Deep Learning-Accelerated Non-Contrast Abbreviated Liver MRI for Detecting Malignant Focal Hepatic Lesions: Dual-Center Validation

被引:2
作者
Park, So Hyun [1 ,7 ]
Choi, Moon Hyung [2 ]
Kim, Bohyun [3 ,6 ]
Lee, Hyun-Soo [4 ]
Yoon, Sungjin [1 ]
Lee, Young Joon [2 ]
Nickel, Dominik [5 ]
Benkert, Thomas [5 ]
机构
[1] Gachon Univ, Gil Med Ctr, Dept Radiol, Coll Med, Incheon, South Korea
[2] Catholic Univ Korea, Eunpyeong St Marys Hosp, Coll Med, Dept Radiol, Seoul, South Korea
[3] Catholic Univ Korea, Seoul St Marys Hosp, Coll Med, Dept Radiol, 222 Banpo Daero, Seoul 06591, South Korea
[4] Siemens Healthineers Ltd, Seoul, South Korea
[5] Siemens Healthineers AG, Diagnost Imaging, Forchheim, Germany
[6] Catholic Univ Korea, Seoul St Marys Hosp, Coll Med, Dept Radiol, 222 Banpo Daero, Seoul 06591, South Korea
[7] Seoul Natl Univ, Dept Radiol, Bundang Hosp, Seongnam, South Korea
基金
新加坡国家研究基金会;
关键词
Deep learning; Liver; Sensitivity; Magnetic resonance imaging; Hepatocellular carcinoma; HEPATOCELLULAR-CARCINOMA; DIAGNOSTIC CONFIDENCE; SUPERRESOLUTION; RECONSTRUCTION;
D O I
10.3348/kjr.2024.0862
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
Objective: To compare a deep learning (DL)-accelerated non-enhanced abbreviated MRI (AMRI(DL)) protocol with standard AMRI (AMRI(STD)) of the liver in terms of image quality and malignant focal lesion detection. Materials and methods: This retrospective study included 155 consecutive patients (110 male; mean age 62.4 +/- 11 years) from two sites who underwent standard liver MRI and additional AMRI(DL) sequences, specifically DL-accelerated single-shot fast-spin echo (SSFSEDL) and DL-accelerated diffusion-weighted imaging (DWIDL). Additional MRI phantom experiments assessed signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and apparent diffusion coefficient (ADC) values. Three reviewers evaluated AMRI(DL) and AMRI(STD) protocols for image quality using a five-point Likert scale and identified malignant hepatic lesions. Image quality scores and per-lesion sensitivities were compared between AMRI(DL) and AMRI(STD) using the Wilcoxon signed-rank test and logistic regression with generalized estimating equations, respectively. Results: Phantom experiments demonstrated comparable SNR and higher CNR for SSFSEDL compared to SSFSESTD, with similar ADC values for DWIDL and DWISTD. Among the 155 patients, 130 (83.9%) had chronic liver disease or a history of intra- or extrahepatic malignancy. Of 104 malignant focal lesions in 64 patients, 58 (55.8%) were hepatocellular carcinomas (HCCs), 38 (36.5%) were metastases, four (3.8%) were cholangiocarcinomas, and four (3.8%) were lymphomas. The pooled per-lesion sensitivity across three readers was 97.6% for AMRI(DL), comparable to 97.6% for AMRI(STD). Compared with AMRI(STD), AMRI(DL) demonstrated superior image quality regarding structural sharpness, artifacts, and noise (all P < 0.001) and reduced the average scan time by approximately 50% (2 min 29 sec vs. 4 min 11 sec). In patients with chronic liver disease, AMRI(DL) achieved a 96.6% per-lesion sensitivity for HCC detection, similar to 96.5% for AMRI(STD) (P > 0.05). Conclusion: The AMRI(DL) protocol offers comparable sensitivity for detecting malignant focal lesions, including HCC while significantly enhancing image quality and reducing scan time by approximately 50% compared to AMRI(STD).
引用
收藏
页码:333 / 345
页数:13
相关论文
共 25 条
[1]   Acquisition time reduction of diffusion-weighted liver imaging using deep learning image reconstruction [J].
Afat, Saif ;
Herrmann, Judith ;
Almansour, Haidara ;
Benkert, Thomas ;
Weiland, Elisabeth ;
Hoelldobler, Thomas ;
Nikolaou, Konstantin ;
Gassenmaier, Sebastian .
DIAGNOSTIC AND INTERVENTIONAL IMAGING, 2023, 104 (04) :178-184
[2]   Combined Deep Learning-based Super-Resolution and Partial Fourier Reconstruction for Gradient Echo Sequences in Abdominal MRI at 3 Tesla: Shortening Breath-Hold Time and Improving Image Sharpness and Lesion Conspicuity [J].
Almansour, Haidara ;
Herrmann, Judith ;
Gassenmaier, Sebastian ;
Lingg, Andreas ;
Nickel, Marcel Dominik ;
Kannengiesser, Stephan ;
Arberet, Simon ;
Othman, Ahmed E. ;
Afat, Saif .
ACADEMIC RADIOLOGY, 2023, 30 (05) :863-872
[3]   Deep Learning-Based Superresolution Reconstruction for Upper Abdominal Magnetic Resonance Imaging An Analysis of Image Quality, Diagnostic Confidence, and Lesion Conspicuity [J].
Almansour, Haidara ;
Gassenmaier, Sebastian ;
Nickel, Dominik ;
Kannengiesser, Stephan ;
Afat, Saif ;
Weiss, Jakob ;
Hoffmann, Rudiger ;
Othman, Ahmed E. .
INVESTIGATIVE RADIOLOGY, 2021, 56 (08) :509-516
[4]   Abbreviated MRI for Hepatocellular Carcinoma Screening and Surveillance [J].
An, Julie Y. ;
Pena, Miguel A. ;
Cunha, Guilherme M. ;
Booker, Michael T. ;
Taouli, Bachir ;
Yokoo, Takeshi ;
Sirlin, Claude B. ;
Fowler, Kathryn J. .
RADIOGRAPHICS, 2020, 40 (07) :1916-1931
[5]   Clinical feasibility of accelerated diffusion weighted imaging of the abdomen with deep learning reconstruction: Comparison with conventional diffusion weighted imaging [J].
Bae, Sung Hwan ;
Hwang, Jiyoung ;
Hong, Seong Sook ;
Lee, Eun Ji ;
Jeong, Jewon ;
Benkert, Thomas ;
Sung, JaeKon ;
Arberet, Simon .
EUROPEAN JOURNAL OF RADIOLOGY, 2022, 154
[6]   Liver lesion detection and characterization: Role of diffusion-weighted imaging [J].
Galea, Nicola ;
Cantisani, Vito ;
Taouli, Bachir .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2013, 37 (06) :1260-1276
[7]   Deep Learning Applications in Magnetic Resonance Imaging: Has the Future Become Present? [J].
Gassenmaier, Sebastian ;
Kuestner, Thomas ;
Nickel, Dominik ;
Herrmann, Judith ;
Hoffmann, Ruediger ;
Almansour, Haidara ;
Afat, Saif ;
Nikolaou, Konstantin ;
Othman, Ahmed E. .
DIAGNOSTICS, 2021, 11 (12)
[8]   Accelerated T2-weighted MRI of the liver at 3 T using a single-shot technique with deep learning-based image reconstruction: impact on the image quality and lesion detection [J].
Ginocchio, Luke A. ;
Smereka, Paul N. ;
Tong, Angela ;
Prabhu, Vinay ;
Nickel, Dominik ;
Arberet, Simon ;
Chandarana, Hersh ;
Shanbhogue, Krishna P. .
ABDOMINAL RADIOLOGY, 2023, 48 (01) :282-290
[9]   Statistical Methods for the Analysis of Inter-Reader Agreement Among Three or More Readers [J].
Han, Kyunghwa ;
Ryu, Leeha .
KOREAN JOURNAL OF RADIOLOGY, 2024, 25 (04) :325-327
[10]   Evaluation of HASTE T2 weighted image with reduced echo time for detecting focal liver lesions in patients at risk of developing hepatocellular carcinoma [J].
Han, Seungchul ;
Lee, Jeong Min ;
Kim, Se Woo ;
Park, Sungeun ;
Nickel, Marcel Dominik ;
Yoon, Jeong Hee .
EUROPEAN JOURNAL OF RADIOLOGY, 2022, 157