Clinical feasibility of deep learning reconstruction in liver diffusion-weighted imaging: Improvement of image quality and impact on apparent diffusion coefficient value

被引:7
作者
Chen, Qian [1 ,2 ]
Fang, Shu [1 ]
Yang, Yuchen [3 ]
Li, Ruokun [1 ]
Deng, Rong [1 ]
Chen, Yongjun [3 ]
Ma, Di [3 ]
Lin, Huimin [1 ]
Yan, Fuhua [1 ,4 ]
机构
[1] Shanghai Jiao Tong Univ, Sch Med, Ruijin Hosp, Dept Radiol, 197 Ruijin Er Rd, Shanghai 200025, Peoples R China
[2] Tianjin Med Univ, Natl Clin Res Ctr Canc, Key Lab Canc Prevent & Therapy, Dept Radiol,Canc Inst & Hosp, Huan Hu Xi Rd, Tianjin 300060, Peoples R China
[3] Shanghai Jiao Tong Univ, Sch Med, Ruijin Hosp, Dept Gen Surg, 197 Ruijin Er Rd, Shanghai 200025, Peoples R China
[4] Shanghai Jiao Tong Univ, Coll Hlth Sci & Technol, Sch Med, Shanghai, Peoples R China
基金
中国国家自然科学基金;
关键词
Deep learning reconstruction; Diffusion weighted imaging; Apparent diffusion coefficient; NOISE-REDUCTION; MRI; ACQUISITION; ARTIFACTS; BODY;
D O I
10.1016/j.ejrad.2023.111149
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: Diffusion-weighted imaging (DWI) of the liver suffers from low resolution, noise, and artifacts. This study aimed to investigate the effect of deep learning reconstruction (DLR) on image quality and apparent diffusion coefficient (ADC) quantification of liver DWI at 3 Tesla.Method: In this prospective study, images of the liver obtained at DWI with b-values of 0 (DWI0), 50 (DWI50) and 800 s/mm(2) (DWI800) from consecutive patients with liver lesions from February 2022 to February 2023 were reconstructed with and without DLR (non-DLR). Image quality was assessed qualitatively using Likert scoring system and quantitatively using signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and liver/parenchyma boundary sharpness from region-of-interest (ROI) analysis. ADC value of lesion were measured. Phantom experiment was also performed to investigate the factors that determine the effect of DLR on ADC value. Qualitative score, SNR, CNR, boundary sharpness, and apparent diffusion coefficients (ADCs) for DWI were compared using paired t-test and Wilcoxon signed rank test. P < 0.05 was considered statistically significant.Results: A total of 85 patients with 170 lesions were included. DLR group showed a higher qualitative score than the non-DLR group. for example, with DWI800 the score was 4.77 +/- 0.52 versus 4.30 +/- 0.63 (P < 0.001). DLR group also showed higher SNRs, CNRs and boundary sharpness than the non-DLR group. DLR reduced the ADC of malignant tumors (1.105[0.904, 1.340] versus 1.114[0.904, 1.320]) (P < 0.001), but there was no significant difference in the diagnostic value of malignancy for DLR and non-DLR groups (P = 57.3). The phantom study confirmed a reduction of ADC in images with low resolution, and a stronger reduction of ADC in heterogeneous structures than in homogeneous ones (P < 0.001).Conclusions: DLR improved image quality of liver DWI. DLR reduced the ADC value of lesions, but did not affect the diagnostic performance of ADC in distinguishing malignant tumors on a 3.0-T MRI system.
引用
收藏
页数:9
相关论文
共 50 条
  • [31] Shortening Acquisition Time and Improving Image Quality for Pelvic MRI Using Deep Learning Reconstruction for Diffusion-Weighted Imaging at 1.5 T
    Herrmann, Judith
    Benkert, Thomas
    Brendlin, Andreas
    Gassenmaier, Sebastian
    Hoelldobler, Thomas
    Maennlin, Simon
    Almansour, Haidara
    Lingg, Andreas
    Weiland, Elisabeth
    Afat, Saif
    ACADEMIC RADIOLOGY, 2024, 31 (03) : 921 - 928
  • [32] Optimization and Clinical Feasibility of Free-breathing Diffusion-weighted Imaging of the Liver: Comparison with Respiratory-Triggered Diffusion-weighted Imaging
    Takayama, Yukihisa
    Nishie, Akihiro
    Asayama, Yoshiki
    Ishigami, Kousei
    Kakihara, Daisuke
    Uhijima, Yasuhiro
    Fujita, Nobuhiro
    Yoshiura, Takashi
    Takemura, Atsushi
    Obara, Makoto
    Takahara, Taro
    Honda, Hiroshi
    MAGNETIC RESONANCE IN MEDICAL SCIENCES, 2015, 14 (02) : 123 - 132
  • [33] Diagnostic Utility of Diffusion-Weighted MR Imaging and Apparent Diffusion Coefficient Value for the Diagnosis of Adrenal Tumors
    Tsushima, Yoshito
    Takahashi-Taketomi, Ayako
    Endo, Keigo
    JOURNAL OF MAGNETIC RESONANCE IMAGING, 2009, 29 (01) : 112 - 117
  • [34] Predicting liver metastasis of gastrointestinal tract cancer by diffusion-weighted imaging of apparent diffusion coefficient values
    Zheng, De-Xian
    Meng, Shu-Chun
    Liu, Qing-Jun
    Li, Chuan-Ting
    Shang, Xi-Dan
    Zhu, Yu-Seng
    Bai, Tian-Jun
    Xu, Shi-Ming
    WORLD JOURNAL OF GASTROENTEROLOGY, 2016, 22 (10) : 3031 - 3037
  • [35] Evaluating Spinal Canal Lesions Using Apparent Diffusion Coefficient Maps with Diffusion-Weighted Imaging
    Kanamoto, Hirohito
    Norimoto, Masaki
    Eguchi, Yawara
    Oikawa, Yasuhiro
    Orita, Sumihisa
    Inage, Kazuhide
    Abe, Koki
    Inoue, Masahiro
    Kinoshita, Hideyuki
    Umimura, Tomotaka
    Matsumoto, Koji
    Masuda, Yoshitada
    Furuya, Takeo
    Koda, Masao
    Aoki, Yasuchika
    Watanabe, Atsuya
    Takahashi, Kazuhisa
    Ohtori, Seiji
    ASIAN SPINE JOURNAL, 2020, 14 (03) : 312 - 319
  • [36] Diffusion-weighted imaging and apparent diffusion coefficient evaluation of herpes simplex encephalitis and Japanese encephalitis
    Sawlani, Vijay
    JOURNAL OF THE NEUROLOGICAL SCIENCES, 2009, 287 (1-2) : 221 - 226
  • [37] Abdominal apparent diffusion coefficient measurements: effect of diffusion-weighted image quality and usefulness of anisotropic images
    Yoshikawa, Takeshi
    Ohno, Yoshiharu
    Kawamitsu, Hideaki
    Ku, Yonson
    Seo, Yasushi
    Zamora, Carlos A.
    Aoyama, Nobukazu
    Sugimura, Kazuro
    MAGNETIC RESONANCE IMAGING, 2008, 26 (10) : 1415 - 1420
  • [38] Does reversal of ischemia on diffusion-weighted imaging reflect higher apparent diffusion coefficient values?
    Lutsep, HL
    Nesbit, GM
    Berger, RM
    Coshow, WR
    JOURNAL OF NEUROIMAGING, 2001, 11 (03) : 313 - 316
  • [39] Apparent diffusion coefficient of pituitary macroadenoma evaluated with line-scan diffusion-weighted imaging
    Suzuki, C.
    Maeda, M.
    Hori, K.
    Kozuka, Y.
    Sakuma, H.
    Taki, W.
    Takeda, K.
    JOURNAL OF NEURORADIOLOGY, 2007, 34 (04) : 228 - 235
  • [40] Diffusion-Weighted Imaging of Breast Masses: Comparison of Diagnostic Performance Using Various Apparent Diffusion Coefficient Parameters
    Hirano, Maki
    Satake, Hiroko
    Ishigaki, Satoko
    Ikeda, Mitsuru
    Kawai, Hisashi
    Naganawa, Shinji
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2012, 198 (03) : 717 - 722