Authors: | Midya, A.; Chakraborty, J.; Pak, L. M.; Zheng, J.; Jarnagin, W. R.; Do, R. K. G.; Simpson, A. L. |
Editors: | Mori, K.; Petrick, N. |
Title: | Deep convolutional neural network for the classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma |
Conference Title: | Medical Imaging 2018: Computer-Aided Diagnosis |
Abstract: | Liver cancer is the second leading cause of cancer-related death worldwide.1 Hepatocellular carcinoma (HCC) is the most common primary liver cancer accounting for approximately 80% of cases. Intrahepatic cholangiocarcinoma (ICC) is a rare liver cancer, arising in patients with the same risk factors as HCC, but treatment options and prognosis differ. The diagnosis of HCC is based primarily on imaging but distinguishing between HCC and ICC is challenging due to common radiographic features.2-4 The aim of the present study is to classify HCC and ICC in portal venous phase CT. 107 patients with resected ICC and 116 patients with resected HCC were included in our analysis. We developed a deep neural network by modifying a pre-trained Inception network by retraining the final layers. The proposed method achieved the best accuracy and area under the receiver operating characteristics curve of 69.70% and 0.72, respectively on the test data. © 2018 SPIE. |
Keywords: | hepatocellular carcinoma; risk factors; computerized tomography; medical imaging; intrahepatic cholangiocarcinoma; cholangiocarcinoma; patient treatment; diseases; computer aided diagnosis; neural networks; treatment stratification; receiver operating characteristics; deep neural networks; deep neural network; inception net; deep convolutional neural networks; liver cancers; primary liver cancers |
Journal Title | Proceedings of SPIE |
Volume: | 10575 |
Conference Dates: | 2018 Feb 12-15 |
Conference Location: | Houston, TX |
ISBN: | 0277-786X |
Publisher: | SPIE |
Date Published: | 2018-02-27 |
Start Page: | 10575 28 |
Language: | English |
DOI: | 10.1117/12.2293683 |
PROVIDER: | scopus |
DOI/URL: | |
Notes: | Conference Paper -- Export Date: 1 June 2018 -- Source: Scopus |