18F-FDG PET/CT-based radiomics nomogram for preoperative prediction of macrotrabecular-massive hepatocellular carcinoma: a two-center study

Siqi Hu; Yinqian Kang; Yujie Xie; Ting Yang; Yuan Yang; Ju Jiao; Qiong Zou; Hong Zhang; Yong Zhang

doi:10.1007/s00261-022-03722-y

¹⁸F-FDG PET/CT-based radiomics nomogram for preoperative prediction of macrotrabecular-massive hepatocellular carcinoma: a two-center study

Abdom Radiol (NY). 2023 Feb;48(2):532-542. doi: 10.1007/s00261-022-03722-y. Epub 2022 Nov 12.

Authors

Siqi Hu¹, Yinqian Kang^{1

2}, Yujie Xie¹, Ting Yang¹, Yuan Yang¹, Ju Jiao¹, Qiong Zou¹, Hong Zhang³, Yong Zhang⁴

Affiliations

¹ Department of Nuclear Medicine, The Third Affiliated Hospital of Sun Yat-Sen University, No. 600 Tianhe Road, Tianhe District, Guangzhou, 510630, China.
² Department of Anesthesiology, Sun Yat-Sen University Cancer Center, No. 651 Dongfeng East Road, Yuexiu District, Guangzhou, 510060, China.
³ Department of Nuclear Medicine, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, No. 33 Yingfeng Road, Haizhu District, Guangzhou, 510289, China. zhanghn@mail.sysu.edu.cn.
⁴ Department of Nuclear Medicine, The Third Affiliated Hospital of Sun Yat-Sen University, No. 600 Tianhe Road, Tianhe District, Guangzhou, 510630, China. zhangyn9@mail.sysu.edu.cn.

PMID: 36370179
DOI: 10.1007/s00261-022-03722-y

Abstract

Purpose: To explore the potential of β-2-[18F] fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) in the evaluation of macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC) and to apply radiomics approach to build a radiomics nomogram for predicting MTM-HCC.

Methods: This study included 140 (training cohort:101; validation cohort:39) HCC patients who underwent preoperative ¹⁸F-FDG PET/CT at two institutions. The clinical features and tumor FDG metabolism measured by the tumor-to-liver ratio (TLR) via ¹⁸F-FDG PET/CT were retrospectively collected. Radiomics features were extracted from ¹⁸F-FDG PET/CT images and a radiomics score (Rad-score) was calculated. A radiomics nomogram was then constructed by combining Rad-score and independent clinical features and was assessed with a calibration curve. The performance of the radiomics nomogram, Rad-score and TLR was evaluated by receiver operating characteristic (ROC) curves and decision curve analysis (DCA).

Results: A total of six top weighted radiomics features were selected from PET/CT images by the least absolute shrinkage and selection operator (LASSO) regression algorithm and were used to construct a Rad-score. Multivariate analysis identified Rad-score (OR = 2.183, P = 0.004), age ≤ 50 years (OR = 3.136, P = 0.036), AST > 40U/L (OR = 0.270, P = 0.017) and TLR (OR = 1.641, P = 0.049) as independent predictors of MTM-HCC. The radiomics nomogram had a higher area under the curves (AUCs) than the Rad-score and TLR for predicting MTM-HCC in both training (0.849 [95% CI 0.774-0.924] vs. 0.764 [95% CI 0.669-0.843], 0.763 [95% CI 0.668-0.842]) and validation (0.749 [95% CI 0.584-0.873] vs. 0.690 [95% CI 0.522-0.828], 0.541 [95% CI 0.374-0.701]) cohorts. DCA showed the radiomics nomogram to be more clinically useful than Rad-score and TLR.

Conclusions: Tumor FDG metabolism is significantly associated with MTM-HCC. A ¹⁸F-FDG PET/CT-based radiomics nomogram may be useful for preoperatively predicting the MTM subtype in primary HCC patients, contributing to pretreatment decision-making.

Keywords: Diagnosis; Hepatocellular carcinoma; Nomogram Radiomics; PET/CT.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Carcinoma, Hepatocellular* / diagnostic imaging
Carcinoma, Hepatocellular* / surgery
Fluorodeoxyglucose F18
Humans
Liver Neoplasms* / diagnostic imaging
Liver Neoplasms* / surgery
Middle Aged
Nomograms
Positron Emission Tomography Computed Tomography
Retrospective Studies

Substances

Fluorodeoxyglucose F18
CI 924