AUTHOR=Li Wei , Lv Xiao-Zhou , Zheng Xin , Ruan Si-Min , Hu Hang-Tong , Chen Li-Da , Huang Yang , Li Xin , Zhang Chu-Qing , Xie Xiao-Yan , Kuang Ming , Lu Ming-De , Zhuang Bo-Wen , Wang Wei 

TITLE=Machine Learning-Based Ultrasomics Improves the Diagnostic Performance in Differentiating Focal Nodular Hyperplasia and Atypical Hepatocellular Carcinoma

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.544979

DOI=10.3389/fonc.2021.544979

ISSN=2234-943X

ABSTRACT=Background
The typical enhancement patterns of hepatocellular carcinoma (HCC) on contrast-enhanced ultrasound (CEUS) are hyper-enhancement in the arterial phase and wash-out during the portal venous and late phases. However, atypical variations making the differential diagnosis both challenging and crucial. We aimed to investigate whether machine learning-based ultrasomics signature derived from CEUS images could improve the diagnostic performance in differentiating focal nodular hyperplasia (FNH) and atypical hepatocellular carcinoma (aHCC).
Patients and Methods
Two hundred twenty-six 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 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).
Results
Fourteen 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). 
Conclusions
Machine learning-based ultrasomics is as good 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.