Cargando…
Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses
Ultrasound (US) is often used to diagnose liver masses. Ensemble learning has recently been commonly used for image classification, but its detailed methods are not fully optimized. The purpose of this study is to investigate the usefulness and comparison of some ensemble learning and ensemble pruni...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9854883/ https://www.ncbi.nlm.nih.gov/pubmed/36671641 http://dx.doi.org/10.3390/bioengineering10010069 |
_version_ | 1784873238629711872 |
---|---|
author | Nakata, Norio Siina, Tsuyoshi |
author_facet | Nakata, Norio Siina, Tsuyoshi |
author_sort | Nakata, Norio |
collection | PubMed |
description | Ultrasound (US) is often used to diagnose liver masses. Ensemble learning has recently been commonly used for image classification, but its detailed methods are not fully optimized. The purpose of this study is to investigate the usefulness and comparison of some ensemble learning and ensemble pruning techniques using multiple convolutional neural network (CNN) trained models for image classification of liver masses in US images. Dataset of the US images were classified into four categories: benign liver tumor (BLT) 6320 images, liver cyst (LCY) 2320 images, metastatic liver cancer (MLC) 9720 images, primary liver cancer (PLC) 7840 images. In this study, 250 test images were randomly selected for each class, for a total of 1000 images, and the remaining images were used as the training. 16 different CNNs were used for training and testing ultrasound images. The ensemble learning used soft voting (SV), weighted average voting (WAV), weighted hard voting (WHV) and stacking (ST). All four types of ensemble learning (SV, ST, WAV, and WHV) showed higher values of accuracy than the single CNN. All four types also showed significantly higher deep learning (DL) performance than ResNeXt101 alone. For image classification of liver masses using US images, ensemble learning improved the performance of DL over a single CNN. |
format | Online Article Text |
id | pubmed-9854883 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-98548832023-01-21 Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses Nakata, Norio Siina, Tsuyoshi Bioengineering (Basel) Article Ultrasound (US) is often used to diagnose liver masses. Ensemble learning has recently been commonly used for image classification, but its detailed methods are not fully optimized. The purpose of this study is to investigate the usefulness and comparison of some ensemble learning and ensemble pruning techniques using multiple convolutional neural network (CNN) trained models for image classification of liver masses in US images. Dataset of the US images were classified into four categories: benign liver tumor (BLT) 6320 images, liver cyst (LCY) 2320 images, metastatic liver cancer (MLC) 9720 images, primary liver cancer (PLC) 7840 images. In this study, 250 test images were randomly selected for each class, for a total of 1000 images, and the remaining images were used as the training. 16 different CNNs were used for training and testing ultrasound images. The ensemble learning used soft voting (SV), weighted average voting (WAV), weighted hard voting (WHV) and stacking (ST). All four types of ensemble learning (SV, ST, WAV, and WHV) showed higher values of accuracy than the single CNN. All four types also showed significantly higher deep learning (DL) performance than ResNeXt101 alone. For image classification of liver masses using US images, ensemble learning improved the performance of DL over a single CNN. MDPI 2023-01-05 /pmc/articles/PMC9854883/ /pubmed/36671641 http://dx.doi.org/10.3390/bioengineering10010069 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 Nakata, Norio Siina, Tsuyoshi Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses |
title | Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses |
title_full | Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses |
title_fullStr | Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses |
title_full_unstemmed | Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses |
title_short | Ensemble Learning of Multiple Models Using Deep Learning for Multiclass Classification of Ultrasound Images of Hepatic Masses |
title_sort | ensemble learning of multiple models using deep learning for multiclass classification of ultrasound images of hepatic masses |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9854883/ https://www.ncbi.nlm.nih.gov/pubmed/36671641 http://dx.doi.org/10.3390/bioengineering10010069 |
work_keys_str_mv | AT nakatanorio ensemblelearningofmultiplemodelsusingdeeplearningformulticlassclassificationofultrasoundimagesofhepaticmasses AT siinatsuyoshi ensemblelearningofmultiplemodelsusingdeeplearningformulticlassclassificationofultrasoundimagesofhepaticmasses |