A Cox Nomogram for Assessing Recurrence Free Survival in Hepatocellular Carcinoma Following Surgical Resection Using Dynamic Contrast‐Enhanced MRI Radiomics

Abstract

BackgroundThe prognosis of hepatocellular carcinoma (HCC) is difficult to predict and carries high mortality. This study utilized radiomic techniques with clinical examinations to assess recurrence in HCC.PurposeTo develop a Cox nomogram to assess the risk of postoperative recurrence in HCC using radiomic features of three volumes of interest (VOIs) in preoperative dynamic contrast‐enhanced MRI (DCE‐MRI), along with clinical findings.Study TypeRetrospective.Subjects249 patients with pathologically proven HCCs undergoing surgical resection at three institutions were selected.Field Strength/SequenceFat saturated T2‐weighted, Fat saturated T1‐weighted, and DCE‐MRI performed at 1.5 T and 3.0 T.AssessmentThree VOIs were generated; the tumor VOI corresponds to the area from the tumor core to the outer perimeter of the tumor, the tumor +10 mm VOI represents the area from the tumor perimeter to 10 mm distal to the tumor in all directions, finally, the background liver parenchyma VOI represents the hepatic tissue outside the tumor. Three models were generated. The total radiomic model combined information from the three listed VOI's above. The clinical–radiological model combines physical examination findings with imaging characteristics such as tumor size, margin features, and metastasis. The combined radiomic model includes features from both models listed above and showed the highest reliability for assessing 24‐month survival for HCC.Statistical TestsThe least absolute shrinkage and selection operator (LASSO) Cox regression, univariable, and multivariable Cox regression, Kmeans clustering, and Kaplan–Meier analysis. The discrimination performance of each model was quantified by the C‐index. A P value <0.05 was considered statistically significant.ResultsThe combined radiomic model, which included features from the radiomic VOI's and clinical imaging provided the highest performance (C‐index: training cohort = 0.893, test cohort = 0.851, external cohort = 0.797) in assessing the survival of HCC.ConclusionThe combined radiomic model provides superior ability to discern the possibility of recurrence‐free survival in HCC over the total radiomic and the clinical–radiological models.Evidence Level4.Technical EfficacyStage 2.

Evaluation of Four Deep Learning-Based Postoperative Survival Prediction Models for Hepatocellular Carcinoma Based on SEER

“…By combining large-scale data and powerful algorithms, machine learning can provide personalized prognosis assessment, precise treatment recommendations, and improved clinical decision support, leading to breakthroughs in cancer treatment. By integrating clinical features, gene expression data, and pathological parameters 19 , machine learning models can establish personalized prognostic prediction models 20 . For instance, Yunlang She et al compared a deep learning survival neural network model with tumor, lymph node, and metastasis staging systems for lung cancer.…”

MRI radiomics based on deep learning automated segmentation to predict early recurrence of hepatocellular carcinoma

“…Radiomics has emerged as a new radiological technique that enables the extraction of high-throughput quantitative image features beyond inspections of naked human eyes from standard-of-care medical images, providing important insights into cancer phenotypes and tumor microenvironments that are distinct and complementary to other clinical information [ 10 ]. Previous studies have shown good predictive accuracy of MRI radiomic analyses for HCC recurrence after surgery [ 6 , 11 – 13 ]. However, these studies generally included limited sample sizes (e.g., 48–361 patients) and utilized manual or semiautomated segmentation, which are time-consuming, labor-intensive, operator-dependent, and subject to inter-rater variability.…”