CT-radiomics and clinical risk scores for response and overall survival prognostication in TACE HCC patients

Abstract

We aimed to identify hepatocellular carcinoma (HCC) patients who will respond to repetitive transarterial chemoembolization (TACE) to improve the treatment algorithm. Retrospectively, 61 patients (mean age, 65.3 years ± 10.0 [SD]; 49 men) with 94 HCC mRECIST target-lesions who had three consecutive TACE between 01/2012 and 01/2020 were included. Robust and non-redundant radiomics features were extracted from the 24 h post-embolization CT. Five different clinical TACE-scores were assessed. Seven different feature selection methods and machine learning models were used. Radiomics, clinical and combined models were built to predict response to TACE on a lesion-wise and patient-wise level as well as its impact on overall-survival prognostication. 29 target-lesions of 19 patients were evaluated in the test set. Response rates were 37.9% (11/29) on the lesion-level and 42.1% (8/19) on the patient-level. Radiomics top lesion-wise response prognostications was AUC 0.55-0.67. Clinical scores revealed top AUCs of 0.65-0.69. The best working model combined the radiomic feature LargeDependenceHighGrayLevelEmphasis and the clinical score mHAP_II_score_group with AUC = 0.70, accuracy = 0.72. We transferred this model on a patient-level to achieve AUC = 0.62, CI = 0.41-0.83. The two radiomics-clinical features revealed overall-survival prognostication of C-index = 0.67. In conclusion, a random forest model using the radiomic feature LargeDependenceHighGrayLevelEmphasis and the clinical mHAP-II-score-group seems promising for TACE response prognostication.

Figure 1

STARD Flowchart of patient inclusion into the study. STARD, Standards for Reporting Diagnostic Accuracy Studies.

Figure 2

Workflow of the image analysis. (a) Baseline arterial-phase MRI showing mildly enhancing hepatocellular carcinoma. The 24 h post-TACE CT (b) was used to semi-automatically segment the lipiodol retention-pattern in three dimensions (c–d).

Figure 3

Prediction of response and overall survival. (a, b) Receiver operating characteristics (ROC) curves trained and tested using the final combined feature set of the radiomics feature LargeDependenceHighGrayLevelEmphasis and the clinical score mHAP_II_score_group. (a) Lesion-wise prediction with class 1 describing the individual responding lesions according to mRECIST. (b) Patient-wise prediction with class 1 describing the overall response on the patient-level according to mRECIST, including the impact of non-target lesions and potential new-lesions. (c) Patient-wise overall survival prediction. Kaplan–Meier plot of two test-patients who showed the shortest (102 days) or longest (censored at 2043 days) survival. Kaplan–Meier estimator was based on our final model. Logrank-Test was used.