Cargando…

Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques

Hepatocellular Carcinoma (HCC) is the most frequent malignant liver tumor and the third cause of cancer-related deaths worldwide. For many years, the golden standard for HCC diagnosis has been the needle biopsy, which is invasive and carries risks. Computerized methods are due to achieve a noninvasi...

Descripción completa

Detalles Bibliográficos
Autores principales: Mitrea, Delia-Alexandrina, Brehar, Raluca, Nedevschi, Sergiu, Lupsor-Platon, Monica, Socaciu, Mihai, Badea, Radu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006909/
https://www.ncbi.nlm.nih.gov/pubmed/36904722
http://dx.doi.org/10.3390/s23052520
_version_ 1784905387520032768
author Mitrea, Delia-Alexandrina
Brehar, Raluca
Nedevschi, Sergiu
Lupsor-Platon, Monica
Socaciu, Mihai
Badea, Radu
author_facet Mitrea, Delia-Alexandrina
Brehar, Raluca
Nedevschi, Sergiu
Lupsor-Platon, Monica
Socaciu, Mihai
Badea, Radu
author_sort Mitrea, Delia-Alexandrina
collection PubMed
description Hepatocellular Carcinoma (HCC) is the most frequent malignant liver tumor and the third cause of cancer-related deaths worldwide. For many years, the golden standard for HCC diagnosis has been the needle biopsy, which is invasive and carries risks. Computerized methods are due to achieve a noninvasive, accurate HCC detection process based on medical images. We developed image analysis and recognition methods to perform automatic and computer-aided diagnosis of HCC. Conventional approaches that combined advanced texture analysis, mainly based on Generalized Co-occurrence Matrices (GCM) with traditional classifiers, as well as deep learning approaches based on Convolutional Neural Networks (CNN) and Stacked Denoising Autoencoders (SAE), were involved in our research. The best accuracy of 91% was achieved for B-mode ultrasound images through CNN by our research group. In this work, we combined the classical approaches with CNN techniques, within B-mode ultrasound images. The combination was performed at the classifier level. The CNN features obtained at the output of various convolution layers were combined with powerful textural features, then supervised classifiers were employed. The experiments were conducted on two datasets, acquired with different ultrasound machines. The best performance, above 98%, overpassed our previous results, as well as representative state-of-the-art results.
format Online
Article
Text
id pubmed-10006909
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100069092023-03-12 Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques Mitrea, Delia-Alexandrina Brehar, Raluca Nedevschi, Sergiu Lupsor-Platon, Monica Socaciu, Mihai Badea, Radu Sensors (Basel) Article Hepatocellular Carcinoma (HCC) is the most frequent malignant liver tumor and the third cause of cancer-related deaths worldwide. For many years, the golden standard for HCC diagnosis has been the needle biopsy, which is invasive and carries risks. Computerized methods are due to achieve a noninvasive, accurate HCC detection process based on medical images. We developed image analysis and recognition methods to perform automatic and computer-aided diagnosis of HCC. Conventional approaches that combined advanced texture analysis, mainly based on Generalized Co-occurrence Matrices (GCM) with traditional classifiers, as well as deep learning approaches based on Convolutional Neural Networks (CNN) and Stacked Denoising Autoencoders (SAE), were involved in our research. The best accuracy of 91% was achieved for B-mode ultrasound images through CNN by our research group. In this work, we combined the classical approaches with CNN techniques, within B-mode ultrasound images. The combination was performed at the classifier level. The CNN features obtained at the output of various convolution layers were combined with powerful textural features, then supervised classifiers were employed. The experiments were conducted on two datasets, acquired with different ultrasound machines. The best performance, above 98%, overpassed our previous results, as well as representative state-of-the-art results. MDPI 2023-02-24 /pmc/articles/PMC10006909/ /pubmed/36904722 http://dx.doi.org/10.3390/s23052520 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Mitrea, Delia-Alexandrina
Brehar, Raluca
Nedevschi, Sergiu
Lupsor-Platon, Monica
Socaciu, Mihai
Badea, Radu
Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques
title Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques
title_full Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques
title_fullStr Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques
title_full_unstemmed Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques
title_short Hepatocellular Carcinoma Recognition from Ultrasound Images Using Combinations of Conventional and Deep Learning Techniques
title_sort hepatocellular carcinoma recognition from ultrasound images using combinations of conventional and deep learning techniques
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006909/
https://www.ncbi.nlm.nih.gov/pubmed/36904722
http://dx.doi.org/10.3390/s23052520
work_keys_str_mv AT mitreadeliaalexandrina hepatocellularcarcinomarecognitionfromultrasoundimagesusingcombinationsofconventionalanddeeplearningtechniques
AT breharraluca hepatocellularcarcinomarecognitionfromultrasoundimagesusingcombinationsofconventionalanddeeplearningtechniques
AT nedevschisergiu hepatocellularcarcinomarecognitionfromultrasoundimagesusingcombinationsofconventionalanddeeplearningtechniques
AT lupsorplatonmonica hepatocellularcarcinomarecognitionfromultrasoundimagesusingcombinationsofconventionalanddeeplearningtechniques
AT socaciumihai hepatocellularcarcinomarecognitionfromultrasoundimagesusingcombinationsofconventionalanddeeplearningtechniques
AT badearadu hepatocellularcarcinomarecognitionfromultrasoundimagesusingcombinationsofconventionalanddeeplearningtechniques