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...

Full description

Saved in:

Bibliographic Details
Published in:	European radiology Vol. 31; no. 7; pp. 4981 - 4990
Main Authors:	Oestmann, Paula M., Wang, Clinton J., Savic, Lynn J., Hamm, Charlie A., Stark, Sophie, Schobert, Isabel, Gebauer, Bernhard, Schlachter, Todd, Lin, MingDe, Weinreb, Jeffrey C., Batra, Ramesh, Mulligan, David, Zhang, Xuchen, Duncan, James S., Chapiro, Julius
Format:	Journal Article
Language:	English
Published:	Berlin/Heidelberg Springer Berlin Heidelberg 01-07-2021 Springer Nature B.V
Subjects:	Accuracy Artificial neural networks Autopsies Carcinoma, Hepatocellular - diagnostic imaging Computer applications Computing time Contrast Media Criteria Deep Learning Diagnostic Radiology Hepatocellular carcinoma Humans Imaging Imaging Informatics and Artificial Intelligence Internal Medicine Interventional Radiology Lesions Liver Liver cancer Liver Neoplasms - diagnostic imaging Liver transplantation Machine learning Magnetic Resonance Imaging Medical imaging Medicine Medicine & Public Health Neural networks Neuroradiology Radiology Retrospective Studies Transplants Ultrasound Carcinoma, hepatocellular Deep learning Neural networks, computer Magnetic resonance imaging Liver neoplasms
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.” Key Points • A CNN trained on atypical appearing pathologically proven HCC lesions not meeting LI-RADS criteria for definitive HCC (LR5) can correctly differentiate HCC lesions from other liver malignancies, potentially expanding the role of image-based diagnosis in primary liver cancer with atypical features. • The trained CNN demonstrated an overall accuracy of 87.3% and a computational time of < 3 ms which paves the way for clinical application as a decision support instrument.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0938-7994 1432-1084
DOI:	10.1007/s00330-020-07559-1