. Girshick, et al., “Focal loss for dense object detection,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), (2017).
  51. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, N. Navab, J. Hornegger, W. M. Wells, et al., Eds., 234–241, Springer International Publishing, (Cham) (2015).
  52. ICRP, “The 2007 recommendations of the international commission on radiological protection: ICRP publication 103,” Ann ICRP 37, 1–332 (2007).
  53. C. McCollough, D. M. Bakalyar, M. Bostani, et al., “Use of water equivalent diameter for calculating patient size and size-specific dose estimates (ssde) in CT: the report of aapm task group 220,” AAPM report 2014, 6 (2014).
  54. Y. Wang, B. Liu, F. Zhou, et al., “Region context aggregation network for multi-organ segmentation on abdominal ct,” in International Conference on Image and Graphics, 664–674, Springer (2021).
  55. H. Lin, Z. Li, Z. Yang, et al., “Variance-aware attention u-net for multi-organ segmentation,” Medical Physics (2021).
  56. AAPM, “Size-specific dose estimate (ssde) for head CT,” American Association of Physicists in Medicine (AAPM) Report No. 293 (2019).
  57. J. Juszczyk, P. Badura, J. Czajkowska, et al., “Automated size-specific dose estimates using deep learning image processing,” Medical Image Analysis 68, 101898 (2021).
  58. T. G. Schmidt, A. S. Wang, T. Coradi, et al., “Accuracy of patient-specific organ dose estimates obtained using an automated image segmentation algorithm,” Journal of Medical Imaging 3(4), 043502 (2016).
  59. W. A. Kalender, N. Saltybaeva, D. Kolditz, et al., “Generating and using patient-specific whole-body models for organ dose estimates in ct with increased accuracy: feasibility and validation,” Physica Medica 30(8), 925–933 (2014).
  60. X. Tian, W. P. Segars, R. L. Dixon, et al., “Convolution-based estimation of organ dose in tube current modulated ct,” Physics in Medicine & Biology 61(10), 3935 (2016).
  61. A.-A.-Z. Imran, S. Wang, D. Pal, et al., “Multimodal contrastive learning for prospective personalized estimation of ct organ dose,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 634–643, Springer (2022).
Citations (2)
View on Semantic Scholar

Summary

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

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

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate 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