Deep learning-based iodine contrast-augmenting algorithm for low-contrast-dose liver CT to assess hypovascular hepatic metastasis

被引:6
作者
Lee, Taehee [1 ]
Yoon, Jeong Hee [1 ,2 ,3 ]
Park, Jin Young [4 ]
Lee, Jihyuk [1 ]
Choi, Jae Won [2 ,5 ]
Ahn, Chulkyun [6 ,7 ]
Lee, Jeong Min [1 ,2 ,3 ]
机构
[1] Seoul Natl Univ Hosp, Dept Radiol, Seoul, South Korea
[2] Seoul Natl Univ, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea
[3] Seoul Natl Univ, Med Res Ctr, Inst Radiat Med, Seoul, South Korea
[4] Inje Univ, Busan Paik Hosp, Coll Med, Dept Radiol, Busan, South Korea
[5] Armed Forces Yangju Hosp, Dept Radiol, Yangju, South Korea
[6] Seoul Natl Univ, Grad Sch Convergence Sci & Technol, Dept Transdisciplinary Studies, Program Biomed Radiat Sci, Seoul, South Korea
[7] ClariPi Res, Seoul, South Korea
关键词
Contrast media; Deep learning; Liver; Neoplasm metastasis; X-ray computed tomography; DUAL-ENERGY CT; LESIONS; CANCER;
D O I
10.1007/s00261-023-04039-0
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
Purpose To investigate the image quality and diagnostic performance of low-contrast-dose liver CT using a deep learning based iodine contrast-augmenting algorithm (DLICA) for hypovascular hepatic metastases.Methods This retrospective study included 128 patients who underwent contrast-enhanced dual-energy CT for hepatic metastasis surveillance between July 2019 and June 2022 using a 30% reduced iodine contrast dose in the portal phase. Three image types were reconstructed: 50-keV virtual monoenergetic images (50-keV VMI); linearly blended images simulating 120-kVp images (120-kVp); and post-processed 120-kVp images using DLICA (DLICA 120-kVp). Three reviewers evaluated lesion conspicuity, image contrast, and subjective image noise. We also measured image noise, contrast-to-noise ratios (CNRs), and signal-to-noise ratios (SNRs). The diagnostic performance for hepatic metastases was evaluated using a jackknife alternative free-response receiver operating characteristic method with the consensus of two independent radiologists as the reference standard.Results DLICA 120-kVp demonstrated significantly higher CNR of lesions to liver (5.7 +/- 3.1 vs. 3.8 +/- 2.1 vs. 3.8 +/- 2.1) and higher SNR compared with 50-keV VMI and 120-kVp (p < 0.001 for all). DLICA 120-kVp had significantly lower image noise than 50-kVp VMI for all regions (p < 0.001 for all). DLICA 120-kVp also exhibited superior lesion conspicuity (4.0 [3.3-4.3] vs. 3.7 [3.0-4.0] vs. 3.7 [3.0-4.0]), higher image contrast, and lower subjective image noise compared with 50-keV VMI and 120-kVp (p < 0.001 for all). Although there was no significant difference in the figure of merit for lesion diagnosis among the three methods (p = 0.11), DLICA 120-kVp had a significantly higher figure of merit for lesions with a diameter < 20 mm than 50-keV VMI (0.677 vs. 0.648, p = 0.007). On a per-lesion basis, DLICA 120-kVp also demonstrated higher sensitivity than the 50-keV VMI (81.2% vs. 72.9%, p < 0.001). The specificities per lesion were not significantly different among the three algorithms (p = 0.15).Conclusion DLICA at 120-kVp provided superior lesion conspicuity and image quality and similar diagnostic performance for hypovascular hepatic metastases compared with 50-keV VMI.
引用
收藏
页码:3430 / 3440
页数:11
相关论文
共 24 条
  • [1] Review of Clinical Applications for Virtual Monoenergetic Dual-Energy CT
    Albrecht, Moritz H.
    Vogl, Thomas J.
    Martin, Simon S.
    Nance, John W.
    Duguay, Taylor M.
    Wichmann, Julian L.
    De Cecco, Carlo N.
    Varga-Szemes, Akos
    van Assen, Marly
    Tesche, Christian
    Schoepf, U. Joseph
    [J]. RADIOLOGY, 2019, 293 (02) : 260 - 271
  • [2] A software tool for increased efficiency in observer performance studies in radiology
    Börjesson, S
    Håkansson, M
    Båth, M
    Kheddache, S
    Svensson, S
    Tingberg, A
    Grahn, A
    Ruschin, M
    Hemdal, B
    Mattsson, S
    Månsson, LG
    [J]. RADIATION PROTECTION DOSIMETRY, 2005, 114 (1-3) : 45 - 52
  • [3] Can dual-energy computed tomography improve visualization of hypoenhancing liver lesions in portal venous phase? Assessment of advanced image-based virtual monoenergetic images
    Caruso, Damiano
    De Cecco, Carlo N.
    Schoepf, U. Joseph
    Schaefer, Amanda R.
    Leland, Parker W.
    Johnson, Dustin
    Laghi, Andrea
    Hardie, Andrew D.
    [J]. CLINICAL IMAGING, 2017, 41 : 118 - 124
  • [4] Presurgical Evaluation of Pancreatic Cancer: A Comprehensive Imaging Comparison of CT Versus MRI
    Chen, Fang-Ming
    Ni, Jian-Ming
    Zhang, Zhui-Yang
    Zhang, Lei
    Li, Bin
    Jiang, Chun-Juan
    [J]. AMERICAN JOURNAL OF ROENTGENOLOGY, 2016, 206 (03) : 526 - 535
  • [5] Dual-Energy CT: Oncologic Applications
    De Cecco, Carlo Nicola
    Darnell, Anna
    Rengo, Marco
    Muscogiuri, Giuseppe
    Bellini, Davide
    Ayuso, Carmen
    Laghi, Andrea
    [J]. AMERICAN JOURNAL OF ROENTGENOLOGY, 2012, 199 (05) : S98 - S105
  • [6] Jointly Optimized Deep Neural Networks to Synthesize Monoenergetic Images from Single-Energy CT Angiography for Improving Classification of Pulmonary Embolism
    Fink, Matthias A.
    Seibold, Constantin
    Kauczor, Hans-Ulrich
    Stiefelhagen, Rainer
    Kleesiek, Jens
    [J]. DIAGNOSTICS, 2022, 12 (05)
  • [7] Deep-learning-based direct synthesis of low-energy virtual monoenergetic images with multi-energy CT
    Gong, Hao
    Marsh, Jeffrey F.
    D'Souza, Karen N.
    Huber, Nathan R.
    Rajendran, Kishore
    Fletcher, Joel G.
    McCollough, Cynthia H.
    Leng, Shuai
    [J]. JOURNAL OF MEDICAL IMAGING, 2021, 8 (05)
  • [8] Low kV versus dual-energy virtual monoenergetic CT imaging for proven liver lesions: what are the advantages and trade-offs in conspicuity and image quality? A pilot study
    Hanson, G. Jay
    Michalak, Gregory J.
    Childs, Robert
    McCollough, Brian
    Kurup, Anil N.
    Hough, David M.
    Frye, Judson M.
    Fidler, Jeff L.
    Venkatesh, Sudhakar K.
    Leng, Shuai
    Yu, Lifeng
    Halaweish, Ahmed F.
    Harmsen, W. Scott
    McCollough, Cynthia H.
    Fletcher, J. G.
    [J]. ABDOMINAL RADIOLOGY, 2018, 43 (06) : 1404 - 1412
  • [9] Contrast agent dose reduction in computed tomography with deep learning using a conditional generative adversarial network
    Haubold, Johannes
    Hosch, Rene
    Umutlu, Lale
    Wetter, Axel
    Haubold, Patrizia
    Radbruch, Alexander
    Forsting, Michael
    Nensa, Felix
    Koitka, Sven
    [J]. EUROPEAN RADIOLOGY, 2021, 31 (08) : 6087 - 6095
  • [10] 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