Differentiation of malignant from benign focal liver lesions in triphase-enhanced CT using machine-learning-based radiomics

Lingyun Wang; Zhihan Xu; Lu Zhang; Keke Zhao; Hongcheng Sun; Zhijie Pan; Qingyao Li; Yaping Zhang; Xueqian Xie

doi:10.1093/bjr/tqaf138

Differentiation of malignant from benign focal liver lesions in triphase-enhanced CT using machine-learning-based radiomics

Br J Radiol. 2025 Jun 23:tqaf138. doi: 10.1093/bjr/tqaf138. Online ahead of print.

Authors

Lingyun Wang¹, Zhihan Xu², Lu Zhang¹, Keke Zhao¹, Hongcheng Sun³, Zhijie Pan¹, Qingyao Li^{1

4}, Yaping Zhang¹, Xueqian Xie¹

Affiliations

¹ Radiology department, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Haining Rd.100, Shanghai, 200080, China.
² Siemens Healthineers Ltd, Shanghai, China.
³ Department of General Surgery, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200080, China.
⁴ Radiology department, Shanghai General Hospital, University of Shanghai for Science and Technology, Shanghai, China.

PMID: 40581616
DOI: 10.1093/bjr/tqaf138

Abstract

Objectives: Triphasic enhanced CT provides more information about blood supply. The aim was to establish a radiomics model of triphasic-enhanced CT to differentiate malignant from benign focal liver lesions (FLLs).

Methods: Patients with FLLs who underwent triphasic enhanced CT with histopathological results were retrospectively included. We extracted the radiomic features of each lesion in arterial phase (AP), portal vein phase (PVP), delayed phase (DP), slope of AP to PVP, and slope of PVP to DP. The features that best discriminated malignant from benign FLLs were selected using the Boruta algorithm and random forest algorithm and combined to create a radiomic signature. Three radiologists independently graded the LI-RADS category.

Results: Of the 322 FLLs, the training, validation and test cohorts consisted of 160 (122 malignant, 76.3%), 83 (63 malignant, 75.9%), and 79 (63 malignant , 79.7%) lesions. The three observers classified 235, 169, and 220 as malignant respectively. In the test cohort, the AUC of the radiomic signature in identifying malignant FLLs was 0.896 (0.850-0.973), lower than 0.935 (0.873-0.996) (p = 0.463) of the senior radiologist, but higher than 0.812 (0.713-0.910) (p = 0.228) and 0.747 (0.667-0.827) (p = 0.016) of the two less-experienced radiologists.

Conclusions: The radiomics-based model for triphasic enhanced CT images performed well in differentiating malignant from benign FLLs and may be a potential tool to screen for positive cases and avoid false negatives.

Advances in knowledge: The radiomics-based model for triphasic enhanced CT achieved high performance in differentiating malignant from benign focal liver lesions and may help to screen for positive cases and avoid false negatives.

Keywords: Focal liver lesions; LI-RADS; Radiomics; Triphase-enhanced CT.

© The Author(s) 2025. Published by Oxford University Press on behalf of the British Institute of Radiology. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com.