A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network
In this paper, we present a fully automatic brain tumor segmentation and classification model using a Deep Convolutional Neural Network that includes a multiscale approach. One of the differences of our proposal with respect to previous works is that input images are processed in three spatial scale...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/9/2/153 |
| id |
doaj-50cfbcebcbe843aabbaca4ca04ee4dbb |
|---|---|
| record_format |
Article |
| spelling |
doaj-50cfbcebcbe843aabbaca4ca04ee4dbb2021-02-03T00:06:01ZengMDPI AGHealthcare2227-90322021-02-01915315310.3390/healthcare9020153A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural NetworkFrancisco Javier Díaz-Pernas0Mario Martínez-Zarzuela1Míriam Antón-Rodríguez2David González-Ortega3Department of Signal Theory, Communications and Telematics Engineering, Telecommunications Engineering School, University of Valladolid, 47011 Valladolid, SpainDepartment of Signal Theory, Communications and Telematics Engineering, Telecommunications Engineering School, University of Valladolid, 47011 Valladolid, SpainDepartment of Signal Theory, Communications and Telematics Engineering, Telecommunications Engineering School, University of Valladolid, 47011 Valladolid, SpainDepartment of Signal Theory, Communications and Telematics Engineering, Telecommunications Engineering School, University of Valladolid, 47011 Valladolid, SpainIn this paper, we present a fully automatic brain tumor segmentation and classification model using a Deep Convolutional Neural Network that includes a multiscale approach. One of the differences of our proposal with respect to previous works is that input images are processed in three spatial scales along different processing pathways. This mechanism is inspired in the inherent operation of the Human Visual System. The proposed neural model can analyze MRI images containing three types of tumors: meningioma, glioma, and pituitary tumor, over sagittal, coronal, and axial views and does not need preprocessing of input images to remove skull or vertebral column parts in advance. The performance of our method on a publicly available MRI image dataset of 3064 slices from 233 patients is compared with previously classical machine learning and deep learning published methods. In the comparison, our method remarkably obtained a tumor classification accuracy of 0.973, higher than the other approaches using the same database.https://www.mdpi.com/2227-9032/9/2/153brain tumor classificationdeep learningconvolutional neural networkmultiscale processingdata augmentationMRI |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Francisco Javier Díaz-Pernas Mario Martínez-Zarzuela Míriam Antón-Rodríguez David González-Ortega |
| spellingShingle |
Francisco Javier Díaz-Pernas Mario Martínez-Zarzuela Míriam Antón-Rodríguez David González-Ortega A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network Healthcare brain tumor classification deep learning convolutional neural network multiscale processing data augmentation MRI |
| author_facet |
Francisco Javier Díaz-Pernas Mario Martínez-Zarzuela Míriam Antón-Rodríguez David González-Ortega |
| author_sort |
Francisco Javier Díaz-Pernas |
| title |
A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network |
| title_short |
A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network |
| title_full |
A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network |
| title_fullStr |
A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network |
| title_full_unstemmed |
A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network |
| title_sort |
deep learning approach for brain tumor classification and segmentation using a multiscale convolutional neural network |
| publisher |
MDPI AG |
| series |
Healthcare |
| issn |
2227-9032 |
| publishDate |
2021-02-01 |
| description |
In this paper, we present a fully automatic brain tumor segmentation and classification model using a Deep Convolutional Neural Network that includes a multiscale approach. One of the differences of our proposal with respect to previous works is that input images are processed in three spatial scales along different processing pathways. This mechanism is inspired in the inherent operation of the Human Visual System. The proposed neural model can analyze MRI images containing three types of tumors: meningioma, glioma, and pituitary tumor, over sagittal, coronal, and axial views and does not need preprocessing of input images to remove skull or vertebral column parts in advance. The performance of our method on a publicly available MRI image dataset of 3064 slices from 233 patients is compared with previously classical machine learning and deep learning published methods. In the comparison, our method remarkably obtained a tumor classification accuracy of 0.973, higher than the other approaches using the same database. |
| topic |
brain tumor classification deep learning convolutional neural network multiscale processing data augmentation MRI |
| url |
https://www.mdpi.com/2227-9032/9/2/153 |
| work_keys_str_mv |
AT franciscojavierdiazpernas adeeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork AT mariomartinezzarzuela adeeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork AT miriamantonrodriguez adeeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork AT davidgonzalezortega adeeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork AT franciscojavierdiazpernas deeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork AT mariomartinezzarzuela deeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork AT miriamantonrodriguez deeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork AT davidgonzalezortega deeplearningapproachforbraintumorclassificationandsegmentationusingamultiscaleconvolutionalneuralnetwork |
| _version_ |
1724290278742818816 |