Machine learning for malignant versus benign focal liver lesions on US and CEUS: a meta-analysis.

Autor: Campello CA; School of Medicine, Universidade Federal do Mato Grosso, 2367 Quarenta e Nove St, Cuiabá, Brazil., Castanha EB; School of Medicine, Universidade Federal de Pelotas, 538 Prof. Dr. Araújo St. Pelotas, Pelotas, Brazil., Vilardo M; School of Medicine, Universidade Catolica de Brasilia, QS 07, Brasília, Brazil., Staziaki PV; Department of Radiology, University of Vermont Medical Center, 111 Colchester Ave, Burlington, USA., Francisco MZ; Department of Radiology, Universidade Federal de Ciencias da Saude de Porto Alegre, 245 Sarmento Leite St, Porto Alegre, Brazil., Mohajer B; Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 601 N Caroline St, Baltimore, USA., Watte G; Department of Radiology, Universidade Federal de Ciencias da Saude de Porto Alegre, 245 Sarmento Leite St, Porto Alegre, Brazil., Moraes FY; Department of Oncology, Queen's University, 76 Stuart St, Kingston, Canada., Hochhegger B; Department of Radiology, University of Florida, 1600 SW Archer Rd, Gainesville, USA., Altmayer S; Department of Radiology, Stanford University, 300 Pasteur Drive, Suite H1330, Stanford, USA. altmayer@stanford.edu.
Jazyk: angličtina
Zdroj: Abdominal radiology (New York) [Abdom Radiol (NY)] 2023 Oct; Vol. 48 (10), pp. 3114-3126. Date of Electronic Publication: 2023 Jun 26.
DOI: 10.1007/s00261-023-03984-0
Abstrakt: Objectives: To perform a meta-analysis of the diagnostic performance of learning (ML) algorithms (conventional and deep learning algorithms) for the classification of malignant versus benign focal liver lesions (FLLs) on US and CEUS.
Methods: Available databases were searched for relevant published studies through September 2022. Studies met eligibility criteria if they evaluate the diagnostic performance of ML for the classification of malignant and benign focal liver lesions on US and CEUS. The pooled per-lesion sensitivities and specificities for each modality with 95% confidence intervals were calculated.
Results: A total of 8 studies on US, 11 on CEUS, and 1 study evaluating both methods met the inclusion criteria with a total of 34,245 FLLs evaluated. The pooled sensitivity and specificity of ML for the malignancy classification of FLLs were 81.7% (95% CI, 77.2-85.4%) and 84.8% (95% CI, 76.0-90.8%) for US, compared to 87.1% (95% CI, 81.8-91.0%) and 87.0% (95% CI, 83.1-90.1%) for CEUS. In the subgroup analysis of studies that evaluated deep learning algorithms, the sensitivity and specificity of CEUS (n = 4) increased to 92.4% (95% CI, 88.5-95.0%) and 88.2% (95% CI, 81.1-92.9%).
Conclusions: The diagnostic performance of ML algorithms for the malignant classification of FLLs was high for both US and CEUS with overall similar sensitivity and specificity. The similar performance of US may be related to the higher prevalence of DL models in that group.
(© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)
Databáze: MEDLINE
Externí odkaz: