Multi-Sequence MR-Based Radiomics Signature for Predicting Early Recurrence in Solitary Hepatocellular Carcinoma ≤5 cm

Abstract

PurposeTo investigate the value of radiomics features derived from preoperative multi-sequence MR images for predicting early recurrence (ER) in patients with solitary hepatocellular carcinoma (HCC) ≤5 cm.MethodsOne hundred and ninety HCC patients were enrolled and allocated to training and validation sets (n = 133:57). The clinical–radiological model was established by significant clinical risk characteristics and qualitative imaging features. The radiomics model was constructed using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm in the training set. The combined model was formed by integrating the clinical–radiological risk factors and selected radiomics features. The predictive performance was assessed by the area under the receiver operating characteristic curve (AUC).ResultsArterial peritumoral hyperenhancement, non-smooth tumor margin, satellite nodules, cirrhosis, serosal invasion, and albumin showed a significant correlation with ER. The AUC of the clinical–radiological model was 0.77 (95% CI: 0.69–0.85) and 0.76 (95% CI: 0.64–0.88) in the training and validation sets, respectively. The radiomics model constructed using 12 radiomics features selected by LASSO regression had an AUC of 0.85 (95% CI: 0.79–0.91) and 0.84 (95% CI: 0.73–0.95) in the training and validation sets, respectively. The combined model further improved the prediction performance compared with the clinical–radiological model, increasing AUC to 0.90 (95% CI: 0.85–0.95) in the training set and 0.88 (95% CI: 0.80–0.97) in the validation set (p < 0.001 and p = 0.012, respectively). The calibration curve fits well with the standard curve.ConclusionsThe predictive model incorporated the clinical–radiological risk factors and radiomics features that could adequately predict the individualized ER risk in patients with solitary HCC ≤5 cm.

Radiomic analysis based on magnetic resonance imaging for the prediction of VEGF expression in hepatocellular carcinoma patients

“…These findings may be beneficial for choosing optimal and individualized treatment strategies for HCC patient. The radiomics model different, and their contributions to the combined model are also different [26]. Multisequence combined models have been shown to have better prediction efficiency [10,11,[27][28][29], consistent with our present study.…”

“…the most preserved, consistent with previous studies [10,30]. Among the 7 optimal features of the combined model, there were six features from FS-T2WI and one feature from DCE-MRI; thus, there were more features from FS-T2WI than from contrast-enhanced sequences, which is inconsistent with the literature [26,31]. The main reason for this may be that other contrast-enhanced sequences, such as those from the delayed phase and the hepatobiliary phase, were not included in this study.…”

Preoperative prediction for early recurrence of hepatocellular carcinoma using machine learning-based radiomics

“…Previous studies have reported that radiomics may be helpful to the preoperative prediction of early recurrence of HCC, we selected 15 representative papers and compared them with our study in terms of imaging modality, number of included patients, modeling methods, etc. From the perspective of image modality, CT(n=6) (6,20,21,(32)(33)(34) has higher specificity than MRI (n=9) (7,(35)(36)(37)(38)(39)(40)(41)(42). In our study, we used CECT which hold fixed and uniform parameters than MRI to predict early recurrence.…”

Leveraging radiomics and AI for precision diagnosis and prognostication of liver malignancies

“…Multiple studies -including ten studies on HCC (88)(89)(90)(91)(92)(93)(94)(95)(96)(97), four studies on Mass-forming CC (98-101), and three studies on colorectal liver metastases (102-104)-utilized various radiomics approaches to predict outcomes and guide treatment decisions. The studies involved diverse cohorts, including patients undergoing liver transplantation, surgical resection, or chemotherapy.…”

“…The endpoint outcomes ranged from overall survival (OS), recurrence free survival (RFS), progression-free survival (PFS), event-free survival (EFS), early recurrence (ER), 1-year survival and 5-year survival, post-hepatectomy liver failure (PHLF), and lymph node metastasis. The AUCs for predictive models varied, ranging between 0.70 to 0.98 (88)(89)(90)(91)(92)(93)(94)(95)(96)(97)(98)(99)(100)(101)(102)(103)(104). Moreover, the integration of radiomics with clinical factors consistently improved predictive performance, demonstrating the potential for personalized risk assessment.…”