Image Quality and Diagnostic Performance of Accelerated 2D Hip MRI with Deep Learning Reconstruction Based on a Deep Iterative Hierarchical Network

被引:1
|
作者
Herrmann, Judith [1 ]
Afat, Saif [1 ]
Gassenmaier, Sebastian [1 ]
Koerzdoerfer, Gregor [2 ]
Lingg, Andreas [1 ]
Almansour, Haidara [1 ]
Nickel, Dominik [2 ]
Werner, Sebastian [1 ]
机构
[1] Eberhard Karls Univ Tuebingen, Dept Diagnost & Intervent Radiol, Hoppe Seyler Str 3, D-72076 Tubingen, Germany
[2] Siemens Healthcare GmbH, MR Applicat Predev, Allee Roethelheimpk 2, D-91052 Erlangen, Germany
关键词
magnetic resonance imaging; deep learning reconstruction; image processing; diagnostic imaging; hip; CONVOLUTIONAL NEURAL-NETWORKS; SPIN-ECHO SEQUENCE; KNEE; PROTOCOL; SPACE;
D O I
10.3390/diagnostics13203241
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Objectives: Hip MRI using standard multiplanar sequences requires long scan times. Accelerating MRI is accompanied by reduced image quality. This study aimed to compare standard two-dimensional (2D) turbo spin echo (TSE) sequences with accelerated 2D TSE sequences with deep learning (DL) reconstruction (TSEDL) for routine clinical hip MRI at 1.5 and 3 T in terms of feasibility, image quality, and diagnostic performance.Material and Methods: In this prospective, monocentric study, TSEDL was implemented clinically and evaluated in 14 prospectively enrolled patients undergoing a clinically indicated hip MRI at 1.5 and 3T between October 2020 and May 2021. Each patient underwent two examinations: For the first exam, we used standard sequences with generalized autocalibrating partial parallel acquisition reconstruction (TSES). For the second exam, we implemented prospectively undersampled TSE sequences with DL reconstruction (TSEDL). Two radiologists assessed the TSEDL and TSES regarding image quality, artifacts, noise, edge sharpness, diagnostic confidence, and delineation of anatomical structures using an ordinal five-point Likert scale (1 = non-diagnostic; 2 = poor; 3 = moderate; 4 = good; 5 = excellent). Both sequences were compared regarding the detection of common pathologies of the hip. Comparative analyses were conducted to assess the differences between TSEDL and TSES.Results: Compared with TSES, TSEDL was rated to be significantly superior in terms of image quality (p <= 0.020) with significantly reduced noise (p <= 0.001) and significantly improved edge sharpness (p = 0.003). No difference was found between TSES and TSEDL concerning the extent of artifacts, diagnostic confidence, or the delineation of anatomical structures (p > 0.05). Example acquisition time reductions for the TSE sequences of 52% at 3 Tesla and 70% at 1.5 Tesla were achieved.Conclusion: TSEDL of the hip is clinically feasible, showing excellent image quality and equivalent diagnostic performance compared with TSES, reducing the acquisition time significantly.
引用
收藏
页数:11
相关论文
共 50 条
  • [41] Iterative reconstruction vs deep learning image reconstruction: comparison of image quality and diagnostic accuracy of arterial stenosis in low--dose lower extremity CT angiography
    Qu, Tingting
    Guo, Yinxia
    Li, Jianying
    Cao, Le
    Li, Yanan
    Chen, Lihong
    Sun, Jingtao
    Lu, Xueni
    Guo, Jianxin
    BRITISH JOURNAL OF RADIOLOGY, 2022, 95 (1140):
  • [42] Diagnostic performance of deep learning-based reconstruction algorithm in 3D MR neurography
    Ensle, Falko
    Kaniewska, Malwina
    Tiessen, Anja
    Lohezic, Maelene
    Getzmann, Jonas M.
    Guggenberger, Roman
    SKELETAL RADIOLOGY, 2023, 52 (12) : 2409 - 2418
  • [43] Accelerated Cine Cardiac MRI Using Deep Learning-Based Reconstruction: A Systematic Evaluation
    Pednekar, Amol
    Kocaoglu, Murat
    Wang, Hui
    Tanimoto, Aki
    Tkach, Jean A.
    Lang, Sean
    Taylor, Michael D.
    JOURNAL OF MAGNETIC RESONANCE IMAGING, 2024, 60 (02) : 640 - 650
  • [44] Deep-learning-based quality filtering of mechanically exfoliated 2D crystals
    Yu Saito
    Kento Shin
    Kei Terayama
    Shaan Desai
    Masaru Onga
    Yuji Nakagawa
    Yuki M. Itahashi
    Yoshihiro Iwasa
    Makoto Yamada
    Koji Tsuda
    npj Computational Materials, 5
  • [45] Deep-learning-based quality filtering of mechanically exfoliated 2D crystals
    Saito, Yu
    Shin, Kento
    Terayama, Kei
    Desai, Shaan
    Onga, Masaru
    Nakagawa, Yuji
    Itahashi, Yuki M.
    Iwasa, Yoshihiro
    Yamada, Makoto
    Tsuda, Koji
    NPJ COMPUTATIONAL MATERIALS, 2019, 5 (1)
  • [46] 2D-3D Reconstruction of a Femur by Single X-Ray Image Based on Deep Transfer Learning Network
    Ha, Ho -Gun
    Lee, Jinhan
    Jung, Gu-Hee
    Hong, Jaesung
    Lee, Hyunki
    IRBM, 2024, 45 (01)
  • [47] Deep Learning Reconstruction of Diffusion-weighted MRI Improves Image Quality for Prostatic Imaging
    Ueda, Takahiro
    Ohno, Yoshiharu
    Yamamoto, Kaori
    Murayama, Kazuhiro
    Ikedo, Masato
    Yui, Masao
    Hanamatsu, Satomu
    Tanaka, Yumi
    Obama, Yuki
    Ikeda, Hirotaka
    Toyama, Hiroshi
    RADIOLOGY, 2022, 303 (02)
  • [48] Deep learning for efficient reconstruction of highly accelerated 3D FLAIR MRI in neurological deficits
    Liebrand, Luka C.
    Karkalousos, Dimitrios
    Poirion, Emilie
    Emmer, Bart J.
    Roosendaal, Stefan D.
    Marquering, Henk A.
    Majoie, Charles B. L. M.
    Savatovsky, Julien
    Caan, Matthan W. A.
    MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE, 2025, 38 (01): : 1 - 12
  • [49] Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction
    Yoo, Hyunsuk
    Moon, Hee Eun
    Kim, Soojin
    Kim, Da Hee
    Choi, Young Hun
    Cheon, Jeong-Eun
    Lee, Joon Sung
    Lee, Seunghyun
    KOREAN JOURNAL OF RADIOLOGY, 2025, 26 (02) : 180 - 192
  • [50] 2D shape reconstruction of irregular particles with deep learning based on interferometric particle imaging
    Fan, Wenbo
    Sun, Jinlu
    Qiu, Yue
    Wu, Yuhang
    Chen, Shengyong
    APPLIED OPTICS, 2022, 61 (32) : 9595 - 9602