Deep learning reconstruction for contrast-enhanced CT of the upper abdomen: similar image quality with lower radiation dose in direct comparison with iterative reconstruction

European Radiology - Tập 31 - Trang 5533-5543 - 2021
Ju Gang Nam1, Jung Hee Hong1, Da Som Kim2, Jiseon Oh1, Jin Mo Goo1,3
1Department of Radiology, Seoul National University Hospital and College of Medicine, and Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea
2Department of Radiology, Busan Paik Hospital, Inje University College of Medicine, Busan, Republic of Korea
3Cancer Research Institute, Seoul National University College of Medicine, Seoul, Republic of Korea

Tóm tắt

To evaluate the effect of a commercial deep learning algorithm on the image quality of chest CT, focusing on the upper abdomen. One hundred consecutive patients who simultaneously underwent contrast-enhanced chest and abdominal CT were collected. The radiation dose was optimized for each scan (mean CTDIvol: chest CT, 3.19 ± 1.53 mGy; abdominal CT, 7.10 ± 1.88 mGy). Three image sets were collected: chest CT reconstructed with an adaptive statistical iterative reconstruction (ASiR-CHT; 50% blending), chest CT with a deep learning algorithm (DLIR-CHT), and abdominal CT with ASiR (ASiR-ABD; 40% blending). Afterwards, the images covering the upper abdomen were extracted, and image noise, the signal-to-noise ratio (SNR), and the contrast-to-noise ratio (CNR) were measured. For subjective evaluation, three radiologists independently assessed noise, spatial resolution, presence of artifacts, and overall image quality. Additionally, readers selected the most preferable reconstruction technique among three image sets for each case. The average measured noise for DLIR-CHT, ASiR-CHT, and ASiR-ABD was 8.01 ± 2.81, 14.8 ± 2.56, and 12.3 ± 2.28, respectively (p < .001). Deep learning–based image reconstruction (DLIR) also showed the best SNR and CNR (p < .001). However, in the subjective analysis, ASiR-ABD showed less subjective noise than DLIR (2.94 ± 0.23 vs. 2.87 ± 0.26; p < .001), while DLIR showed better spatial resolution (2.60 ± 0.34 vs. 2.44 ± 0.31; p = .02). ASiR-ABD showed a better overall image quality (p = .001), but two of the three readers preferred DLIR more frequently. With < 50% of the radiation dose, DLIR chest CT showed comparable image quality in the upper abdomen to that of dedicated abdominal CT and was preferred by most readers. • With < 50% radiation dose, a deep learning algorithm applied to contrast-enhanced chest CT exhibited better image noise and signal-to-noise ratio than standard abdominal CT with the ASiR technique. • Pooled readers mostly preferred deep learning algorithm–reconstructed contrast-enhanced chest CT reconstructed using a standard ASiR-reconstructed abdominal CT. • Reconstruction algorithm–induced distortion artifacts were more frequently observed on deep learning algorithm–reconstructed images, but diagnostic difficulty was reported in only 0.3% of cases.

Tài liệu tham khảo

Mettler FA Jr, Mahesh M, Bhargavan-Chatfield M et al (2020) Patient exposure from radiologic and nuclear medicine procedures in the United States: procedure volume and effective dose for the period 2006–2016. Radiology 295:418–427 Deak PD, Smal Y, Kalender WA (2010) Multisection CT protocols: sex-and age-specific conversion factors used to determine effective dose from dose-length product. Radiology 257:158–166 Prakash P, Kalra MK, Kambadakone AK et al (2010) Reducing abdominal CT radiation dose with adaptive statistical iterative reconstruction technique. Invest Radiol 45:202–210 Singh S, Kalra MK, Shenoy-Bhangle AS et al (2012) Radiation dose reduction with hybrid iterative reconstruction for pediatric CT. Radiology 263:537–546 Sagara Y, Hara AK, Pavlicek W, Silva AC, Paden RG, Wu Q (2010) Abdominal CT: comparison of low-dose CT with adaptive statistical iterative reconstruction and routine-dose CT with filtered back projection in 53 patients. AJR Am J Roentgenol 195:713–719 Park C, Choo KS, Jung Y, Jeong HS, Hwang J-Y, Yun MS (2020) CT iterative vs deep learning reconstruction: comparison of noise and sharpness. Eur Radiol ahead of print. https://doi.org/10.1007/s00330-020-07535-9 Greffier J, Hamard A, Pereira F et al (2020) Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study. Eur Radiol 30:3951–3959 Hsieh J, Liu E, Nett B, Tang J, Thibault J-B, Sahney S (2019) A new era of image reconstruction: TrueFidelity™. White Paper (JB68676XX), GE Healthcare Vardhanabhuti V, Loader RJ, Mitchell GR, Riordan RD, Roobottom CA (2013) Image quality assessment of standard-and low-dose chest CT using filtered back projection, adaptive statistical iterative reconstruction, and novel model-based iterative reconstruction algorithms. AJR Am J Roentgenol 200:545–552 Hu X, Ding X, Wu R, Zhang M (2011) Radiation dose of non-enhanced chest CT can be reduced 40% by using iterative reconstruction in image space. Clin Radiol 66:1023–1029 Marin D, Nelson RC, Schindera ST et al (2010) Low-tube-voltage, high-tube-current multidetector abdominal CT: improved image quality and decreased radiation dose with adaptive statistical iterative reconstruction algorithm—initial clinical experience. Radiology 254:145–153 Nakayama Y, Awai K, Funama Y et al (2005) Abdominal CT with low tube voltage: preliminary observations about radiation dose, contrast enhancement, image quality, and noise. Radiology 237:945–951 Hur S, Lee JM, Kim SJ, Park JH, Han JK, Choi BI (2012) 80-kVp CT using iterative reconstruction in image space algorithm for the detection of hypervascular hepatocellular carcinoma: phantom and initial clinical experience. Korean J Radiol 13:152–164 Wong K, Paulson EK, Nelson RC (2001) Breath-hold three-dimensional CT of the liver with multi-detector row helical CT. Radiology 219:75–79 McClellan TR, Motosugi U, Middleton MS et al (2017) Intravenous gadoxetate disodium administration reduces breath-holding capacity in the hepatic arterial phase: a multi-center randomized placebo-controlled trial. Radiology 282:361–368 Stengel D, Ottersbach C, Matthes G et al (2012) Accuracy of single-pass whole-body computed tomography for detection of injuries in patients with major blunt trauma. CMAJ 184:869–876 Leung V, Sastry A, Woo T, Jones H (2015) Implementation of a split-bolus single-pass CT protocol at a UK major trauma centre to reduce excess radiation dose in trauma pan-CT. Clin Radiol 70:1110–1115 Ptak T, Rhea JT, Novelline RA (2003) Radiation dose is reduced with a single-pass whole-body multi-detector row CT trauma protocol compared with a conventional segmented method: initial experience. Radiology 229:902–905 Sedlic A, Chingkoe CM, Tso DK, Galea-Soler S, Nicolaou S (2013) Rapid imaging protocol in trauma: a whole-body dual-source CT scan. Emerg Radiol 20:401–408 Long B, April MD, Summers S, Koyfman A (2017) Whole body CT versus selective radiological imaging strategy in trauma: an evidence-based clinical review. Am J Emerg Med 35:1356–1362 Jeavons C, Hacking C, Beenen LF et al (2018) A review of split-bolus single-pass CT in the assessment of trauma patients. Emerg Radiol 25:367–374 Scialpi M, Schiavone R, D'Andrea A et al (2015) Single-phase whole-body 64-MDCT split-bolus protocol for pediatric oncology: diagnostic efficacy and dose radiation. Anticancer Res 35:3041–3048 Israel GM, Herlihy S, Rubinowitz AN, Cornfeld D, Brink J (2008) Does a combination of dose modulation with fast gantry rotation time limit CT image quality? AJR Am J Roentgenol 191:140–144