Modern Computer Tomography with Artificial Intelligence and Deep Learning Applications

Abstract

X-ray computed tomography (CT) aims production of 2-dimensional mass-density (or X-ray attenuation coefficient) maps of the sliced interior body by using directed X-rays through it to construct 3D CT images from the collection of these sliced 2D maps. That the CT scan gives the necessary information about the interior structure of the body without any cut or physical damage makes it indispensable in our modern medical applications along with the related medical sciences. However, since the X-rays involve ionizing radiation, it is dangerous for living organisms and it brings about the ALARA (as low as reasonably achievable) principle in medical applications emphasizing as high-quality CT images (with the highest possible resolution) as possible by using as little X-ray exposure of the body under scan as possible. This challenging task along with the correct interpretation of these CT images to lead a correct diagnosis and treatment plan brings about designing various fan geometries, scanning styles, and advanced image reconstruction techniques in the evolution of X-ray CT scans. We can see that X-ray CT scans have been evolved enormously since the first discovery in early 1970s and it continues today with the applications of artificial intelligence (AI) and deep learning (DL) in our modern CT with promising successful results. In this work, a pedagogical study of our modern X-ray CT with the related review of literature regarding i-scanning geometry, ii-reconstruction techniques, and iii-AI&DL applications is being presented hoping to be useful as a quick reference especially for the scholars and researchers in the field.

Keywords

• X-ray computed tomography
• X-ray CT
• Artificial intelligence
• AI
• Deep learning
• DL

References

1. [1] Arndt, C. et al. (2021). Deep Learning CT Image Reconstruction in Clinical Practice. Fortschr Röntgenstr, (193), 252–261.
2. [2] Booij, R., et al. (2020). Technological developments of X-ray computed tomography over half a century: User’s influence on protocol optimization. European Journal of Radiology, (131), 109261.
3. [3] Bueno et al. (2018). Development of a New Cone-Beam Computed Tomography Software for Endodontic Diagnosis. Brazilian Dental Journal, 29(6). 517-529. http://dx.doi.org/10.1590/0103- 6440201802455.
4. [4] Liu, Y. (2018). Ch. 5: Research Status and Prospect for CT Imaging of book: “State of the Art in Nanobioimaging”. IntechOpen, 73-93. https://www.intechopen.com/chapters/58660.
5. [5] Padole, A., Khawaja, R., D., A., Kalra, M., K., Singh, S. (2015). CT Radiation Dose and Iterative Reconstruction Techniques, Residents’ Section-Structured Review, AJR, (204), W384–W392.
6. [6] Samei, E. & Pelc, N. (2020). Computed Tomography Approaches, Applications, and Operations: Approaches, Applications, and Operations. Springer Nature, 2020, Switzerland. Doi: 10.1007/978-3-030-26957-9 (e-book).
7. [7] Xing, R. (2020). Deep Learning Based CT Image Reconstruction, MSc Thesis, University of Washington.
8. [8] Sun J, Li H, Wang B, Li J, Li M, Zhou Z, Peng Y. (2021). Application of a deep learning image reconstruction (DLIR) algorithm in head CT imaging for children to improve image quality and lesion detection. BMC Med Imaging, 21(1), 108. doi: 10.1186/s12880-021-00637-w. PMID: 34238229; PMCID: PMC8268450.

9. [9] Zhong J, Wang L, Shen H, Li J, Lu W, Shi X, Xing Y, Hu Y, Ge X, Ding D, Yan F, Du L, Yao W, Zhang H. (2023). Improving lesion conspicuity in abdominal dual-energy CT with deep learning image reconstruction: a prospective study with five readers. Eur Radiol., doi: 10.1007/s00330-023-09556-6. Epub ahead of print. PMID: 36976337.
10. [10] Kalender, W. A. (2006). X-ray computed tomography, Phys. Med. Biol., 51, R29–R43.
11. [11] Lee T, Seeram E. (2020). The use of artificial intelligence in computed tomography image reconstruction: A systematic review. Radiol Open J., 4(2): 30-38. doi: 10.17140/ROJ-4-129.
12. [12] Buzug, T., M. (2008). Computed Tomography: from Photon Statistics to Modern Cone-Beam CT, Springer, Berlin, Heidelberg.
13. [13] Kak, C., A., Slany, M., Principles of computerized tomographic imaging, IEEE press, 1999.
14. [14] Michael, G. (2001). X-ray computed tomography, Phys. Educ., 442-451.
15. [15] Romans, L., E. (2019). Computed tomography for technologists: A comprehensive text, 2nd ed., Wolters Kluwer.
16. [16] Venkatesh, E., Elluru, S., V.(2017). Cone beam computed tomography: basics and applications in dentistry, J Istanbul Univ Fac Dent., 51 (3 Suppl 1), S102-S121.
17. [17] Cunningham, I. A., Philip, F. J.. (2000). Computed Tomography, CRC Press LLC.
18. [18] Ginat, D. T., Gupta, R. (2014). Advances in Computed Tomography Imaging Technology, Annu. Rev. Biomed. Eng., 16, 431–453.
19. [19] Goldman, L., W. (2007). Principles of CT and CT Technology, J Nucl Med Technol., 35, 115–128. DOI: 10.2967/jnmt.107.042978.
20. [20] Lell, M. M, Wildberger, J. E., Alkadhi, H., Damilakis, J., Kachelriess, M. (2015). Evolution in computed tomography: the battle for speed and dose. Investigative Radiology, 50(9), 629-644. DOI: https://doi.org/10.1097/RLI.0000000000000172.
21. [21] Akagi, M., Nakamura, Y., et al. 2019. Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT. Eur Radiol, 29(11), 6163–6171. (Erratum in: Eur Radiol. 2019 May 27, PMID: 30976831).
22. [22] Hsieh, J., Nett, B., Yu, Z. et al. (2013). Recent Advances in CT Image Reconstruction. Curr Radiol Rep, 1, 39–51. https://doi.org/10.1007/s40134-012-0003-7
23. [23] Assili, S. (17 Sep 2018). A Review of Tomographic Reconstruction Techniques for Computed Tomography, arXiv:1808.09172v2 [physics.med-ph], 1-5.
24. [24] Geyer, L., L., Schoepf, U., J., et al. (2015). State of the Art: Iterative CT Reconstruction Techniques, Radiology. 276(2), 339-357.
25. [25] Ji, D., Qu, G., Liu, B. (2016). Simultaneous algebraic reconstruction technique based on guided image filtering, Optics Express, 24(14), 15897-15911.
26. [26] Willemink, M. J., Noel, P. B. (2019). The evolution of image reconstruction for CT—from filtered back projection to artificial intelligence, Computed Tomography, European Radiology, 29, 2185–2195. https://doi.org/10.1007/s00330-018-5810-7.
27. [27] Rubin, G. D. (2014). Computed Tomography: Revolutionizing the Practice of Medicine for 40 Years, Radiology, 273(2 Suppl.), (Suppl), 545-74. doi: 10.1148/radiol.14141356. PMID: 25340438.
28. [28] Kaczmarz, S. (1937). Angenäherte auflösung von systemen linearer Gleichungen, Bull. Int. Acad. Sci. Pologne, 35, 355–357.
29. [29] Yusoff, M. S. M., Sulaiman R., Shafinah, K.. (2012). Image Reconstruction for CT Scanner by Using Filtered Back projection Approach, Journal of American Science; 8(6), 797-803.
30. [30] Jorgensen, J. S. (2013). Sparse Image Reconstruction in computed tomography, Technical University of Denmark PHD-2013 No. 293.
31. [31] Kharfi, F. (2013). Ch. 4: Mathematics and Physics of Computed Tomography (CT): Demonstrations and Practical Examples of book: “Imaging and Radioanalytical Techniques in Interdisciplinary Research”, IntechOpen, 81-106.
32. [32] Onur, T., Ö. (2021). An application of filtered back projection method for computed tomography images, International Review of Applied Sciences and Engineering, 12, (2), 194-200.
33. [33] Siahaan, F. M. (2008). Computed Tomography (CT) image reconstruction using Matlab programming, Master thesis in University of Indonesia.
34. [34] Golsher, J., G. (1977). Iterative Three-Dimensional Image Reconstruction from Tomographic Projections. Computer Graphics and Image Processing, 6, 513-537.
35. [35] Do S, Song KD, Chung JW. (2020). Basics of Deep Learning: A Radiologist's Guide to Understanding Published Radiology Articles on Deep Learning. Korean J Radiol., 21(1), 33-41. https://doi.org/10.3348/kjr.2019.0312
36. [36] Hsieh, J., et al. (2019). A new era of image reconstruction: True Fidelity, Technical white paper on deep learning image reconstruction. www.gehealthcare.com.
37. [37] Kim, Y., et al. (2015). Ultra-Low-Dose CT of the Thorax Using Iterative Reconstruction: Evaluation of Image Quality and Radiation Dose Reduction. AJR, 204, 1197-1202.
38. [38] Alagic, Z., Diaz Cardenas, J., Halldorsson, K. et al. (2022). Deep learning versus iterative image reconstruction algorithm for head CT in trauma. Emerg Radiol, 29, 339–352. https://doi.org/10.1007/s10140-021-02012-2, https://doi.org/10.1007/s10140-021-02012-2
39. [39] Dominik, C., B., et al. (2020). Validation of deep-learning image reconstruction for coronary computed tomography angiography: Impact on noise, image quality and diagnostic accuracy, 14(5), 444-451.
40. [40] Jiang, J-M., Miao, L., Liang, X., Liu, Z-H., Zhang, L., Li, M. (2022). The Value of Deep Learning Image Reconstruction in Improving the Quality of Low-Dose Chest CT Images. Diagnostics, 12(10), 2560. https://doi.org/10.3390/diagnostics12102560.
41. [41] Parakh, A., Cao, J., Pierce, T., T. et al. (2021). Sinogram-based deep learning image reconstruction technique in abdominal CT: image quality considerations. Eur Radiol, 31, 8342–8353. https://doi.org/10.1007/s00330-021-07952-4
42. [42] Bie, Y., Yang, S., Li, X., Zhao, K., Zhang, C., Zhong, H. (2022). Impact of deep learning-based image reconstruction on image quality compared with adaptive statistical iterative reconstruction-Veo in renal and adrenal computed tomography. J Xray Sci Technol., 30(3), 409-418. doi: 10.3233/XST-211105. PMID: 35124575; PMCID: PMC9108564.
43. [43] Kim, J., H., Yoon, H., J., Lee, E., Kim, I., Cha, Y., K., Bak, S., H. (2021). Validation of Deep-Learning Image Reconstruction for Low-Dose Chest Computed Tomography Scan: Emphasis on Image Quality and Noise. Korean J Radiol., 22(1), 131-138. doi: 10.3348/kjr.2020.0116. Epub 2020 Jul 27. PMID: 32729277; PMCID: PMC7772377.
44. [44] Tian, Q., Li, X., Li, J., Cheng, Y., Niu, X., Zhu, S., Xu, W., Guo, J. (2022). Image quality improvement in low-dose chest CT with deep learning image reconstruction. J Appl Clin Med Phys., 23(12), e13796. doi: 10.1002/acm2.13796. Epub 2022 Oct 9. PMID: 36210060; PMCID: PMC9797160.
45. [45] Greffier, J., Hamard, A., Pereira, F., Barrau, C., Pasquier, H., Beregi, J.,P., Frandon, J. (2020). Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study. Eur Radiol., 30(7), 3951-3959. doi: 10.1007/s00330-020-06724-w. Epub 2020 Feb 25. PMID: 3210009.
46. [46] Jiang, C., Jin, D., Liu, Z. et al. (2022). Deep learning image reconstruction algorithm for carotid dual-energy computed tomography angiography: evaluation of image quality and diagnostic performance. Insights Imaging, 13, 182. https://doi.org/10.1186/s13244-022-01308-2.
47. [47] Noda, Y., Iritani, Y., Kawai, N. et al. (2021). Deep learning image reconstruction for pancreatic low-dose computed tomography: comparison with hybrid iterative reconstruction. Abdom Radiol, 46, 4238–4244. https://doi.org/10.1007/s00261-021-03111-x.
48. [48] Sun, J., Li, H., Wang, B., Li, J., Li, M., Zhou, Z., Peng, Y. (2021). Application of a deep learning image reconstruction (DLIR) algorithm in head CT imaging for children to improve image quality and lesion detection. BMC Med Imaging. 21(1), 108. doi: 10.1186/s12880-021-00637-w. PMID: 34238229; PMCID: PMC8268450.
49. [49] Sun, J,, Li. H., Li, H., Li, M., Gao, Y., Zhou, Z., Peng, Y. (2022). Application of deep learning image reconstruction algorithm to improve image quality in CT angiography of children with Takayasu arteritis. J Xray Sci Technol, 30(1), 177-184. doi: 10.3233/XST-211033. PMID: 34806646.
50. [50] Yoo, Y., J., Choi, I., Y., Yeom, S., K., Cha, S., H., Jung, Y., Han, H. J., Shim, E. (2022). Evaluation of Abdominal CT Obtained Using a Deep Learning-Based Image Reconstruction Engine Compared with CT Using Adaptive Statistical Iterative Reconstruction. J Belg Soc Radiol, 106(1), 15. doi: 10.5334/jbsr.2638. PMID: 35480337; PMCID: PMC8992765.
51. [51] Li, Y., Jiang, Y., Yu, X., Ren, B., Wang, C., Chen, S., Ma, D., Su, D., Liu, H., Ren, X., Yang, X., Gao, J., Wu, Y. (2022). Deep-learning image reconstruction for image quality evaluation and accurate bone mineral density measurement on quantitative CT: A phantom-patient study. Front Endocrinol (Lausanne). 13, 884306. doi: 10.3389/fendo.2022.884306. PMID: 36034436; PMCID: PMC9403270.
52. [52] Nakamura, Y., Higaki, T., et al. (2019). Deep Learning–based CT Image Reconstruction: Initial Evaluation Targeting Hypovascular Hepatic Metastases. Radiology: Artificial Intelligence, 1, e180011.
53. [53] Higaki, T., Nakamura, Y., Zhou, J., et al. (2020). Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics. Academic Radiology, 27, 82–87.
54. [54] Narita, K., Nakamura, Y., Higaki, T., et al. (2020). Deep learning reconstruction of drip-infusion cholangiography acquired with ultra-high-resolution computed tomography. Abdom Radiol., 45, 2698–2704. http://link.springer.com/10.1007/s00261-020-02508-4