Dataset Information

Clinical Value of Machine Learning-Based Ultrasomics in Preoperative Differentiation Between Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma: A Multicenter Study.

ABSTRACT:

Objective

This study aims to explore the clinical value of machine learning-based ultrasomics in the preoperative noninvasive differentiation between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC).

Methods

The clinical data and ultrasonic images of 226 patients from three hospitals were retrospectively collected and divided into training set (n = 149), test set (n = 38), and independent validation set (n = 39). Manual segmentation of tumor lesion was performed with ITK-SNAP, the ultrasomics features were extracted by the pyradiomics, and ultrasomics signatures were generated using variance filtering and lasso regression. The prediction models for preoperative differentiation between HCC and ICC were established by using support vector machine (SVM). The performance of the three models was evaluated by the area under curve (AUC), sensitivity, specificity, and accuracy.

Results

The ultrasomics signatures extracted from the grayscale ultrasound images could successfully differentiate between HCC and ICC (p < 0.05). The combined model had a better performance than either the clinical model or the ultrasomics model. In addition to stability, the combined model also had a stronger generalization ability (p < 0.05). The AUC (along with 95% CI), sensitivity, specificity, and accuracy of the combined model on the test set and the independent validation set were 0.936 (0.806-0.989), 0.900, 0.857, 0.868, and 0.874 (0.733-0.961), 0.889, 0.867, and 0.872, respectively.

Conclusion

The ultrasomics signatures could facilitate the preoperative noninvasive differentiation between HCC and ICC. The combined model integrating ultrasomics signatures and clinical features had a higher clinical value and a stronger generalization ability.

SUBMITTER: Ren S

PROVIDER: S-EPMC8604281 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeThe present study aimed to determine the reliable imaging features to distinguish atypical hepatocellular carcinoma (HCC) with peripheral rim-like enhancement from intrahepatic mass-forming cholangiocarcinoma (IMCC) on contrast-enhanced magnetic resonance imaging (MRI).MethodsA total of 168 patients (130 male, 57.10 ± 10.53 years) pathological confirmed HCC or IMCC who underwent contrast-enhanced MRI between July 2019 and February 2022 were retrospectively included. Univariate and multivariate logistic regression analyses were used to determine independent differential factors for distinguishing HCC from IMCC, and the model was established. Bootstrap resampling 1000 times was used to verify the model, which was visualized by nomograms. The predictive performance of the model was evaluated based on discrimination, calibration, and clinical utility.ResultsRadiological capsule (OR 0.024, 95% CI: 0.006, 0.095, P<0.001), heterogeneous signal intensity (SI) on T1WI (OR 0.009, 95%CI: 0.001,0.056, P<0.001) were independent differential factors for predicting HCC over IMCC. A lobulated contour (OR 11.732, 95%CI: 2.928,47.007, P = 0.001), target sign on DP (OR 14.269, 95%CI: 2.849,82.106, P = 0.007), bile duct dilatation (OR 12.856, 95%CI: 2.013, P = 0.001) were independent differential factors for predicting IMCCs over HCCs. The independent differential factors constituted a model to distinguish atypical HCCs and IMCCs. The area under receiver operating characteristic (ROC) curve, sensitivity, and specificity values of the model were 0.964(0.940,0.987), 0.88, and 0.906, indicating that the model had an excellent differential diagnostic performance. The decision curve analysis (DCA) curve showed that the model obtained a better net clinical benefit.ConclusionThe present study identified reliable imaging features for distinguishing atypical HCCs with peripheral rim-like enhancement from IMCCs on contrast-enhanced MRI. Our findings may help radiologists provide clinicians with more accurate preoperative imaging diagnoses to select appropriate treatment options.

Project description:BackgroundThe typical enhancement patterns of hepatocellular carcinoma (HCC) on contrast-enhanced ultrasound (CEUS) are hyper-enhanced in the arterial phase and washed out during the portal venous and late phases. However, atypical variations make a differential diagnosis both challenging and crucial. We aimed to investigate whether machine learning-based ultrasonic signatures derived from CEUS images could improve the diagnostic performance in differentiating focal nodular hyperplasia (FNH) and atypical hepatocellular carcinoma (aHCC).Patients and methodsA total of 226 focal liver lesions, including 107 aHCC and 119 FNH lesions, examined by CEUS were reviewed retrospectively. For machine learning-based ultrasomics, 3,132 features were extracted from the images of the baseline, arterial, and portal phases. An ultrasomics signature was generated by a machine learning model. The predictive model was constructed using the support vector machine method trained with the following groups: ultrasomics features, radiologist's score, and combination of ultrasomics features and radiologist's score. The diagnostic performance was explored using the area under the receiver operating characteristic curve (AUC).ResultsA total of 14 ultrasomics features were chosen to build an ultrasomics model, and they presented good performance in differentiating FNH and aHCC with an AUC of 0.86 (95% confidence interval [CI]: 0.80, 0.89), a sensitivity of 76.6% (95% CI: 67.5%, 84.3%), and a specificity of 80.5% (95% CI: 70.6%, 85.9%). The model trained with a combination of ultrasomics features and the radiologist's score achieved a significantly higher AUC (0.93, 95% CI: 0.89, 0.96) than that trained with the radiologist's score (AUC: 0.84, 95% CI: 0.79, 0.89, P < 0.001). For the sub-group of HCC with normal AFP value, the model trained with a combination of ultrasomics features, and the radiologist's score remain achieved the highest AUC of 0.92 (95% CI: 0.87, 0.96) compared to that with the ultrasomics features (AUC: 0.86, 95% CI: 0.74, 0.89, P < 0.001) and radiologist's score (AUC: 0.86, 95% CI: 0.79, 0.91, P < 0.001).ConclusionsMachine learning-based ultrasomics performs as well as the staff radiologist in predicting the differential diagnosis of FNH and aHCC. Incorporating an ultrasomics signature into the radiologist's score improves the diagnostic performance in differentiating FNH and aHCC.

Project description:ObjectiveTo assess significant liver fibrosis by multiparametric ultrasomics data using machine learning.Materials and methodsThis prospective study consisted of 144 patients with chronic hepatitis B. Ultrasomics-high-throughput quantitative data from ultrasound imaging of liver fibrosis-were generated using conventional radiomics, original radiofrequency (ORF) and contrast-enhanced micro-flow (CEMF) features. Three categories of features were explored using pairwise correlation and hierarchical clustering. Features were selected using diagnostic tests for fibrosis, activity and steatosis stage, with the histopathological results as the reference. The fibrosis staging performance of ultrasomics models with combinations of the selected features was evaluated with machine-learning algorithms by calculating the area under the receiver-operator characteristic curve (AUC).ResultsORF and CEMF features had better predictive power than conventional radiomics for liver fibrosis stage (both p < 0.01). CEMF features exhibited the highest diagnostic value for activity stage (both p < 0.05), and ORF had the best diagnostic value for steatosis stage (both p < 0.01). The machine-learning classifiers of adaptive boosting, random forest and support vector machine were found to be optimal algorithms with better (all mean AUCs = 0.85) and more stable performance (coefficient of variation = 0.01-0.02) for fibrosis staging than decision tree, logistic regression and neural network (mean AUC = 0.61-0.72, CV = 0.07-0.08). The multiparametric ultrasomics model achieved much better performance (mean AUC values of 0.78-0.85) than the features from a single modality in discriminating significant fibrosis (≥ F2).ConclusionMachine-learning-based analysis of multiparametric ultrasomics can help improve the discrimination of significant fibrosis compared with mono or dual modalities.Key points• Multiparametric ultrasomics has achieved much better performance in the discrimination of significant fibrosis (≥ F2) than the single modality of conventional radiomics, original radiofrequency and contrast-enhanced micro-flow. • Adaptive boosting, random forest and support vector machine are the optimal algorithms for machine learning.

Project description:BackgroundAppropriate preoperative identification of iCCA subtype is essential for personalized management, so the aim of this study is to investigate the role of MR imaging features in preoperatively differentiating the iCCA subtype.MethodsNinety-three patients with mass-forming intrahepatic cholangiocarcinoma (iCCA, 63 small duct type and 30 large duct type) were retrospectively enrolled according to the latest 5th WHO classification (mean age, males vs. females: 60.66 ± 10.53 vs. 61.88 ± 12.82, 50 men). Significant imaging features for differentiating large duct iCCA and small duct iCCA were identified using univariate and multivariate logistic regression analyses, and a regression-based predictive model was then generated. Furthermore, diagnostic performance parameters of single significant imaging features and the predictive model were obtained, and corresponding receiver operating characteristic (ROC) curves were subsequently presented.ResultsThe univariate analysis showed that tumor in vein, arterial phase hypoenhancement, intrahepatic duct dilatation, lack of targetoid restriction and lack of targetoid appearance in T2 were predictors of large duct type iCCA. Arterial phase hypoenhancement, intrahepatic duct dilatation and lack of targetoid restriction were independent predictors for large duct type iCCA in multivariate analysis. The regression-based predictive model has achieved the best preoperative prediction performance in iCCA subcategorization so far. The area under the ROC curve of the regression-based predictive model was up to 0.91 (95% CI: 0.85, 0.98), and it was significantly higher than every single significant imaging feature.ConclusionsArterial phase hypoenhancement, intrahepatic duct dilatation and lack of targetoid restriction could be considered reliable MR imaging indicators of large duct type iCCA. MR imaging features can facilitate noninvasive prediction of iCCA subtype with satisfactory predictive performance.