AUTHOR=Zhang Wei-bin , Hou Si-ze , Chen Yan-ling , Mao Feng , Dong Yi , Chen Jian-gang , Wang Wen-ping 

TITLE=Deep Learning for Approaching Hepatocellular Carcinoma Ultrasound Screening Dilemma: Identification of α-Fetoprotein-Negative Hepatocellular Carcinoma From Focal Liver Lesion Found in High-Risk Patients

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.862297

DOI=10.3389/fonc.2022.862297

ISSN=2234-943X

ABSTRACT=Abstract
Background: First line surveillance on HBV-infected populations with B-mode ultrasound is relatively limited to identify hepatocellular carcinoma (HCC) without elevated α-fetoprotein (AFP). To improve present HCC surveillance strategy, the state-of-the-art of artificial intelligence (AI), a deep learning (DL) approach, is proposed to assist diagnosis of focal liver lesion (FLL) in HBV-infected liver background. 
Methods: Our proposed deep learning model was based on B-mode ultrasound images of surgery proved 209 HCC and 198 focal nodular hyperplasia (FNH) cases with 413 lesions. The model cohort and test cohort were set at a ratio of 3:1, in which the test cohort was composed of AFP-negative HBV-infected cases. Four additional deep learning models (MobileNet, Resnet50, DenseNet121 and InceptionV3) were also constructed as comparative baselines. To evaluate the models in terms of diagnostic power, sensitivity, specificity, accuracy, confusion matrix, F1-score and area under the receiver operator characteristic curve (AUC) were calculated in the test cohort. 
Results: The AUC of our model, Xception, achieved 93.68% in the test cohort, superior to other baselines (89.06%, 85.67%, 83.94% and 78.13% respectively for MobileNet, Resnet50, DenseNet121 and InceptionV3). In terms of diagnostic power, our model showed sensitivity, specificity, accuracy and F1-score of 96.08%, 76.92%, 86.41% and 87.50%, and PPV, NPV, FPR and FNR calculated from the confusion matrix were 80.33%, 95.24%, 23.08% and 3.92% in identifying AFP-negative HCC from HBV-infected FLL cases. Satisfactory robustness of our proposed model was shown based on 5-fold cross validation performed among the models above. 
Conclusions: Our DL approach has great potential to assist B-mode ultrasound on identifying AFP-negative HCC from FLL found in surveillance of HBV-infected patients.