Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans

© 2020, International Federation for Medical and Biological Engineering. Liver and bile duct cancers are leading causes of worldwide cancer death. The most common ones are hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). Influencing factors and prognosis of HCC and ICC are d...

Full description

Saved in:
Bibliographic Details
Main Authors: Donlapark Ponnoprat, Papangkorn Inkeaw, Jeerayut Chaijaruwanich, Patrinee Traisathit, Patumrat Sripan, Nakarin Inmutto, Wittanee Na Chiangmai, Donsuk Pongnikorn, Imjai Chitapanarux
Format: Journal
Published: 2020
Subjects:
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089394837&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/70415
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-70415
record_format dspace
spelling th-cmuir.6653943832-704152020-10-14T08:33:28Z Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans Donlapark Ponnoprat Papangkorn Inkeaw Jeerayut Chaijaruwanich Patrinee Traisathit Patumrat Sripan Nakarin Inmutto Wittanee Na Chiangmai Donsuk Pongnikorn Imjai Chitapanarux Computer Science Engineering © 2020, International Federation for Medical and Biological Engineering. Liver and bile duct cancers are leading causes of worldwide cancer death. The most common ones are hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). Influencing factors and prognosis of HCC and ICC are different. Precise classification of these two liver cancers is essential for treatment and prevention plans. The aim of this study is to develop a machine-based method that differentiates between the two types of liver cancers from multi-phase abdominal computerized tomography (CT) scans. The proposed method consists of two major steps. In the first step, the liver is segmented from the original images using a convolutional neural network model, together with task-specific pre-processing and post-processing techniques. In the second step, by looking at the intensity histograms of the segmented images, we extract features from regions that are discriminating between HCC and ICC, and use them as an input for classification using support vector machine model. By testing on a dataset of labeled multi-phase CT scans provided by Maharaj Nakorn Chiang Mai Hospital, Thailand, we have obtained 88% in classification accuracy. Our proposed method has a great potential in helping radiologists diagnosing liver cancer. 2020-10-14T08:30:04Z 2020-10-14T08:30:04Z 2020-10-01 Journal 17410444 01400118 2-s2.0-85089394837 10.1007/s11517-020-02229-2 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089394837&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/70415
institution Chiang Mai University
building Chiang Mai University Library
continent Asia
country Thailand
Thailand
content_provider Chiang Mai University Library
collection CMU Intellectual Repository
topic Computer Science
Engineering
spellingShingle Computer Science
Engineering
Donlapark Ponnoprat
Papangkorn Inkeaw
Jeerayut Chaijaruwanich
Patrinee Traisathit
Patumrat Sripan
Nakarin Inmutto
Wittanee Na Chiangmai
Donsuk Pongnikorn
Imjai Chitapanarux
Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans
description © 2020, International Federation for Medical and Biological Engineering. Liver and bile duct cancers are leading causes of worldwide cancer death. The most common ones are hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). Influencing factors and prognosis of HCC and ICC are different. Precise classification of these two liver cancers is essential for treatment and prevention plans. The aim of this study is to develop a machine-based method that differentiates between the two types of liver cancers from multi-phase abdominal computerized tomography (CT) scans. The proposed method consists of two major steps. In the first step, the liver is segmented from the original images using a convolutional neural network model, together with task-specific pre-processing and post-processing techniques. In the second step, by looking at the intensity histograms of the segmented images, we extract features from regions that are discriminating between HCC and ICC, and use them as an input for classification using support vector machine model. By testing on a dataset of labeled multi-phase CT scans provided by Maharaj Nakorn Chiang Mai Hospital, Thailand, we have obtained 88% in classification accuracy. Our proposed method has a great potential in helping radiologists diagnosing liver cancer.
format Journal
author Donlapark Ponnoprat
Papangkorn Inkeaw
Jeerayut Chaijaruwanich
Patrinee Traisathit
Patumrat Sripan
Nakarin Inmutto
Wittanee Na Chiangmai
Donsuk Pongnikorn
Imjai Chitapanarux
author_facet Donlapark Ponnoprat
Papangkorn Inkeaw
Jeerayut Chaijaruwanich
Patrinee Traisathit
Patumrat Sripan
Nakarin Inmutto
Wittanee Na Chiangmai
Donsuk Pongnikorn
Imjai Chitapanarux
author_sort Donlapark Ponnoprat
title Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans
title_short Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans
title_full Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans
title_fullStr Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans
title_full_unstemmed Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans
title_sort classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase ct scans
publishDate 2020
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089394837&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/70415
_version_ 1681752898522841088