Detection of Hepatocellular Carcinoma in Contrast-Enhanced Magnetic Resonance Imaging Using Deep Learning Classifier: A Multi-Center Retrospective Study

Hepatocellular carcinoma (HCC) is one of the most common malignant tumors and a leading cause of cancer-related death worldwide. We propose a fully automated deep learning model to detect HCC using hepatobiliary phase magnetic resonance images from 549 patients who underwent surgical resection. Our...

Full description

Saved in:
Bibliographic Details
Published inScientific reports Vol. 10; no. 1; p. 9458
Main Authors Kim, Junmo, Min, Ji Hye, Kim, Seon Kyoung, Shin, Soo-Yong, Lee, Min Woo
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 11.06.2020
Nature Publishing Group
Subjects
631/67/2322
639/705/794
Deep learning
Hepatocellular carcinoma
Humanities and Social Sciences
Liver cancer
Magnetic resonance imaging
multidisciplinary
Neural networks
Science
Science (multidisciplinary)
Tumors
Online AccessGet full text

Cover

More Information
Summary:Hepatocellular carcinoma (HCC) is one of the most common malignant tumors and a leading cause of cancer-related death worldwide. We propose a fully automated deep learning model to detect HCC using hepatobiliary phase magnetic resonance images from 549 patients who underwent surgical resection. Our model used a fine-tuned convolutional neural network and achieved 87% sensitivity and 93% specificity for the detection of HCCs with an external validation data set (54 patients). We also confirmed whether the lesion detected by our deep learning model is a true lesion using a class activation map.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-65875-4