Cargando…

Deep Learning Hybrid Techniques for Brain Tumor Segmentation

Medical images play an important role in medical diagnosis and treatment. Oncologists analyze images to determine the different characteristics of deadly diseases, plan the therapy, and observe the evolution of the disease. The objective of this paper is to propose a method for the detection of brai...

Descripción completa

Detalles Bibliográficos
Autores principales: Munir, Khushboo, Frezza, Fabrizio, Rizzi, Antonello
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9658353/
https://www.ncbi.nlm.nih.gov/pubmed/36365900
http://dx.doi.org/10.3390/s22218201
_version_ 1784829930155016192
author Munir, Khushboo
Frezza, Fabrizio
Rizzi, Antonello
author_facet Munir, Khushboo
Frezza, Fabrizio
Rizzi, Antonello
author_sort Munir, Khushboo
collection PubMed
description Medical images play an important role in medical diagnosis and treatment. Oncologists analyze images to determine the different characteristics of deadly diseases, plan the therapy, and observe the evolution of the disease. The objective of this paper is to propose a method for the detection of brain tumors. Brain tumors are identified from Magnetic Resonance (MR) images by performing suitable segmentation procedures. The latest technical literature concerning radiographic images of the brain shows that deep learning methods can be implemented to extract specific features of brain tumors, aiding clinical diagnosis. For this reason, most data scientists and AI researchers work on Machine Learning methods for designing automatic screening procedures. Indeed, an automated method would result in quicker segmentation findings, providing a robust output with respect to possible differences in data sources, mostly due to different procedures in data recording and storing, resulting in a more consistent identification of brain tumors. To improve the performance of the segmentation procedure, new architectures are proposed and tested in this paper. We propose deep neural networks for the detection of brain tumors, trained on the MRI scans of patients’ brains. The proposed architectures are based on convolutional neural networks and inception modules for brain tumor segmentation. A comparison of these proposed architectures with the baseline reference ones shows very interesting results. MI-Unet showed a performance increase in comparison to baseline Unet architecture by [Formula: see text] in dice score, [Formula: see text] insensitivity, and [Formula: see text] in specificity. Depth-wise separable MI-Unet showed a performance increase by [Formula: see text] in dice score, [Formula: see text] in sensitivity, and [Formula: see text] in specificity as compared to the baseline Unet architecture. Hybrid Unet architecture achieved performance improvement of [Formula: see text] in dice score, [Formula: see text] in sensitivity, and [Formula: see text] in specificity. Whereas the depth-wise separable hybrid Unet architecture outperformed the baseline architecture by [Formula: see text] in dice score, [Formula: see text] in sensitivity, and [Formula: see text] in specificity.
format Online
Article
Text
id pubmed-9658353
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96583532022-11-15 Deep Learning Hybrid Techniques for Brain Tumor Segmentation Munir, Khushboo Frezza, Fabrizio Rizzi, Antonello Sensors (Basel) Article Medical images play an important role in medical diagnosis and treatment. Oncologists analyze images to determine the different characteristics of deadly diseases, plan the therapy, and observe the evolution of the disease. The objective of this paper is to propose a method for the detection of brain tumors. Brain tumors are identified from Magnetic Resonance (MR) images by performing suitable segmentation procedures. The latest technical literature concerning radiographic images of the brain shows that deep learning methods can be implemented to extract specific features of brain tumors, aiding clinical diagnosis. For this reason, most data scientists and AI researchers work on Machine Learning methods for designing automatic screening procedures. Indeed, an automated method would result in quicker segmentation findings, providing a robust output with respect to possible differences in data sources, mostly due to different procedures in data recording and storing, resulting in a more consistent identification of brain tumors. To improve the performance of the segmentation procedure, new architectures are proposed and tested in this paper. We propose deep neural networks for the detection of brain tumors, trained on the MRI scans of patients’ brains. The proposed architectures are based on convolutional neural networks and inception modules for brain tumor segmentation. A comparison of these proposed architectures with the baseline reference ones shows very interesting results. MI-Unet showed a performance increase in comparison to baseline Unet architecture by [Formula: see text] in dice score, [Formula: see text] insensitivity, and [Formula: see text] in specificity. Depth-wise separable MI-Unet showed a performance increase by [Formula: see text] in dice score, [Formula: see text] in sensitivity, and [Formula: see text] in specificity as compared to the baseline Unet architecture. Hybrid Unet architecture achieved performance improvement of [Formula: see text] in dice score, [Formula: see text] in sensitivity, and [Formula: see text] in specificity. Whereas the depth-wise separable hybrid Unet architecture outperformed the baseline architecture by [Formula: see text] in dice score, [Formula: see text] in sensitivity, and [Formula: see text] in specificity. MDPI 2022-10-26 /pmc/articles/PMC9658353/ /pubmed/36365900 http://dx.doi.org/10.3390/s22218201 Text en © 2022 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
Munir, Khushboo
Frezza, Fabrizio
Rizzi, Antonello
Deep Learning Hybrid Techniques for Brain Tumor Segmentation
title Deep Learning Hybrid Techniques for Brain Tumor Segmentation
title_full Deep Learning Hybrid Techniques for Brain Tumor Segmentation
title_fullStr Deep Learning Hybrid Techniques for Brain Tumor Segmentation
title_full_unstemmed Deep Learning Hybrid Techniques for Brain Tumor Segmentation
title_short Deep Learning Hybrid Techniques for Brain Tumor Segmentation
title_sort deep learning hybrid techniques for brain tumor segmentation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9658353/
https://www.ncbi.nlm.nih.gov/pubmed/36365900
http://dx.doi.org/10.3390/s22218201
work_keys_str_mv AT munirkhushboo deeplearninghybridtechniquesforbraintumorsegmentation
AT frezzafabrizio deeplearninghybridtechniquesforbraintumorsegmentation
AT rizziantonello deeplearninghybridtechniquesforbraintumorsegmentation