Preoperative prediction for pathological grade of hepatocellular carcinoma via machine learning–based radiomics

• Published in: European radiology Vol. 30; no. 12; pp. 6924 - 6932
• Main Authors: Mao, Bing, Zhang, Lianzhong, Ning, Peigang, Ding, Feng, Wu, Fatian, Lu, Gary, Geng, Yayuan, Ma, Jingdong
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2020; Springer Nature B.V
• Subjects: Accuracy; Adult; Aged; Area Under Curve; Carcinoma, Hepatocellular - diagnostic imaging; Carcinoma, Hepatocellular - pathology; Computed tomography; Confidence intervals; Datasets; Diagnosis, Computer-Assisted - methods; Diagnostic Radiology; Feature extraction; Female; Hepatocellular carcinoma; Humans; Image enhancement; Image Processing, Computer-Assisted - methods; Image segmentation; Imaging; Imaging Informatics and Artificial Intelligence; Internal Medicine; Interventional Radiology; Itk protein; Learning algorithms; Liver cancer; Liver Neoplasms - diagnostic imaging; Liver Neoplasms - pathology; Machine Learning; Male; Medicine; Medicine & Public Health; Middle Aged; Neuroradiology; Prediction models; Radiology; Radiomics; Reproducibility of Results; Retrospective Studies; ROC Curve; Sensitivity; Sensitivity and Specificity; Signatures; Standard deviation; Tomography, X-Ray Computed; Ultrasound; Biomarkers; Hepatocellular carcinoma; Neoplasm grading; Machine learning; Multidetector computed tomography
• ISSN: 0938-7994; 1432-1084; 1432-1084
• DOI: 10.1007/s00330-020-07056-5

Objective To investigate the efficacy of contrast-enhanced computed tomography (CECT)–based radiomics signatures for preoperative prediction of pathological grades of hepatocellular carcinoma (HCC) via machine learning. Methods In this single-center retrospective study, data collected from 297 consecutive subjects with HCC were allocated to training dataset ( n  = 237) and test dataset ( n  = 60). Manual segmentation of lesion sites was performed with ITK-SNAP, the radiomics features were extracted by the Pyradiomics, and radiomics signatures were synthesized using recursive feature elimination (RFE) method. The prediction models for pathological grading of HCC were established by using eXtreme Gradient Boosting (XGBoost). The performance of the models was evaluated using the AUC along with 95% confidence intervals (CIs) and standard deviation, sensitivity, specificity, and accuracy. Results The radiomics signatures were found highly efficient for machine learning to differentiate high-grade HCC from low-grade HCC. For the clinical factors, when they were merely applied to train a machine learning model, the model achieved an AUC of 0.6698, along with 95% CI and standard deviation of 0.5307–0.8089 and 0.0710, respectively (sensitivity, 0.6522; specificity, 0.4595; accuracy, 0.5333). Meanwhile, when the radiomics signatures were applied in association with clinical factors to train a machine learning model, the performance of the model remarkably increased with AUC of 0.8014, along with 95% CI and standard deviation of 0.6899–0.9129 and 0.0569, respectively (sensitivity, 0.6522; specificity, 0.7297; accuracy, 0.7000). Conclusions The radiomics signatures could non-invasively explore the underlying association between CECT images and pathological grades of HCC. Key Points • The radiomics signatures may non-invasively explore the underlying association between CECT images and pathological grades of HCC via machine learning. • The radiomics signatures of CECT images may enhance the prediction performance of pathological grading of HCC , and further validation is required. • The features extracted from arterial phase CECT images may be more reliable than venous phase CECT images for predicting pathological grades of HCC.