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

Citations

WEB OF SCIENCE

57
Citations

SCOPUS

75

초록

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.

키워드

CONVOLUTIONAL NEURAL-NETWORK; PHASE; CT
제목
Detection of Hepatocellular Carcinoma in Contrast-Enhanced Magnetic Resonance Imaging Using Deep Learning Classifier: A Multi-Center Retrospective Study
저자
Kim, Junmo; Min, Ji Hye; Kim, Seon Kyoung; Shin, Soo-Yong; Lee, Min Woo
DOI
10.1038/s41598-020-65875-4
발행일
2020-06-11
유형
Article
저널명
Scientific Reports
권
10
호
1