Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment

Abstract We propose a random forest classifier for identifying adequacy of liver MR images using handcrafted (HC) features and deep convolutional neural networks (CNNs), and analyze the relative role of these two components in relation to the training sample size. The HC features, specifically devel...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wenyi Lin, Kyle Hasenstab, Guilherme Moura Cunha, Armin Schwartzman
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
R
Q
Acceso en línea:https://doaj.org/article/8163ba569a264ccba16c94fb8f0d2882
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8163ba569a264ccba16c94fb8f0d2882
record_format dspace
spelling oai:doaj.org-article:8163ba569a264ccba16c94fb8f0d28822021-12-02T12:33:53ZComparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment10.1038/s41598-020-77264-y2045-2322https://doaj.org/article/8163ba569a264ccba16c94fb8f0d28822020-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-77264-yhttps://doaj.org/toc/2045-2322Abstract We propose a random forest classifier for identifying adequacy of liver MR images using handcrafted (HC) features and deep convolutional neural networks (CNNs), and analyze the relative role of these two components in relation to the training sample size. The HC features, specifically developed for this application, include Gaussian mixture models, Euler characteristic curves and texture analysis. Using HC features outperforms the CNN for smaller sample sizes and with increased interpretability. On the other hand, with enough training data, the combined classifier outperforms the models trained with HC features or CNN features alone. These results illustrate the added value of HC features with respect to CNNs, especially when insufficient data is available, as is often found in clinical studies.Wenyi LinKyle HasenstabGuilherme Moura CunhaArmin SchwartzmanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-11 (2020)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Wenyi Lin
Kyle Hasenstab
Guilherme Moura Cunha
Armin Schwartzman
Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment
description Abstract We propose a random forest classifier for identifying adequacy of liver MR images using handcrafted (HC) features and deep convolutional neural networks (CNNs), and analyze the relative role of these two components in relation to the training sample size. The HC features, specifically developed for this application, include Gaussian mixture models, Euler characteristic curves and texture analysis. Using HC features outperforms the CNN for smaller sample sizes and with increased interpretability. On the other hand, with enough training data, the combined classifier outperforms the models trained with HC features or CNN features alone. These results illustrate the added value of HC features with respect to CNNs, especially when insufficient data is available, as is often found in clinical studies.
format article
author Wenyi Lin
Kyle Hasenstab
Guilherme Moura Cunha
Armin Schwartzman
author_facet Wenyi Lin
Kyle Hasenstab
Guilherme Moura Cunha
Armin Schwartzman
author_sort Wenyi Lin
title Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment
title_short Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment
title_full Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment
title_fullStr Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment
title_full_unstemmed Comparison of handcrafted features and convolutional neural networks for liver MR image adequacy assessment
title_sort comparison of handcrafted features and convolutional neural networks for liver mr image adequacy assessment
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/8163ba569a264ccba16c94fb8f0d2882
work_keys_str_mv AT wenyilin comparisonofhandcraftedfeaturesandconvolutionalneuralnetworksforlivermrimageadequacyassessment
AT kylehasenstab comparisonofhandcraftedfeaturesandconvolutionalneuralnetworksforlivermrimageadequacyassessment
AT guilhermemouracunha comparisonofhandcraftedfeaturesandconvolutionalneuralnetworksforlivermrimageadequacyassessment
AT arminschwartzman comparisonofhandcraftedfeaturesandconvolutionalneuralnetworksforlivermrimageadequacyassessment
_version_ 1718393869031178240