Study on the changes of CT texture parameters before and after HCC treatment in the efficacy evaluation and survival predication of patients with HCC

Abstract

ObjectiveTo investigate texture parameters of contrast-enhanced computed tomography (CT) images before and after transarterial chemoembolization (TACE) as a tool for assessing the therapeutic response and survival predication in hepatocellular carcinoma (HCC).Materials and methodsData of 77 HCC patients who underwent three-phase dynamic contrast-enhanced CT examination within 4 weeks before and 4–8 weeks after TACE were collected and efficacy evaluation was performed according to the modified Response Evaluation Criteria in Solid Tumors (mRECIST) standard. The remission group consisted of 31 patients (12 with complete remission+19 with partial remission), while the non-remission group consisted of 46 patients (27 with stable disease+19 with progressive disease). Full-volume manual delineation of the region of interest (ROI) and texture analysis of the ROI were performed on the CT images using FireVoxel software. Changes in the 48 texture parameters from three-phase CT images before and after TACE were calculated and compared between the two groups. The receiver operating characteristic (ROC) curve and the areas under the curve (AUC) were used to analyze the diagnostic performance of texture parameters. A multifactorial Cox model was used for predicting survival. The C-indices of texture parameter difference values with predictive value, texture features model, and texture features combined with mRECIST in predicting OS were compared with those of mRECIST.ResultsA total of 41 changes in texture parameters were statistically significant between the remission and non-remission groups. The receiver operating characteristic (ROC) curve showed that the AUC of changes in the 90th percentile in the arterial phase was the largest at 0.842. When the cut-off value was 70.50, the Youden index was the largest (0.621), and the sensitivity and specificity were 0.710 and 0.911, respectively. Three changes in texture parameters were independent factors associated with patient survival, with a hazard of 0.173, 2.068, and 1.940, respectively. The C-index of the OS predicted by the texture features model was not statistically different from that of the mRECIST (0.695 vs. 0.668, p=0.493). While the C-indices of skewness in the portal venous phase combined with mRECIST (0.729, p=0.015), skewness in the delayed phase combined with mRECIST (0.715, p=0.044), and skewness in both two phases combined with mRECIST (0.728, p=0.017) were statistically different.ConclusionChanges in the texture parameters of CT images before and after TACE treatment can be used to obtain relevant grayscale histogram parameters for evaluating the early efficacy of TACE in HCC treatment. And the texture analysis combined with mRECIST may be superior to the mRECIST alone in predicting survival in HCC after TACE treatment.

Enhancing prognostic prediction in hepatocellular carcinoma post-TACE: a machine learning approach integrating radiomics and clinical features

“…To date, various machine learning algorithms have been utilized to predict survival, prognosis, and treatment efficacy in patients with intermediate or advanced HCC treated with TACE. However, previous studies usually limit themselves to a single machine learning algorithm for analysis and modeling ( 34 , 35 ). Considering the different features and scopes of application of various machine learning algorithms, this study used four advanced algorithms: XGBoost, RSF, gradient boosting, and Coxph to build models predicting the OS of patients with HCC under TACE treatment.…”

Trans-Arterial Chemoembolization for the Treatment of Hepatocellular Carcinoma: A Single Tertiary Care Institute Experience

“…Assessing tumor response to TACE is crucial for determining treatment efficacy and future therapy. 11 To assess response to LRT, a "modified response evaluation criterion in solid tumours (mRECIST) are a set of published rules used to assess tumor burden in order to provide an objective assessment of response to therapy with targeted agents for hepatocellular carcinoma (HCC). It considers the extent of viable contrast-enhancing regions within the tumor 9,10,12 .…”

“…It considers the extent of viable contrast-enhancing regions within the tumor 9,10,12 . Although there is a validated relationship between HCC enhancement patterns and image results, these findings are closely associated with tumor differentiation, which plays a crucial role in understanding the aggressiveness and prognosis of HCC 11,13,14 However there is a data scarcity of this region and the therapy outcomes remain diverse. Considering this, the present study is conducted to determine the radiological and clinical response of HCC patients who underwent TACE.…”