Share：
Share this content in WeChat
X
[Chinese][PDF]4724
• Review •
Research progresses of artificial intelligence in imaging of liver fibrosis
LI Fukai  LIU Jianli 

Cite this article as: LI F K, LIU J L. Research progresses of artificial intelligence in imaging of liver fibrosis[J]. Chin J Magn Reson Imaging, 2024, 15(2): 219-223. DOI:10.12015/issn.1674-8034.2024.02.036.


[Abstract] Liver fibrosis is a necessary pathway for chronic liver disease to progress to cirrhosis or even liver cancer. Effective clinical interventions can reverse liver fibrosis, so timely and accurate assessment of the severity of liver fibrosis is of great significance to the treatment and prognosis of patients with liver fibrosis. Liver histopathology is an important basis for definitive diagnosis and measurement of the degree of liver fibrosis, but it is invasive and the results are affected by the site of puncture, which makes it less accurate and comprehensive. It is important to explore a non-invasive, comprehensive and accurate assessment model. Artificial intelligence constructs disease assessment and prediction models by analyzing massive imaging data and continuous self-learning, and analyzes and researches the changing law of imaging in the development of diseases. With the rapid development of imaging technology and computer science, AI technology based on imaging has shown its outstanding clinical value and application potential in non-invasive diagnosis and staging of liver fibrosis.In this paper, we provide an overview of AI technology in liver fibrosis imaging (ultrasound, computed tomography, MRI) at home and abroad in recent years, aiming to introduce the current status of the development of AI in this field and attempt to analyze the current problems faced, with a view to achieving noninvasive and precise assessment of liver fibrosis and providing imaging support for individualized and precise clinical medical treatment.
[Keywords] liver fibrosis；chronic liver disease；artificial intelligence；imaging；magnetic resonance imaging；quantitative evaluation

LI Fukai1, 2, 3, 4   LIU Jianli1, 2, 3, 4*  

1 Department of Radiology, Lanzhou University Second Hospital, Lanzhou 730030, China

2 Second Clinical School, Lanzhou University, Lanzhou 730030, China

3 Key Laboratory of Medical Imaging of Gansu Province, Lanzhou 730030, China

4 Gansu International Scientific and Technological Cooperation Base of Medical lmaging Artificial Intelligence, Lanzhou 730030, China

Corresponding author: LIU J L, E-mail: liujl_1219@163.com

Conflicts of interest   None.

Received  2023-11-24
Accepted  2024-01-15
DOI: 10.12015/issn.1674-8034.2024.02.036
Cite this article as: LI F K, LIU J L. Research progresses of artificial intelligence in imaging of liver fibrosis[J]. Chin J Magn Reson Imaging, 2024, 15(2): 219-223. DOI:10.12015/issn.1674-8034.2024.02.036.

[1]
DEVARBHAVI H, ASRANI S K, ARAB J P, et al. Global burden of liver disease: 2023 update[J]. J Hepatol, 2023, 79(2): 516-537. DOI: 10.1016/j.jhep.2023.03.017.
[2]
ANNALISA B, EMMANUUIL T, JEROME B, et al. EASL Clinical Practice Guidelines on non-invasive tests for evaluation of liver disease severity and prognosis-2021 update[J]. J Hepatol, 2021, 75(3): 659-689. DOI: 10.1016/j.jhep.2021.05.025.
[3]
KISSELEVA T, BRENNER D. Molecular and cellular mechanisms of liver fibrosis and its regression[J]. Nat Rev Gastroenterol Hepatol, 2021, 18(3): 151-166. DOI: 10.1038/s41575-020-00372-7.
[4]
FRIEDMAN S L, PINZANI M. Hepatic fibrosis 2022: Unmet needs and a blueprint for the future[J]. Hepatology, 2022, 75(2): 473-488. DOI: 10.1002/hep.32285.
[5]
Chinese Medical Association Hepatology Branch, Chinese Medical Association Digestive Disease Branch, Chinese Medical Association Infectious Disease Branch. Consensus on the diagnosis and therapy of hepatic fibrosis (2019)[J]. Chinese Journal of Hepatology, 2019, 27(9):657-667. DOI: 10.3760/cma.j.issn.1007-3418.2019.09.001.
[6]
FROŃ A, SEMIANIUK A, LAZUK U, et al. Artificial Intelligence in Urooncology: what We Have and What We Expect[J/OL]. Cancers, 2023, 15(17): 4282 [2023-10-23]. https://doi.org/10.3390/cancers15174282. DOI: 10.3390/cancers15174282.
[7]
LIU X, SHI J X, LI Z P, et al. The present and future of artificial intelligence in urological cancer[J/OL]. J Clin Med, 2023, 12(15): 4995 [2023-10-23]. https://doi.org/10.3390/jcm12154995. DOI: 10.3390/jcm12154995.
[8]
CLEMENT N D, SIMPSON A H R W. Artificial intelligence in orthopaedics[J]. Bone Joint Res, 2023, 12(8): 494-496. DOI: 10.1302/2046-3758.128.bjr-2023-0199.
[9]
ZHOU L Q, WANG J Y, YU S Y, et al. Artificial intelligence in medical imaging of the liver[J]. World J Gastroenterol, 2019, 25(6): 672-682. DOI: 10.3748/wjg.v25.i6.672.
[10]
WANG L Y, ZHANG L, JIANG B B, et al. Clinical application of deep learning and radiomics in hepatic disease imaging: a systematic scoping review[J/OL]. Br J Radiol, 2022, 95(1136): 20211136 [2023-10-23]. https://doi.org/10.1259/bjr.20211136. DOI: 10.1259/bjr.20211136.
[11]
CHEN Y, LUO Y, HUANG W, et al. Machine-learning-based classification of real-time tissue elastography for hepatic fibrosis in patients with chronic hepatitis B[J]. Comput Biol Med, 2017, 89: 18-23. DOI: 10.1016/j.compbiomed.2017.07.012.
[12]
LAMBRECHT J, VAN GRUNSVEN L A, TACKE F. Current and emerging pharmacotherapeutic interventions for the treatment of liver fibrosis[J]. Expert Opin Pharmacother, 2020, 21(13): 1637-1650. DOI: 10.1080/14656566.2020.1774553.
[13]
MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[14]
BEDOSSA P, POYNARD T. An algorithm for the grading of activity in chronic hepatitis C. The METAVIR Cooperative Study Group[J]. Hepatology, 1996, 24(2): 289-293. DOI: 10.1002/hep.510240201.
[15]
ICHIKAWA Y, KANII Y, YAMAZAKI A, et al. Deep learning image reconstruction for improvement of image quality of abdominal computed tomography: comparison with hybrid iterative reconstruction[J]. Jpn J Radiol, 2021, 39(6): 598-604. DOI: 10.1007/s11604-021-01089-6.
[16]
SATO M, ICHIKAWA Y, DOMAE K, et al. Deep learning image reconstruction for improving image quality of contrast-enhanced dual-energy CT in abdomen[J]. Eur Radiol, 2022, 32(8): 5499-5507. DOI: 10.1007/s00330-022-08647-0.
[17]
CARUSO D, DE SANTIS D, DEL GAUDIO A, et al. Low-dose liver CT: image quality and diagnostic accuracy of deep learning image reconstruction algorithm[J/OL]. Eur Radiol, 2023 [2023-10-23]. https://doi.org/10.1007/s00330-023-10171-8. DOI: 10.1007/s00330-023-10171-8.
[18]
CAO L L, PENG M, XIE X, et al. Artificial intelligence in liver ultrasound[J]. World J Gastroenterol, 2022, 28(27): 3398-3409. DOI: 10.3748/wjg.v28.i27.3398.
[19]
ACHARYA U R, RAGHAVENDRA U, KOH J E W, et al. Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features[J]. Comput Methods Programs Biomed, 2018, 166: 91-98. DOI: 10.1016/j.cmpb.2018.10.006.
[20]
OZTURK A, OLSON M C, SAMIR A E, et al. Liver fibrosis assessment: MR and US elastography[J]. Abdom Radiol (NY), 2022, 47(9): 3037-3050. DOI: 10.1007/s00261-021-03269-4.
[21]
LU Q, LU C L, LI J W, et al. Stiffness value and serum biomarkers in liver fibrosis staging: study in large surgical specimens in patients with chronic hepatitis B[J]. Radiology, 2016, 280(1): 290-299. DOI: 10.1148/radiol.2016151229.
[22]
LEE J H, JOO I, KANG T W, et al. Deep learning with ultrasonography: automated classification of liver fibrosis using a deep convolutional neural network[J]. Eur Radiol, 2020, 30(2): 1264-1273. DOI: 10.1007/s00330-019-06407-1.
[23]
WANG K, LU X, ZHOU H, et al. Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study[J]. Gut, 2019, 68(4): 729-741. DOI: 10.1136/gutjnl-2018-316204.
[24]
LU X, ZHOU H, WANG K, et al. Comparing radiomics models with different inputs for accurate diagnosis of significant fibrosis in chronic liver disease[J]. Eur Radiol, 2021, 31(11): 8743-8754. DOI: 10.1007/s00330-021-07934-6.
[25]
KLOTZ E, HABERLAND U, GLATTING G, et al. Technical prerequisites and imaging protocols for CT perfusion imaging in oncology[J]. Eur J Radiol, 2015, 84(12): 2359-2367. DOI: 10.1016/j.ejrad.2015.06.010.
[26]
KIM S H, KAMAYA A, WILLMANN J K. CT perfusion of the liver: principles and applications in oncology[J]. Radiology, 2014, 272(2): 322-344. DOI: 10.1148/radiol.14130091.
[27]
CUI E M, LONG W S, WU J H, et al. Predicting the stages of liver fibrosis with multiphase CT radiomics based on volumetric features[J]. Abdom Radiol, 2021, 46(8): 3866-3876. DOI: 10.1007/s00261-021-03051-6.
[28]
WANG J C, TANG S N, MAO Y F, et al. Radiomics analysis of contrast-enhanced CT for staging liver fibrosis: an update for image biomarker[J]. Hepatol Int, 2022, 16(3): 627-639. DOI: 10.1007/s12072-022-10326-7.
[29]
LEE S B, CHO Y J, HONG Y, et al. Deep learning-based image conversion improves the reproducibility of computed tomography radiomics features: a phantom study[J]. Invest Radiol, 2022, 57(5): 308-317. DOI: 10.1097/RLI.0000000000000839.
[30]
SON J H, LEE S S, LEE Y, et al. Assessment of liver fibrosis severity using computed tomography-based liver and spleen volumetric indices in patients with chronic liver disease[J]. Eur Radiol, 2020, 30(6): 3486-3496. DOI: 10.1007/s00330-020-06665-4.
[31]
LEE C M, LEE S S, CHOI W M, et al. An index based on deep learning-measured spleen volume on CT for the assessment of high-risk varix in B-viral compensated cirrhosis[J]. Eur Radiol, 2021, 31(5): 3355-3365. DOI: 10.1007/s00330-020-07430-3.
[32]
YIN Y C, YAKAR D, DIERCKX R A J O, et al. Liver fibrosis staging by deep learning: a visual-based explanation of diagnostic decisions of the model[J]. Eur Radiol, 2021, 31(12): 9620-9627. DOI: 10.1007/s00330-021-08046-x.
[33]
CHOI K J, JANG J K, LEE S S, et al. Development and validation of a deep learning system for staging liver fibrosis by using contrast agent-enhanced CT images in the liver[J]. Radiology, 2018, 289(3): 688-697. DOI: 10.1148/radiol.2018180763.
[34]
HECTORS S J, KENNEDY P, HUANG K H, et al. Fully automated prediction of liver fibrosis using deep learning analysis of gadoxetic acid-enhanced MRI[J]. Eur Radiol, 2021, 31(6): 3805-3814. DOI: 10.1007/s00330-020-07475-4.
[35]
SUZUKI T, YAMADA A, KOMATSU D, et al. Evaluation of splenic perfusion and spleen size using dynamic computed tomography: usefulness in assessing degree of liver fibrosis[J]. Hepatol Res, 2018, 48(1): 87-93. DOI: 10.1111/hepr.12900.
[36]
GOSHIMA S, KANEMATSU M, KOBAYASHI T, et al. Staging hepatic fibrosis: computer-aided analysis of hepatic contours on gadolinium ethoxybenzyl diethylenetriaminepentaacetic acid-enhanced hepatocyte-phase magnetic resonance imaging[J]. Hepatology, 2012, 55(1): 328-329. DOI: 10.1002/hep.24677.
[37]
YIN Y C, YAKAR D, DIERCKX R A J O, et al. Combining hepatic and splenic CT radiomic features improves radiomic analysis performance for liver fibrosis staging[J/OL]. Diagnostics, 2022, 12(2): 550 [2023-10-23]. https://doi.org/10.3390/diagnostics12020550. DOI: 10.3390/diagnostics12020550.
[38]
KARTALIS N, BREHMER K, LOIZOU L. Multi-detector CT: liver protocol and recent developments[J]. Eur J Radiol, 2017, 97: 101-109. DOI: 10.1016/j.ejrad.2017.10.026.
[39]
IDILMAN I S, LI J H, YIN M, et al. MR elastography of liver: current status and future perspectives[J]. Abdom Radiol, 2020, 45(11): 3444-3462. DOI: 10.1007/s00261-020-02656-7.
[40]
WEI H H, SHAO Z H, FU F F, et al. Value of multimodal MRI radiomics and machine learning in predicting staging liver fibrosis and grading inflammatory activity[J/OL]. Br J Radiol, 2023, 96(1141): 20220512 [2023-10-23]. https://doi.org/10.1259/bjr.20220512. DOI: 10.1259/bjr.20220512.
[41]
NOWAK S, MESROPYAN N, FARON A, et al. Detection of liver cirrhosis in standard T2-weighted MRI using deep transfer learning[J]. Eur Radiol, 2021, 31(11): 8807-8815. DOI: 10.1007/s00330-021-07858-1.
[42]
FAN F X, HU W J, JIANG Y L, et al. The value of 3D convolution neural network based on multimodal MRI images in the classification of liver fibrosis[J]. Chin J Magn Reson Imag, 2022, 13(9): 30-34. DOI: 10.12015/issn.1674-8034.2022.09.006.
[43]
PARK H J, LEE S S, PARK B, et al. Radiomics analysis of gadoxetic acid-enhanced MRI for staging liver fibrosis[J]. Radiology, 2019, 290(2): 380-387. DOI: 10.1148/radiol.2018181197.
[44]
ZHENG R C, SHI C Z, WANG C Y, et al. Imaging-based staging of hepatic fibrosis in patients with hepatitis B: a dynamic radiomics model based on Gd-EOB-DTPA-enhanced MRI[J/OL]. Biomolecules, 2021, 11(2): 307 [2023-10-23]. https://doi.org/10.3390/biom11020307. DOI: 10.3390/biom11020307.
[45]
STROTZER Q D, WINTHER H, UTPATEL K, et al. Application of A U-net for map-like segmentation and classification of discontinuous fibrosis distribution in Gd-EOB-DTPA-enhanced liver MRI[J/OL]. Diagnostics, 2022, 12(8): 1938 [2023-10-23]. https://doi.org/10.3390/diagnostics12081938. DOI: 10.3390/diagnostics12081938.
[46]
ZHENG W J, GUO W, XIONG M L, et al. Clinic-radiological features and radiomics signatures based on Gd-BOPTA-enhanced MRI for predicting advanced liver fibrosis[J]. Eur Radiol, 2023, 33(1): 633-644. DOI: 10.1007/s00330-022-08992-0.
[47]
WANG M Y. Research status and development prospect of magnetic resonance imaging artificial intelligence[J]. Chin J Magn Reson Imag, 2023, 14(3): 1-5. DOI: 10.12015/issn.1674-8034.2023.03.001.

PREV Radiographic progress of microvascular invasion in hepatocellular carcinoma
NEXT Application of magnetic resonance fat quantification technique in liver tumors
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn