Deep learning-based radiomics based on contrast-enhanced ultrasound predicts early recurrence and survival outcome in hepatocellular carcinoma

BACKGROUND Hepatocellular carcinoma(HCC)is the most common primary liver malignancy.AIM To predict early recurrence(ER)and overall survival(OS)in patients with HCC after radical resection using deep learning-based radiomics(DLR).METHODS A total of 414 consecutive patients with HCC who underwent surgical resection with available preoperative grayscale and contrast-enhanced ultrasound images were enrolled.The clinical,DLR,and clinical+DLR models were then designed to predict ER and OS.RESULTS The DLR model for predicting ER showed satisfactory clinical benefits[area under the curve(AUC=0.819 and 0.568 in the training and testing cohorts,respectively)],similar to the clinical model(AUC=0.580 and 0.520 in the training and testing cohorts,respectively;P>0.05).The C-index of the clinical+DLR model in the prediction of OS in the training and testing cohorts was 0.800 and 0.759,respectively.The clinical+DLR model and the DLR model outperformed the clinical model in the training and testing cohorts(P<0.001 for all).We divided patients into four categories by dichotomizing predicted ER and OS.For patients in class 1(high ER rate and low risk of OS),retreatment(microwave ablation)after recurrence was associated with improved survival(hazard ratio=7.895,P=0.005).CONCLUSION Compared to the clinical model,the clinical+DLR model significantly improves the accuracy of predicting OS in HCC patients after radical resection.

Correlation of dynamic contrast-enhanced ultrasonography and the Ki-67 labelling index in pancreatic ductal adenocarcinoma

BACKGROUND Pancreatic ductal adenocarcinoma(PDAC)is a highly malignant and aggressive tumor,and high Ki-67 expression indicates poor histological differentiation and prognosis.Therefore,one of the challenges in diagnosing preoperatively patients with PDAC is predicting the degree of malignancy.Dynamic contrast-enhanced ultrasonography(DCE-US)plays a crucial role in abdominal tumor diagnosis,and can adequately show the microvascular composition within the tumors.However,the relationship between DCE-US and the Ki-67 labelling index remains unclear at the present time.AIM To predict the correlation between Ki-67 expression and the parameters of DCEUS.METHODS Patients with PDAC who underwent DCE-US were retrospectively analyzed.Patients who had received any treatment(radiotherapy or chemotherapy)prior to DCE-US;had incomplete clinical,imaging,or pathologic information;and had poor-quality image analysis were excluded.Correlations between Ki-67 expression and the parameters of DCE-US in patients with PDAC were assessed using Spearman’s rank correlation analysis.The diagnostic performances of these parameters in high Ki-67 expression group were evaluated according to receiver operating characteristic curve.RESULTS Based on the Ki-67 labelling index,30 patients were divided into two groups,i.e.,the high expression group and the low expression group.Among the relative quantitative parameters between the two groups,relative half-decrease time(rHDT),relative peak enhancement,relative wash-in perfusion index and relative wash-in rate were significantly different between two groups(P=0.018,P=0.025,P=0.028,P=0.035,respectively).The DCE-US parameter rHDT was moderately correlated with Ki-67 expression,and rHDT≥1.07 was more helpful in accurately diagnosing high Ki-67 expression,exhibiting a sensitivity and specificity of 53.8%and 94.1%,respectively.CONCLUSION One parameter of DCE-US,rHDT,correlates with high Ki-67 expression.It demonstrates that parameters obtained noninvasively by DCE-US could better predict Ki-67 expression in PDAC preoperatively.