Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods
Hepatocellular Carcinoma (HCC) is the most common malignant liver tumor, being present in 70% of liver cancer cases. It usually evolves on the top of the cirrhotic parenchyma. The most reliable method for HCC diagnosis is the needle biopsy, which is an invasive, dangerous method. In our research, sp...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/6/2202 |
id |
doaj-5315beec09f043cba79edf96c39b3cfc |
---|---|
record_format |
Article |
spelling |
doaj-5315beec09f043cba79edf96c39b3cfc2021-03-22T00:02:55ZengMDPI AGSensors1424-82202021-03-01212202220210.3390/s21062202Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning MethodsDelia Mitrea0Radu Badea1Paulina Mitrea2Stelian Brad3Sergiu Nedevschi4Department of Computer Science, Faculty of Automation and Computer Science, Technical University of Cluj-Napoca, Baritiu Street, No. 26-28, 400027 Cluj-Napoca, RomaniaMedical Imaging Department, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Babes Street, No. 8, 400012 Cluj-Napoca, RomaniaDepartment of Computer Science, Faculty of Automation and Computer Science, Technical University of Cluj-Napoca, Baritiu Street, No. 26-28, 400027 Cluj-Napoca, RomaniaDepartment of Design Engineering and Robotics, Faculty of Machine Building, Technical University of Cluj-Napoca, Muncii Boulevard, No. 103-105, 400641 Cluj-Napoca, RomaniaDepartment of Computer Science, Faculty of Automation and Computer Science, Technical University of Cluj-Napoca, Baritiu Street, No. 26-28, 400027 Cluj-Napoca, RomaniaHepatocellular Carcinoma (HCC) is the most common malignant liver tumor, being present in 70% of liver cancer cases. It usually evolves on the top of the cirrhotic parenchyma. The most reliable method for HCC diagnosis is the needle biopsy, which is an invasive, dangerous method. In our research, specific techniques for non-invasive, computerized HCC diagnosis are developed, by exploiting the information from ultrasound images. In this work, the possibility of performing the automatic diagnosis of HCC within B-mode ultrasound and Contrast-Enhanced Ultrasound (CEUS) images, using advanced machine learning methods based on Convolutional Neural Networks (CNN), was assessed. The recognition performance was evaluated separately on B-mode ultrasound images and on CEUS images, respectively, as well as on combined B-mode ultrasound and CEUS images. For this purpose, we considered the possibility of combining the input images directly, performing feature level fusion, then providing the resulted data at the entrances of representative CNN classifiers. In addition, several multimodal combined classifiers were experimented, resulted by the fusion, at classifier, respectively, at the decision levels of two different branches based on the same CNN architecture, as well as on different CNN architectures. Various combination methods, and also the dimensionality reduction method of Kernel Principal Component Analysis (KPCA), were involved in this process. These results were compared with those obtained on the same dataset, when employing advanced texture analysis techniques in conjunction with conventional classification methods and also with equivalent state-of-the-art approaches. An accuracy above 97% was achieved when our new methodology was applied.https://www.mdpi.com/1424-8220/21/6/2202hepatocellular carcinoma (HCC)contrast-enhanced ultrasound (CEUS) imagesmultimodal combined CNN classifiersfeature level fusionclassifier level fusiondecision level fusion |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Delia Mitrea Radu Badea Paulina Mitrea Stelian Brad Sergiu Nedevschi |
spellingShingle |
Delia Mitrea Radu Badea Paulina Mitrea Stelian Brad Sergiu Nedevschi Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods Sensors hepatocellular carcinoma (HCC) contrast-enhanced ultrasound (CEUS) images multimodal combined CNN classifiers feature level fusion classifier level fusion decision level fusion |
author_facet |
Delia Mitrea Radu Badea Paulina Mitrea Stelian Brad Sergiu Nedevschi |
author_sort |
Delia Mitrea |
title |
Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods |
title_short |
Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods |
title_full |
Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods |
title_fullStr |
Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods |
title_full_unstemmed |
Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods |
title_sort |
hepatocellular carcinoma automatic diagnosis within ceus and b-mode ultrasound images using advanced machine learning methods |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-03-01 |
description |
Hepatocellular Carcinoma (HCC) is the most common malignant liver tumor, being present in 70% of liver cancer cases. It usually evolves on the top of the cirrhotic parenchyma. The most reliable method for HCC diagnosis is the needle biopsy, which is an invasive, dangerous method. In our research, specific techniques for non-invasive, computerized HCC diagnosis are developed, by exploiting the information from ultrasound images. In this work, the possibility of performing the automatic diagnosis of HCC within B-mode ultrasound and Contrast-Enhanced Ultrasound (CEUS) images, using advanced machine learning methods based on Convolutional Neural Networks (CNN), was assessed. The recognition performance was evaluated separately on B-mode ultrasound images and on CEUS images, respectively, as well as on combined B-mode ultrasound and CEUS images. For this purpose, we considered the possibility of combining the input images directly, performing feature level fusion, then providing the resulted data at the entrances of representative CNN classifiers. In addition, several multimodal combined classifiers were experimented, resulted by the fusion, at classifier, respectively, at the decision levels of two different branches based on the same CNN architecture, as well as on different CNN architectures. Various combination methods, and also the dimensionality reduction method of Kernel Principal Component Analysis (KPCA), were involved in this process. These results were compared with those obtained on the same dataset, when employing advanced texture analysis techniques in conjunction with conventional classification methods and also with equivalent state-of-the-art approaches. An accuracy above 97% was achieved when our new methodology was applied. |
topic |
hepatocellular carcinoma (HCC) contrast-enhanced ultrasound (CEUS) images multimodal combined CNN classifiers feature level fusion classifier level fusion decision level fusion |
url |
https://www.mdpi.com/1424-8220/21/6/2202 |
work_keys_str_mv |
AT deliamitrea hepatocellularcarcinomaautomaticdiagnosiswithinceusandbmodeultrasoundimagesusingadvancedmachinelearningmethods AT radubadea hepatocellularcarcinomaautomaticdiagnosiswithinceusandbmodeultrasoundimagesusingadvancedmachinelearningmethods AT paulinamitrea hepatocellularcarcinomaautomaticdiagnosiswithinceusandbmodeultrasoundimagesusingadvancedmachinelearningmethods AT stelianbrad hepatocellularcarcinomaautomaticdiagnosiswithinceusandbmodeultrasoundimagesusingadvancedmachinelearningmethods AT sergiunedevschi hepatocellularcarcinomaautomaticdiagnosiswithinceusandbmodeultrasoundimagesusingadvancedmachinelearningmethods |
_version_ |
1724209608506998784 |