Preoperative prediction of pathological grading of hepatocellular carcinoma using machine learning-based ultrasomics: A multicenter study

Ren, Shanshan; Qi, Qinghua; Liu, Shunhua; Duan, Shaobo; Mao, Bing; Chang, Zhiyang; Zhang, Ye; Wang, Shuaiyang; Zhang, Lianzhong

doi:10.1016/j.ejrad.2021.109891

Cited by 15 publications

(16 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A regularization method is one of the most used methods for penalizing a feature based on a coefficient threshold [32]. If the objective function connects with the absolute values concerning the model parameters, LASSO (L1) regularization allows a penalty term by shrinking some coefficients to zero [33]. L1 provides the regression coefficients to be overcome to zero, collecting aggregated important features concurrently.…”

Section: Embedded Methodsmentioning

confidence: 99%

A Novel Method for Survival Prediction of Hepatocellular Carcinoma Using Feature-Selection Techniques

Ali

Orban

Ramasamy³

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

The World Health Organization (WHO) predicted that 10 million people would have died of cancer by 2020. According to recent studies, liver cancer is the most prevalent cancer worldwide. Hepatocellular carcinoma (HCC) is the leading cause of early-stage liver cancer. However, HCC occurs most frequently in patients with chronic liver conditions (such as cirrhosis). Therefore, it is important to predict liver cancer more explicitly by using machine learning. This study examines the survival prediction of a dataset of HCC based on three strategies. Originally, missing values are estimated using mean, mode, and k-Nearest Neighbor (k-NN). We then compare the different select features using the wrapper and embedded methods. The embedded method employs Least Absolute Shrinkage and Selection Operator (LASSO) and ridge regression in conjunction with Logistic Regression (LR). In the wrapper method, gradient boosting and random forests eliminate features recursively. Classification algorithms for predicting results include k-NN, Random Forest (RF), and Logistic Regression. The experimental results indicate that Recursive Feature Elimination with Gradient Boosting (RFE-GB) produces better results, with a 96.66% accuracy rate and a 95.66% F1-score.

show abstract

Section: Embedded Methodsmentioning

confidence: 99%

A Novel Method for Survival Prediction of Hepatocellular Carcinoma Using Feature-Selection Techniques

Ali

Orban

Ramasamy³

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…We excluded the features with zero variance using the variance filtering method. Fourth, we performed the LASSO method for further dimensionality reduction of the features and selected the most valuable features (11). We then repeated the 10fold cross-validation on training and validation set process 100,000 times to obtain the optimal value of parameter l, which we introduced into the LASSO method to calculate the regression coefficients of each feature.…”

Section: Feature Extraction and Selectionmentioning

confidence: 99%

“…Finally, we chose a l value of 0.029470517025518096. After dimensionality reduction with LASSO regression, 14 features were selected, consisting of original (3) and wavelet features (11). The subset of features ultimately selected by the LASSO algorithm is shown in Table 2.…”

Section: Feature Selectionmentioning

confidence: 99%

Machine learning prediction of prostate cancer from transrectal ultrasound video clips

et al. 2022

View full text Add to dashboard Cite

ObjectiveTo build a machine learning (ML) prediction model for prostate cancer (PCa) from transrectal ultrasound video clips of the whole prostate gland, diagnostic performance was compared with magnetic resonance imaging (MRI).MethodsWe systematically collated data from 501 patients—276 with prostate cancer and 225 with benign lesions. From a final selection of 231 patients (118 with prostate cancer and 113 with benign lesions), we randomly chose 170 for the purpose of training and validating a machine learning model, while using the remaining 61 to test a derived model. We extracted 851 features from ultrasound video clips. After dimensionality reduction with the least absolute shrinkage and selection operator (LASSO) regression, 14 features were finally selected and the support vector machine (SVM) and random forest (RF) algorithms were used to establish radiomics models based on those features. In addition, we creatively proposed a machine learning models aided diagnosis algorithm (MLAD) composed of SVM, RF, and radiologists’ diagnosis based on MRI to evaluate the performance of ML models in computer-aided diagnosis (CAD). We evaluated the area under the curve (AUC) as well as the sensitivity, specificity, and precision of the ML models and radiologists’ diagnosis based on MRI by employing receiver operator characteristic curve (ROC) analysis.ResultsThe AUC, sensitivity, specificity, and precision of the SVM in the diagnosis of PCa in the validation set and the test set were 0.78, 63%, 80%; 0.75, 65%, and 67%, respectively. Additionally, the SVM model was found to be superior to senior radiologists’ (SR, more than 10 years of experience) diagnosis based on MRI (AUC, 0.78 vs. 0.75 in the validation set and 0.75 vs. 0.72 in the test set), and the difference was statistically significant (p< 0.05).ConclusionThe prediction model constructed by the ML algorithm has good diagnostic efficiency for prostate cancer. The SVM model’s diagnostic efficiency is superior to that of MRI, as it has a more focused application value. Overall, these prediction models can aid radiologists in making better diagnoses.

show abstract

“…Ultrasound has become one of the most common examination methods for the liver because of its non-invasive and non-radiative properties, more applicable population, repeated observation and relatively low cost (42). As a branch of radiomics, ultrasomics has been successfully applied to the accurate diagnosis of various malignant tumors, such as liver cancer, thyroid cancer and breast cancer, with good results (43)(44)(45)(46)(47). However, there are few reports about the prediction of CK19 expression in HCC patients based on ultrasomics method.…”

Section: Introductionmentioning

confidence: 99%

Ultrasomics prediction for cytokeratin 19 expression in hepatocellular carcinoma: A multicenter study

Zhang

Qi²,

Li³

et al. 2022

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

ObjectiveThe purpose of this study was to investigate the preoperative prediction of Cytokeratin (CK) 19 expression in patients with hepatocellular carcinoma (HCC) by machine learning-based ultrasomics.MethodsWe retrospectively analyzed 214 patients with pathologically confirmed HCC who received CK19 immunohistochemical staining. Through random stratified sampling (ratio, 8:2), patients from institutions I and II were divided into training dataset (n = 143) and test dataset (n = 36), and patients from institution III served as external validation dataset (n = 35). All gray-scale ultrasound images were preprocessed, and then the regions of interest were then manually segmented by two sonographers. A total of 1409 ultrasomics features were extracted from the original and derived images. Next, the intraclass correlation coefficient, variance threshold, mutual information, and embedded method were applied to feature dimension reduction. Finally, the clinical model, ultrasonics model, and combined model were constructed by eXtreme Gradient Boosting algorithm. Model performance was assessed by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.ResultsA total of 12 ultrasomics signatures were used to construct the ultrasomics models. In addition, 21 clinical features were used to construct the clinical model, including gender, age, Child-Pugh classification, hepatitis B surface antigen/hepatitis C virus antibody (positive/negative), cirrhosis (yes/no), splenomegaly (yes/no), tumor location, tumor maximum diameter, tumor number, alpha-fetoprotein, alanine aminotransferase, aspartate aminotransferase, alkaline phosphatase, glutamyl-transpeptidase, albumin, total bilirubin, conjugated bilirubin, creatinine, prothrombin time, fibrinogen, and international normalized ratio. The AUC of the ultrasomics model was 0.789 (0.621 – 0.907) and 0.787 (0.616 – 0.907) in the test and validation datasets, respectively. However, the performance of the combined model covering clinical features and ultrasomics signatures improved significantly. Additionally, the AUC (95% CI), sensitivity, specificity, and accuracy were 0.867 (0.712 – 0.957), 0.750, 0.875, 0.861, and 0.862 (0.703 – 0.955), 0.833, 0.862, and 0.857 in the test dataset and external validation dataset, respectively.ConclusionUltrasomics signatures could be used to predict the expression of CK19 in HCC patients. The combination of clinical features and ultrasomics signatures showed excellent effects, which significantly improved prediction accuracy and robustness.

show abstract

Preoperative prediction of pathological grading of hepatocellular carcinoma using machine learning-based ultrasomics: A multicenter study

Cited by 15 publications

References 37 publications

A Novel Method for Survival Prediction of Hepatocellular Carcinoma Using Feature-Selection Techniques

A Novel Method for Survival Prediction of Hepatocellular Carcinoma Using Feature-Selection Techniques

Machine learning prediction of prostate cancer from transrectal ultrasound video clips

Ultrasomics prediction for cytokeratin 19 expression in hepatocellular carcinoma: A multicenter study

Contact Info

Product

Resources

About