Korean Journal of Radiology

  • 제25권9호
  • /
  • Pages.833-842
  • /
  • 2024
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Reconstruction Algorithm With Lung Enhancement Filter for Chest CT: Effect on Image Quality and Ground Glass Nodule Sharpness

  • Min-Hee Hwang (Department of Radiology and Medical Research Institute, Pusan National University Hospital, Pusan National University School of Medicine) ;
  • Shinhyung Kang (GE HealthCare) ;
  • Ji Won Lee (Department of Radiology and Medical Research Institute, Pusan National University Hospital, Pusan National University School of Medicine) ;
  • Geewon Lee (Department of Radiology and Medical Research Institute, Pusan National University Hospital, Pusan National University School of Medicine)
  • 투고 : 2024.05.18
  • 심사 : 2024.07.18
  • 발행 : 2024.09.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: To assess the effect of a new lung enhancement filter combined with deep learning image reconstruction (DLIR) algorithm on image quality and ground-glass nodule (GGN) sharpness compared to hybrid iterative reconstruction or DLIR alone. Materials and Methods: Five artificial spherical GGNs with various densities (-250, -350, -450, -550, and -630 Hounsfield units) and 10 mm in diameter were placed in a thorax anthropomorphic phantom. Four scans at four different radiation dose levels were performed using a 256-slice CT (Revolution Apex CT, GE Healthcare). Each scan was reconstructed using three different reconstruction algorithms: adaptive statistical iterative reconstruction-V at a level of 50% (AR50), Truefidelity (TF), which is a DLIR method, and TF with a lung enhancement filter (TF + Lu). Thus, 12 sets of reconstructed images were obtained and analyzed. Image noise, signal-to-noise ratio, and contrast-to-noise ratio were compared among the three reconstruction algorithms. Nodule sharpness was compared among the three reconstruction algorithms using the full-width at half-maximum value. Furthermore, subjective image quality analysis was performed. Results: AR50 demonstrated the highest level of noise, which was decreased by using TF + Lu and TF alone (P = 0.001). TF + Lu significantly improved nodule sharpness at all radiation doses compared to TF alone (P = 0.001). The nodule sharpness of TF + Lu was similar to that of AR50. Using TF alone resulted in the lowest nodule sharpness. Conclusion: Adding a lung enhancement filter to DLIR (TF + Lu) significantly improved the nodule sharpness compared to DLIR alone (TF). TF + Lu can be an effective reconstruction technique to enhance image quality and GGN evaluation in ultralow-dose chest CT scans.

키워드

과제정보

This work was supported by clinical research grant from Pusan National University Hospital in 2021.

참고문헌

  1. Koetzier LR, Mastrodicasa D, Szczykutowicz TP, van der Werf NR, Wang AS, Sandfort V, et al. Deep learning image reconstruction for CT: technical principles and clinical prospects. Radiology 2023;306:e221257
  2. Nam JG, Ahn C, Choi H, Hong W, Park J, Kim JH, et al. Image quality of ultralow-dose chest CT using deep learning techniques: potential superiority of vendor-agnostic post-processing over vendor-specific techniques. Eur Radiol 2021;31:5139-5147
  3. Svalkvist A, Fagman E, Vikgren J, Ku S, Diniz MO, Norrlund RR, et al. Evaluation of deep-learning image reconstruction for chest CT examinations at two different dose levels. J Appl Clin Med Phys 2023;24:e13871
  4. National Lung Screening Trial Research Team; Aberle DR, Adams AM, Berg CD, Black WC, Clapp JD, Fagerstrom RM, et al. Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 2011;365:395-409
  5. Kazerooni EA, Armstrong MR, Amorosa JK, Hernandez D, Liebscher LA, Nath H, et al. ACR CT accreditation program and the lung cancer screening program designation. J Am Coll Radiol 2016;13(2 Suppl):R30-R34
  6. MacMahon H, Naidich DP, Goo JM, Lee KS, Leung ANC, Mayo JR, et al. Guidelines for management of incidental pulmonary nodules detected on CT images: from the Fleischner Society 2017. Radiology 2017;284:228-243
  7. Bankier AA, MacMahon H, Colby T, Gevenois PA, Goo JM, Leung ANC, et al. Fleischner Society: glossary of terms for thoracic imaging. Radiology 2024;310:e232558
  8. Remy-Jardin M, Remy J, Giraud F, Wattinne L, Gosselin B. Computed tomography assessment of ground-glass opacity: semiology and significance. J Thorac Imaging 1993;8:249-264
  9. Hu H, Wang Q, Tang H, Xiong L, Lin Q. Multi-slice computed tomography characteristics of solitary pulmonary ground-glass nodules: differences between malignant and benign. Thorac Cancer 2016;7:80-87
  10. Nambu A, Araki T, Taguchi Y, Ozawa K, Miyata K, Miyazawa M, et al. Focal area of ground-glass opacity and ground-glass opacity predominance on thin-section CT: discrimination between neoplastic and non-neoplastic lesions. Clin Radiol 2005;60:1006-1017
  11. Wu F, Tian SP, Jin X, Jing R, Yang YQ, Jin M, et al. CT and histopathologic characteristics of lung adenocarcinoma with pure ground-glass nodules 10 mm or less in diameter. Eur Radiol 2017;27:4037-4043
  12. Gordic S, Morsbach F, Schmidt B, Allmendinger T, Flohr T, Husarik D, et al. Ultralow-dose chest computed tomography for pulmonary nodule detection: first performance evaluation of single energy scanning with spectral shaping. Invest Radiol 2014;49:465-473
  13. Park HJ, Choi SY, Lee JE, Lim S, Lee MH, Yi BH, et al. Deep learning image reconstruction algorithm for abdominal multidetector CT at different tube voltages: assessment of image quality and radiation dose in a phantom study. Eur Radiol 2022;32:3974-3984
  14. Svanholm H, Starklint H, Gundersen HJ, Fabricius J, Barlebo H, Olsen S. Reproducibility of histomorphologic diagnoses with special reference to the kappa statistic. APMIS 1989;97:689-698
  15. Franck C, Zhang G, Deak P, Zanca F. Preserving image texture while reducing radiation dose with a deep learning image reconstruction algorithm in chest CT: a phantom study. Phys Med 2021;81:86-93
  16. Jiang B, Li N, Shi X, Zhang S, Li J, de Bock GH, et al. Deep learning reconstruction shows better lung nodule detection for ultra-low-dose chest CT. Radiology 2022;303:202-212
  17. Kim JH, Yoon HJ, Lee E, Kim I, Cha YK, Bak SH. Validation of deep-learning image reconstruction for low-dose chest computed tomography scan: emphasis on image quality and noise. Korean J Radiol 2021;22:131-138
  18. Padole A, Ali Khawaja RD, Kalra MK, Singh S. CT radiation dose and iterative reconstruction techniques. AJR Am J Roentgenol 2015;204:W384-W392
  19. Wang J, Sui X, Zhao R, Du H, Wang J, Wang Y, et al. Value of deep learning reconstruction of chest low-dose CT for image quality improvement and lung parenchyma assessment on lung window. Eur Radiol 2024;34:1053-1064
  20. Bankier AA, MacMahon H, Goo JM, Rubin GD, Schaefer-Prokop CM, Naidich DP. Recommendations for measuring pulmonary nodules at CT: a statement from the Fleischner Society. Radiology 2017;285:584-600
  21. Funama Y, Awai K, Liu D, Oda S, Yanaga Y, Nakaura T, et al. Detection of nodules showing ground-glass opacity in the lungs at low-dose multidetector computed tomography: phantom and clinical study. J Comput Assist Tomogr 2009;33:49-53
  22. Doo KW, Kang EY, Yong HS, Woo OH, Lee KY, Oh YW. Accuracy of lung nodule volumetry in low-dose CT with iterative reconstruction: an anthropomorphic thoracic phantom study. Br J Radiol 2014;87:20130644
  23. Kubo T, Ohno Y, Takenaka D, Nishino M, Gautam S, Sugimura K, et al. Standard-dose vs. low-dose CT protocols in the evaluation of localized lung lesions: capability for lesion characterization-iLEAD study. Eur J Radiol Open 2016;3:67-73
  24. Greffier J, Hamard A, Pereira F, Barrau C, Pasquier H, Beregi JP, et al. Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study. Eur Radiol 2020;30:3951-3959
  25. Solomon J, Lyu P, Marin D, Samei E. Noise and spatial resolution properties of a commercially available deep learning-based CT reconstruction algorithm. Med Phys 2020;47:3961-3971
  26. Hong JH, Park EA, Lee W, Ahn C, Kim JH. Incremental image noise reduction in coronary CT angiography using a deep learning-based technique with iterative reconstruction. Korean J Radiol 2020;21:1165-1177
  27. Son W, Kim M, Hwang JY, Kim YW, Park C, Choo KS, et al. Comparison of a deep learning-based reconstruction algorithm with filtered back projection and iterative reconstruction algorithms for pediatric abdominopelvic CT. Korean J Radiol 2022;23:752-762
  28. Ohno K, Ohkubo M, Marasinghe JC, Murao K, Matsumoto T, Wada S. Accuracy of lung nodule density on HRCT: analysis by PSF-based image simulation. J Appl Clin Med Phys 2012;13:3868
  29. Rollo FD, Schulz AG. A contrast efficiency function for quantitatively measuring the spatial-resolution characteristics of scanning systems. J Nucl Med 1970;11:53-60
  30. Liu LP, Shapira N, Sahbaee P, Gang GJ, Knollman FD, Chen MY, et al. Consistency of spectral results in cardiac dual-source photon-counting CT. Sci Rep 2023;13:14895
  31. Takafuji M, Kitagawa K, Mizutani S, Hamaguchi A, Kisou R, Iio K, et al. Super-resolution deep learning reconstruction for improved image quality of coronary CT angiography. Radiol Cardiothorac Imaging 2023;5:e230085