Enhanced Regularized Ensemble Encoderdecoder Network for Accurate Brain Tumor Segmentation.

Autoencoder Brain tumor Computer vision MRI. Medical imaging Segmentation

Journal

Current medical imaging
ISSN: 1573-4056
Titre abrégé: Curr Med Imaging
Pays: United Arab Emirates
ID NLM: 101762461

Informations de publication

Date de publication:
2024
Historique:
received: 04 09 2023
revised: 16 10 2023
accepted: 02 11 2023
medline: 23 2 2024
pubmed: 23 2 2024
entrez: 23 2 2024
Statut: ppublish

Résumé

Segmenting tumors in MRI scans is a difficult and time-consuming task for radiologists. This is because tumors come in different shapes, sizes, and textures, making them hard to identify visually. This study proposes a new method called the enhanced regularized ensemble encoder-decoder network (EREEDN) for more accurate brain tumor segmentation. The EREEDN model first preprocesses the MRI data by normalizing the intensity levels. It then uses a series of autoencoder networks to segment the tumor. These autoencoder networks are trained using back-propagation and gradient descent. To prevent overfitting, the EREEDN model also uses L2 regularization and dropout mechanisms. The EREEDN model was evaluated on the BraTS 2020 dataset. It achieved high performance on various metrics, including accuracy, sensitivity, specificity, and dice coefficient score. The EREEDN model outperformed other methods on the BraTS 2020 dataset. The EREEDN model is a promising new method for brain tumor segmentation. It is more accurate and efficient than previous methods. Future studies will focus on improving the performance of the EREEDN model on complex tumors.

Sections du résumé

BACKGROUND BACKGROUND
Segmenting tumors in MRI scans is a difficult and time-consuming task for radiologists. This is because tumors come in different shapes, sizes, and textures, making them hard to identify visually.
OBJECTIVE OBJECTIVE
This study proposes a new method called the enhanced regularized ensemble encoder-decoder network (EREEDN) for more accurate brain tumor segmentation.
METHODS METHODS
The EREEDN model first preprocesses the MRI data by normalizing the intensity levels. It then uses a series of autoencoder networks to segment the tumor. These autoencoder networks are trained using back-propagation and gradient descent. To prevent overfitting, the EREEDN model also uses L2 regularization and dropout mechanisms.
RESULTS RESULTS
The EREEDN model was evaluated on the BraTS 2020 dataset. It achieved high performance on various metrics, including accuracy, sensitivity, specificity, and dice coefficient score. The EREEDN model outperformed other methods on the BraTS 2020 dataset.
CONCLUSION CONCLUSIONS
The EREEDN model is a promising new method for brain tumor segmentation. It is more accurate and efficient than previous methods. Future studies will focus on improving the performance of the EREEDN model on complex tumors.

Identifiants

pubmed: 38389382
pii: CMIR-EPUB-138554
doi: 10.2174/0115734056275635231218114742
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

1-17

Subventions

Organisme : Deanship of Scientific Research, Najran University, Kingdom of Saudi Arabia
ID : NU/RG/MRC/12/10

Informations de copyright

Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.net.

Auteurs

Abdullah A Asiri (AA)

Department of Radiological Sciences, College of Applied Medical Sciences, Najran University, Najran 61441, Saudi Arabia.

Ahmad Shaf (A)

Department of Computer Science, COMSATS University Islamabad, Sahiwal Campus, Sahiwal 57000, Pakistan.

Tariq Ali (T)

Department of Computer Science, COMSATS University Islamabad, Sahiwal Campus, Sahiwal 57000, Pakistan.

Unza Shakeel (U)

Department of Computer Science, COMSATS University Islamabad, Sahiwal Campus, Sahiwal 57000, Pakistan.

Muhammad Irfan (M)

Department of Electrical Engineering, College of Engineering, Najran University, Najran 61441, Saudi Arabia.

Saeed Alqahtani (S)

Department of Radiological Sciences, College of Applied Medical Sciences, Najran University, Najran 61441, Saudi Arabia.

Khlood M Mehdar (KM)

Department of Anatomy, Medicine College, Najran University, Najran 61441, Saudi Arabia.

Hanan T Halawani (HT)

Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 61441, Saudi Arabia.

Ali H Alghamdi (AH)

Department of Radiological Sciences, Faculty of Applied Medical Sciences, The University of Tabuk, Tabuk, Saudi Arabia.

Abdullah Fahad A Alshamrani (AFA)

Department of Diagnostic Radiology Technology, College of Applied Medical Sciences, Taibah University, Madinah, Saudi Arabia.

Aisha M Mashraqi (AM)

Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran 61441, Saudi Arabia.

Classifications MeSH