Deep learning-assisted differentiation of pathologically proven atypical and typical hepatocellular carcinoma (HCC) versus non-HCC on contrast-enhanced MRI of the liver

Objectives To train a deep learning model to differentiate between pathologically proven hepatocellular carcinoma (HCC) and non-HCC lesions including lesions with atypical imaging features on MRI. Methods This IRB-approved retrospective study included 118 patients with 150 lesions (93 (62%) HCC and 57 (38%) non-HCC) pathologically confirmed through biopsies (n = 72), resections (n = 29), liver transplants (n = 46), and autopsies (n = 3). Forty-seven percent of HCC lesions showed atypical imaging features (not meeting Liver Imaging Reporting and Data System [LI-RADS] criteria for definitive HCC/LR5). A 3D convolutional neural network (CNN) was trained on 140 lesions and tested for its ability to classify the 10 remaining lesions (5 HCC/5 non-HCC). Performance of the model was averaged over 150 runs with random sub-sampling to provide class-balanced test sets. A lesion grading system was developed to demonstrate the similarity between atypical HCC and non-HCC lesions prone to misclassification by the CNN. Results The CNN demonstrated an overall accuracy of 87.3%. Sensitivities/specificities for HCC and non-HCC lesions were 92.7%/82.0% and 82.0%/92.7%, respectively. The area under the receiver operating curve was 0.912. CNN's performance was correlated with the lesion grading system, becoming less accurate the more atypical imaging features the lesions showed. Conclusion This study provides proof-of-concept for CNN-based classification of both typical- and atypical-appearing HCC lesions on multi-phasic MRI, utilizing pathologically confirmed lesions as ground truth.

Automated summary

This study successfully trained a deep learning model to differentiate between pathologically confirmed HCC and non-HCC lesions on MRI, with good overall accuracy but lower accuracy for lesions with more atypical imaging features.