Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation

Abstract Introduction and goal to background Due to the importance of segmentation of MRI images in identifying brain tumors, various methods including deep learning have been introduced for automatic brain tumor segmentation. On the other hand, using a combination of methods can improve their perfo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohamadreza Hajiabadi, Behrouz Alizadeh Savareh, Hassan Emami, Azadeh Bashiri
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Brain Tumor Segmentation MRI Convolutional neural network Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/ad091872f0ce4516a5587472f42e8869
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ad091872f0ce4516a5587472f42e8869
record_format	dspace
spelling	oai:doaj.org-article:ad091872f0ce4516a5587472f42e88692021-11-28T12:26:24ZComparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation10.1186/s12911-021-01687-41472-6947https://doaj.org/article/ad091872f0ce4516a5587472f42e88692021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01687-4https://doaj.org/toc/1472-6947Abstract Introduction and goal to background Due to the importance of segmentation of MRI images in identifying brain tumors, various methods including deep learning have been introduced for automatic brain tumor segmentation. On the other hand, using a combination of methods can improve their performance. Among them is the use of wavelet transform as an auxiliary element in deep networks. The analysis of the requirements of such combinations has been addressed in this study. Method In this developmental study, different wavelet functions were used to compress brain MRI images and finally as an auxiliary element in improving the performance of the convolutional neural network in brain tumor segmentation. Results Based on the results of the tests performed, the Daubechies1 function was most effective in enhancing network performance in segmenting MRI images and was able to balance the performance and computational overload. Conclusion Choosing the wavelet function to optimize the performance of a convolutional neural network should be based on the requirements of the problem, also taking into account some considerations such as computational load, processing time, and performance of the wavelet function in optimizing CNN output in the intended task.Mohamadreza HajiabadiBehrouz Alizadeh SavarehHassan EmamiAzadeh BashiriBMCarticleBrainTumorSegmentationMRIConvolutional neural networkComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Brain Tumor Segmentation MRI Convolutional neural network Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Brain Tumor Segmentation MRI Convolutional neural network Computer applications to medicine. Medical informatics R858-859.7 Mohamadreza Hajiabadi Behrouz Alizadeh Savareh Hassan Emami Azadeh Bashiri Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation
description	Abstract Introduction and goal to background Due to the importance of segmentation of MRI images in identifying brain tumors, various methods including deep learning have been introduced for automatic brain tumor segmentation. On the other hand, using a combination of methods can improve their performance. Among them is the use of wavelet transform as an auxiliary element in deep networks. The analysis of the requirements of such combinations has been addressed in this study. Method In this developmental study, different wavelet functions were used to compress brain MRI images and finally as an auxiliary element in improving the performance of the convolutional neural network in brain tumor segmentation. Results Based on the results of the tests performed, the Daubechies1 function was most effective in enhancing network performance in segmenting MRI images and was able to balance the performance and computational overload. Conclusion Choosing the wavelet function to optimize the performance of a convolutional neural network should be based on the requirements of the problem, also taking into account some considerations such as computational load, processing time, and performance of the wavelet function in optimizing CNN output in the intended task.
format	article
author	Mohamadreza Hajiabadi Behrouz Alizadeh Savareh Hassan Emami Azadeh Bashiri
author_facet	Mohamadreza Hajiabadi Behrouz Alizadeh Savareh Hassan Emami Azadeh Bashiri
author_sort	Mohamadreza Hajiabadi
title	Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation
title_short	Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation
title_full	Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation
title_fullStr	Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation
title_full_unstemmed	Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation
title_sort	comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation
publisher	BMC
publishDate	2021
url	https://doaj.org/article/ad091872f0ce4516a5587472f42e8869
work_keys_str_mv	AT mohamadrezahajiabadi comparisonofwavelettransformationstoenhanceconvolutionalneuralnetworkperformanceinbraintumorsegmentation AT behrouzalizadehsavareh comparisonofwavelettransformationstoenhanceconvolutionalneuralnetworkperformanceinbraintumorsegmentation AT hassanemami comparisonofwavelettransformationstoenhanceconvolutionalneuralnetworkperformanceinbraintumorsegmentation AT azadehbashiri comparisonofwavelettransformationstoenhanceconvolutionalneuralnetworkperformanceinbraintumorsegmentation
_version_	1718407975605895168

Comparison of wavelet transformations to enhance convolutional neural network performance in brain tumor segmentation

Ejemplares similares