Deep learning reconstruction vs standard reconstruction for abdominal CT: the influence of BMI

被引:3
|
作者
Wang, Huixia [1 ]
Yue, Songwei [1 ]
Liu, Nana [1 ]
Chen, Yan [1 ]
Zhan, Pengchao [1 ]
Liu, Xing [1 ]
Shang, Bo [1 ]
Wang, Luotong [2 ]
Li, Zhen [3 ]
Gao, Jianbo [1 ]
Lyu, Peijie [1 ]
机构
[1] Zhengzhou Univ, Affiliated Hosp 1, Dept Radiol, 1 Eastern Jianshe Rd, Zhengzhou 450052, Henan, Peoples R China
[2] GE Healthcare China, CT Imaging Res Ctr, Beijing 100176, Peoples R China
[3] Zhengzhou Univ, Dept Intervent Radiol, Affiliated Hosp 1, 1 Eastern Jianshe Rd, Zhengzhou 450052, Henan, Peoples R China
关键词
Deep learning; Radiation dosage; Image processing; computer-assisted; Radiography; abdominal; Tomography; X-ray computed;
D O I
10.1007/s00330-023-10179-0
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
ObjectiveThis study aimed to evaluate the image quality and lesion conspicuity of the deep learning image reconstruction (DLIR) algorithm compared with standard image reconstruction algorithms on abdominal enhanced computed tomography (CT) scanning with a wide range of body mass indexes (BMIs).MethodsA total of 112 participants who underwent contrast-enhanced abdominal CT scans were divided into three groups according to BMIs: the 80-kVp group (BMI <= 23.9 kg/m2), 100-kVp group (BMI 24-28.9 kg/m2), and 120-kVp group (BMI >= 29 kg/m2). All images were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction-V of 50% level (IR), and DLIR at low, medium, and high levels (DL, DM, and DH, respectively). Subjective noise, artifact, overall image quality, and low- and high-contrast hepatic lesion conspicuity were all graded on a 5-point scale. The CT attenuation value (in HU), image noise, and contrast-to-noise ratio (CNR) were quantified and compared.ResultsDM and DH improved the qualitative and quantitative parameters compared with FBP and IR for all three BMI groups. DH had the lowest image noise and highest CNR value, while DM had the highest subjective overall image quality and low- and high-contrast lesion conspicuity scores for the three BMI groups. Based on the FBP, the improvement in image quality and lesion conspicuity of DM and DH images was greater in the 80-kVp group than in the 100-kVp and 120-kVp groups.ConclusionFor all BMIs, DLIR improves both image quality and hepatic lesion conspicuity, of which DM would be the best choice to balance both.Clinical relevance statementThe study suggests that utilizing DLIR, particularly at the medium level, can significantly enhance image quality and lesion visibility on abdominal CT scans across a wide range of BMIs.Key Points center dot DLIR improved the image quality and lesion conspicuity across a wide range of BMIs.center dot DLIR at medium level had the highest subjective parameters and lesion conspicuity scores among all reconstruction levels.center dot On the basis of the FBP, the 80-kVp group had improved image quality and lesion conspicuity more than the 100-kVp and 120-kVp groups.Key Points center dot DLIR improved the image quality and lesion conspicuity across a wide range of BMIs.center dot DLIR at medium level had the highest subjective parameters and lesion conspicuity scores among all reconstruction levels.center dot On the basis of the FBP, the 80-kVp group had improved image quality and lesion conspicuity more than the 100-kVp and 120-kVp groups.Key Points center dot DLIR improved the image quality and lesion conspicuity across a wide range of BMIs.center dot DLIR at medium level had the highest subjective parameters and lesion conspicuity scores among all reconstruction levels.center dot On the basis of the FBP, the 80-kVp group had improved image quality and lesion conspicuity more than the 100-kVp and 120-kVp groups.
引用
收藏
页码:1905 / 1920
页数:16
相关论文
共 50 条
  • [1] Deep learning reconstruction vs standard reconstruction for abdominal CT: the influence of BMI
    Huixia Wang
    Songwei Yue
    Nana Liu
    Yan Chen
    Pengchao Zhan
    Xing Liu
    Bo Shang
    Luotong Wang
    Zhen Li
    Jianbo Gao
    Peijie Lyu
    [J]. European Radiology, 2024, 34 : 1614 - 1623
  • [2] ABDOMEN PELVIS - Deep Learning Reconstruction of CT Images in Patients with different BMI
    Grawert, Stephanie
    [J]. ROFO-FORTSCHRITTE AUF DEM GEBIET DER RONTGENSTRAHLEN UND DER BILDGEBENDEN VERFAHREN, 2024, 196 (08): : 777 - 778
  • [3] CT iterative vs deep learning reconstruction: comparison of noise and sharpness
    Park, Chankue
    Choo, Ki Seok
    Jung, Yunsub
    Jeong, Hee Seok
    Hwang, Jae-Yeon
    Yun, Mi Sook
    [J]. EUROPEAN RADIOLOGY, 2021, 31 (05) : 3156 - 3164
  • [4] CT iterative vs deep learning reconstruction: comparison of noise and sharpness
    Chankue Park
    Ki Seok Choo
    Yunsub Jung
    Hee Seok Jeong
    Jae-Yeon Hwang
    Mi Sook Yun
    [J]. European Radiology, 2021, 31 : 3156 - 3164
  • [5] Image Quality and Lesion Detection on Deep Learning Reconstruction and Iterative Reconstruction of Submillisievert Chest and Abdominal CT
    Singh, Ramandeep
    Digumarthy, Subba R.
    Muse, Victorine V.
    Kambadakone, Avinash R.
    Blake, Michael A.
    Tabari, Azadeh
    Hoi, Yiemeng
    Akino, Naruomi
    Angel, Erin
    Madan, Rachna
    Kalra, Mannudeep K.
    [J]. AMERICAN JOURNAL OF ROENTGENOLOGY, 2020, 214 (03) : 566 - 573
  • [6] The future of CT: deep learning reconstruction
    McLeavy, C. M.
    Chunara, M. H.
    Gravell, R. J.
    Rauf, A.
    Cushnie, A.
    Talbot, C. Staley
    Hawkins, R. M.
    [J]. CLINICAL RADIOLOGY, 2021, 76 (06) : 407 - 415
  • [7] Reduced-Dose Deep Learning Reconstruction for Abdominal CT of Liver Metastases
    Jensen, Corey T.
    Gupta, Shiva
    Saleh, Mohammed M.
    Liu, Xinming
    Wong, Vincenzo K.
    Salem, Usama
    Qiao, Wei
    Samei, Ehsan
    Wagner-Bartak, Nicolaus A.
    [J]. RADIOLOGY, 2022, 303 (01) : 90 - 98
  • [8] Assessing the Effects of Deep Learning Reconstruction on Abdominal CT Without Arm Elevation
    Fujita, Nana
    Yasaka, Koichiro
    Katayama, Akira
    Ohtake, Yuta
    Konishiike, Mao
    Abe, Osamu
    [J]. CANADIAN ASSOCIATION OF RADIOLOGISTS JOURNAL-JOURNAL DE L ASSOCIATION CANADIENNE DES RADIOLOGISTES, 2023, 74 (04): : 688 - 694
  • [9] Correction to: CT iterative vs deep learning reconstruction: comparison of noise and sharpness
    Chankue Park
    Ki Seok Choo
    Yunsub Jung
    Hee Seok Jeong
    Jae-Yeon Hwang
    Mi Sook Yun
    [J]. European Radiology, 2021, 31 : 4410 - 4411
  • [10] Deep learning reconstruction allows low-dose imaging while maintaining image quality: comparison of deep learning reconstruction and hybrid iterative reconstruction in contrast-enhanced abdominal CT
    Tamura, Akio
    Mukaida, Eisuke
    Ota, Yoshitaka
    Nakamura, Iku
    Arakita, Kazumasa
    Yoshioka, Kunihiro
    [J]. QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2022, 12 (05) : 2977 - 2984