Keywords
How to Cite
Abstract
Background: Focal liver lesions (FLLs) encompass a wide spectrum of benign and malignant pathologies, making accurate differentiation critical for appropriate therapeutic decision-making. Shear wave elastography (SWE), a non-invasive ultrasound technique, quantitatively assesses tissue stiffness and supports the evaluation of liver lesions.
Objective: This review explores the integration of artificial intelligence (AI) with SWE for the characterization of FLLs, emphasizing AI’s ability to enhance diagnostic accuracy, reduce interobserver variability, and aid in lesion classification.
Methods: A narrative literature review was conducted using peer-reviewed articles from PubMed, Scopus, and Web of Science databases, focusing on studies investigating the application of AI in SWE for liver imaging.
Results: The integration of AI with SWE has demonstrated improved lesion characterization, particularly in differentiating hepatocellular carcinoma (HCC), metastases, hemangiomas, and focal nodular hyperplasia (FNH). It also enhances reproducibility and standardization across studies.
Conclusion: AI-assisted SWE shows promise as a valuable diagnostic tool in liver imaging. However, its clinical implementation requires further validation and platform standardization through multicenter studies.
References
Ferraioli G, Wong VW, Castera L, Berzigotti A, Sporea I, Dietrich CF, Choi BI, Wilson SR, Kudo M, Barr RG. Liver ultrasound elastography: An update to the WFUMB guidelines. Ultrasound Med Biol. 2018;44(12):2419–2440.
Barr RG, Ferraioli G, Palmeri ML, Goodman ZD, Garcia-Tsao G, Rubin J, Garra B, Myers RP, Wilson SR. Elastography assessment of liver fibrosis: Society of Radiologists in Ultrasound consensus. Radiology. 2015;276(3):845–861.
Park SH, Kim SH, Kang BK, Kim YJ, Kim HJ, Park CK, Kim DW. Characterization of focal liver lesions using shear wave elastography. Eur Radiol. 2014;24(5):1033–1040.
Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S. Deep convolutional neural network-based staging of liver fibrosis using magnetic resonance images. Radiology. 2018;287(1):146–155.
Chartrand G, Cheng PM, Vorontsov E, Drozdzal M, Turcotte S, Pal CJ, Kadoury S, Tang A. Deep learning: A primer for radiologists. Radiographics. 2017;37(7):2113–2131.
Wang K, Lu X, Zhou H, Gao Y, Zheng J, Tong M, Wu C, Huang Z, Wang H, Liu X, Liang J. Deep learning radiomics of shear wave elastography significantly improves diagnostic performance for assessing liver fibrosis in chronic hepatitis B: A prospective multicentre study. Gut. 2019;68(4):729–741.
Liu F, Zhou Z, Jang H, Samsonov A, Zhao G, Kijowski R, McMillan AB. Deep learning MR-based attenuation correction for PET/MR imaging. Radiology. 2018;286(2):676–684.
Yasaka K, Akai H, Abe O. Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: A preliminary study. Jpn J Radiol. 2018;36(4):257–272.
Singh S, Venkatesh SK, Wang Z, Miller FH, Motosugi U, Low RN, Ehman RL, Morishita H, Kudo M, Nightingale KR, Sirlin CB. Diagnostic performance of elastography in staging liver fibrosis: A systematic review and meta-analysis of individual participant data. Radiology. 2016;278(1):158–169.
Topalovic D, Das N, Vintch B, Nagy M, Ahmed S, Hartley E, Liu J, Wall M, Hinton G. Challenges in medical artificial intelligence implementation: A clinical perspective. J Am Med Inform Assoc. 2020;27(9):1394–1398.
Dietrich CF, Bamber J, Berzigotti A, Bota S, Cantisani V, Castera L, Cosgrove D, Ferraioli G, Friedrich-Rust M, Gilja OH, Goodwin R. Elastography of the liver: Recommendations by the EFSUMB. Ultraschall Med. 2017;38(4):e16–e47.
Arntfield R, Millington SJ, Ainsworth C, Arora R, Boyd J, Granton J, Hewak M, Haji K, Friesen D, Mayo P. Artificial intelligence in point-of-care ultrasound. Crit Care. 2020;24(1):1–9.
Kim DW, Jang HY, Kim KW, Shin Y, Park SH. Artificial intelligence in medical education. Korean J Med Educ. 2020;32(3):165–172.
Jiang Y, Wang Y, Li J, Yuan Q, Lv W, Hu Y, Wei J, Cui Y, Yu Y, Ma X, Tian J. Radiogenomics of hepatocellular carcinoma: A comprehensive review. Eur Radiol. 2020;30:5120–5130.
Xu Y, Wang Y, Yuan Q, Hu Y, Wei J, Ma X, Tian J, Cui Y, Li X, Lv W, Zhao Y. Integration of genomics and imaging: Emerging opportunities in hepatocellular carcinoma. J Hepatol. 2021;75(4):1037–1050.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2025 Pak-Euro Journal of Medical and Life Sciences