Comparison of noise-power spectrum and modulation-transfer function for CT images reconstructed with iterative and deep learning image reconstructions: An initial experience study

• Autorzy: Setiawan Adiwasono M. B. , Anam Choirul , Hidayanto Eko , Sutanto Heri , Naufal Ariij , Dougherty Geoff

Identyfikatory

DOI

10.2478/pjmpe-2023-0012

• Języki publikacji: EN

Abstrakty

EN

Deep learning image reconstruction (DLIR) is a very recent image reconstruction method that is already available for commercial use. We evaluated the quality of DLIR images and compared it to the quality of images from the latest adaptive statistical iterative reconstruction (ASIR-V) algorithm in terms of noise-power spectrum (NPS) and modulation-transfer function (MTF). We scanned a Revolution QA phantom (GE Healthcare, USA) and a 20 cm water phantom (GE Healthcare, USA) with our 512 multi-slice computed tomography (CT) scanner. Images of the tungsten wire within the Revolution QA phantom were reconstructed with a 50 mm field of view (FOV). The images were reconstructed with various ASIR-V strengths (i.e. 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100%) and DLIRs (i.e. low, medium, and high) to assess the MTF. The images from the 20 cm water phantom were reconstructed with the same configuration to assess the NPS. The MTF was similar for both reconstruction algorithms of DLIR and ASiR-V. The peak frequency (f_p) of the DLIR low was comparable to that from ASIR-V at 50, 60, 70%; the DLIR medium was comparable to ASIR-V at 80%; and the DLIR high was comparable to ASIR-V at 100%. The average frequency (f_A) of the DLIR low was comparable to that from ASIR-V at 40%; the DLIR medium was comparable to ASIR-V at 50%; and the DLIR high was comparable to ASIR-V at 70%. Both the DLIR and ASIR-V were able to reduce noise, but they had a different texture. The noise in the DLIR images was more homogenous at high and low frequencies, while in the ASIR-V images, the noise was more concentrated at high frequencies. The MTF was similar for both reconstruction algorithms. The DLIR method showed a better noise reduction than the ASIR-V reconstruction.

Słowa kluczowe

EN

ASIR-V; DLIR; noise power spectrum; modulation transfer function

• Wydawca: Polskie Towarzystwo Fizyki Medycznej ; De Gruyter
• Czasopismo: Polish Journal of Medical Physics and Engineering
• Rocznik: 2023
• Tom: Vol. 29, Iss. 2
• Strony: 104--112
• Opis fizyczny: Bibliogr. 38 poz., rys.

Twórcy

autor

Setiawan Adiwasono M. B.

• Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275,Central Java, Indonesia

autor

Anam Choirul

• Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275,Central Java, Indonesia

• https://orcid.org/0000-0003-0156-6797

autor

Hidayanto Eko

• Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275, Central Java, Indonesia

autor

Sutanto Heri

• Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275, Central Java, Indonesia

autor

Naufal Ariij

• Department of Physics, Faculty of Sciences and Mathematics, Diponegoro University, Jl. Prof. Soedarto SH, Tembalang, Semarang 50275, Central Java, Indonesia

autor

Dougherty Geoff

• Department of Applied Physics and Medical Imaging, California State University Channel Islands, Camarillo, CA 93012, USA

Bibliografia

• 1. Yim D, Lee S, Nam K, Lee D, Kim KD, Kim J S. Deep learning-based image reconstruction for few-view computed tomography. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment. 2021;1011:166594. https://doi.org/10.1016/j.nima.2021.165594
• 2. Anam C, Naufal A, Fujibuchi T, Matsubara K, Dougherty G. Automated development of the contrast-detail curve based on statistical low-contrast detectability in CT images. J Appl Clin Med Phys. 2022;23:e13719. https://doi.org/10.1002/acm2.13719
• 3. Li K, Tang J, Chen GH. Statistical model based iterative reconstruction (MBIR) in clinical CT systems: experimental assessment of noise performance. Med Phys. 2014;41:041906. https://doi.org/10.1118/1.4867863
• 4. Morsbach F, Desbiolles L, Raupach R, Leschka S, Schmidt B, Alkadhi H. Noise texture deviation: a measure for quantifying artefacts in computed tomography images with iterative reconstruction. Invest Radiol. 2017;52:87-94. https://doi.org/10.1097/RLI.0000000000000312
• 5. Solomon J, Samei E. Quantum noise properties of CT images with anatomical textured backgrounds across reconstruction algorithms: FBP and SAFIRE. Med Phys. 2014;41:091908. https://doi.org/10.1118/1.4893497
• 6. Andersen HK, Volgyes D, Martinsen ACT. Image quality with iterative reconstruction techniques in CT of the lungs: a phantom study. Eur J Radiol Open. 2018;5:35-40. https://doi.org/10.1016/j.ejro.2018.02.002
• 7. Willemink MJ, Noël PB. The evolution of image reconstruction for CT-from filtered back projection to artificial intelligence. Eur J Radiol. 2019;29:2185-2195. https://doi.org/10.1007/s00330-018-5810-7
• 8. Mcleavy CM, et al. The future of CT: Deep learning reconstruction. Clin Radiol. 2021;76:407-415. https://doi.org/10.1016/j.crad.2021.01.010
• 9. Szczykutowicz PT, Toia VG, Dhanantwari A, Nett B. A review of deep learning CT reconstruction: Concepts, limitations, and promise in clinical practice. Curr Radiol Rep. 2022;10:101-115. https://doi.org/10.1007/s40134-022-00399-5
• 10. Kataria B, Nilsson AJ, Smedby Ö, Persson A, Sökjer H, Sandborg M. Image quality and potential dose reduction using advanced modeled iterative reconstruction (ADMIRE) in abdominal CT - A review. Radiat Prot Dosim. 2021;195:177-187. https://doi.org/10.1093/rpd/ncab020
• 11. Greffier J, Frandon J, Larbi A, Om D, Beregi PJ, Perreira F. CT Iterative reconstruction algorithm: A task-based quality assessment. Eur Radiol. 2020;30:487-500. https://doi.org/10.1007/s00330-019-06359-6
• 12. Greffier J, Franfond J, Si-Mohamed S, et al. Comparison of two deep learning image reconstruction algorithms in chest CT images: A task-based image quality assessment on phantom data. Diagn Interv Imaging. 2022;103:21-22. https://doi.org/10.1016/j.diii.2021.08.001
• 13. Greffier J, Hamard A, Pereira F, 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. https://doi.org/10.1007/s00330-020-06724-w
• 14. Benz DC, Benetos G, Rampidis G, et al. Validation of deep-learning image reconstruction for coronary computed tomography angiography: Impact on noise, image quality and diagnostic accuracy. J Cardiovasc Comput Tomogr. 2020;14:444-451. https://doi.org/10.1016/j.jcct.2020.01.002
• 15. 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. https://doi.org/10.3348/kjr.2020.0116
• 16. Wang H, Li LL, Shang J, Song J, Liu B. Application of deep learning image reconstruction in low-dose chest CT scan. Br J Radiol. 2022;95:20210380. https://doi.org/10.1259/bjr.20210380
• 17. Zahro MU, Anam C, Budi WS, et al. Investigation of noise level and spatial resolution of CT images filtered with a selective mean filter and its comparison to an adaptive statistical iterative reconstruction. Iran J Med Phys. 2021;18:374-383. https://doi.org/10.22038/ijmp.2020.48813.1786
• 18. Hsieh J, Liu E, Nett B, Tang J, Thibault BJ, Sahney S. A new era of image reconstruction: True FidelityTM Technical White Paper on Deep Learning Image Reconstruction. GE Healthcare. 2019. https://www.gehealthcare.com/-/jssmedia/040dd213fa89463287155151fdb01922.pdf
• 19. Szczykutowicz PT, Nett B, Cherkezyan L, et al. Protocol optimization considerations for implementing deep learning CT reconstruction. Am J Radiol. 2021;216:1668-1677. https://doi.org/10.2214/AJR.20.23397
• 20. Anam C, Fujibuchi T, Haryanto F, et al. Automated MTF measurement in CT images with a simple wire phantom. Pol J Med Phys Eng. 2019;25:179-187. https://doi.org/10.2478/pjmpe-2019-0024
• 21. Li G, Liu X, Dodge C T, Jensen CT, Rong XJ. A noise power spectrum study of a new model-based iterative reconstruction system: Veo 3.0. J Appl Clin Med Phys. 2016;17:428-439. https://doi.org/10.1120/jacmp.v17i5.6225
• 22. Samei E, Bakalyar D, Boedeker KL, et al. Performance evaluation of computed tomography systems. Med Phys. 2019;46:735-756. https://doi.org/10.1002/mp.13763
• 23. Hasegawa A, Ishihara T, Thomas MA, Pan T. Noise reduction profile: A new method for evaluation of noise reduction techniques in CT. Med Phys. 2022;49:186-200. https://doi.org/10.1002/mp.15382
• 24. Anam C, Arif I, Haryanto F, et al. An improved method of automated noise measurement system in CT images. J Biomed Phys Eng. 2019;11:163-174. https://doi.org/10.31661%2Fjbpe.v0i0.1198
• 25. Kayugawa A, Ohkubo M, Wada S. Accurate determination of CT point-spread-function with high precision. J Appl Clin Med Phys. 2013;14:3905. https://doi.org/10.1120/jacmp.v14i4.3905
• 26. Anam C, Fujibuchi T, Budi WS, Haryanto F, Dougherty G. An algorithm for automated modulation transfer function measurement using an edge of a PMMA phantom: Impact of field of view on spatial resolution of CT images. J Appl Clin Med Phys. 2018;19:244-252. https://doi.org/10.1002/acm2.12476
• 27. Anam C, Naufal A, Sutanto H, Adi K, Dougherty G. Impact of iterative bilateral filtering on the noise power spectrum of computed tomography images. Algorithms. 2022;15:374. https://doi.org/10.3390/a15100374
• 28. ImQuest. https://deckard.duhs.duke.edu/~samei/tg233.html
• 29. Anam C, Naufal A, Fujibuchi T, Matsubara K, Dougherty G. Automated development of the contrast-detail curve based on statistical low-contrast detectability in CT images. J Appl Clin Med Phys. 2022;23:e13719. https://doi.org/10.1002/acm2.13719
• 30. Verdun FR, Racine D, Ott JG, et al. Image quality in CT: From physical measurements to model observer. Phys Med. 2015;31:823-843. https://doi.org/10.1016/j.ejmp.2015.08.007
• 31. Higaki T, Nakamura Y, Zhou J, et al. Deep learning reconstruction at CT: Phantom study of the image characteristic. Acad Radiol. 2020;27: 82-87. https://doi.org/10.1016/j.acra.2019.09.008
• 32. Anam C, Naufal A, Sutanto H, Dougherty G. Computational phantoms for investigating impact of noise magnitude on modulation transfer function. Indonesian J Elec Eng Comp Sci. 2022;27:1428-1437. https://doi.org/10.11591/ijeecs.v27.i3.pp1428-1437
• 33. Racine D, Becce F, Viry A, et al. Task-based characterization of deep learning image reconstruction and comparison with filtered back-projection and partial mode-based iterative reconstruction in abdominal CT: A phantom study. Phys Med. 2020;76:28-37. https://doi.org/10.1016/j.ejmp.2020.06.004
• 34. Racine D, Brat HG, Dufour B, et al. Image texture, low contrast liver lesion detectability and impact on dose: Deep learning algorithm compare to partial mode-based iterative reconstruction. Eur J Radiol. 2021;141:190808. https://doi.org/10.1016/j.ejrad.2021.109808
• 35. Greffier J, Frandon J, Durand Q, et al. Contribution of an artificial intelligence deep-learning reconstruction algorithm for dose optimization in lumbar spine examination: A phantom study. Diagn Interv Imaging. 2022;1-8. https://doi.org/10.1016/j.diii.2022.08.004
• 36. Solomon J, Daniele M, Lyu P, Samei E. Noise and spatial resolution properties of a commercially available deep learning-based CT reconstruction algorithm. Med Phys. 2020;47:3961-3970. https://doi.org/10.1002/mp.14319
• 37. Papadakis EA, Damilakis J. Technical note: Quality assessment of virtual monochromatic spectral images on a dual energy CT scanner. Phys Med. 2021;82:114-121. https://doi.org/10.1016/j.ejmp.2021.01.079
• 38. Sugisawa K, et al Technical note: Spatial resolution compensation by adjusting the reconstruction kernels for iterative reconstruction images of computed tomography. Phys Med. 2020;74:47-55. https://doi.org/10.1016/j.ejmp.2020.05.002

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).