TY - JOUR
T1 - UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation
AU - Pravitasari, Anindya Apriliyanti
AU - Iriawan, Nur
AU - Almuhayar, Mawanda
AU - Azmi, Taufik
AU - Irhamah,
AU - Fithriasari, Kartika
AU - Purnami, Santi Wulan
AU - Ferriastuti, Widiana
N1 - Publisher Copyright:
© 2019 Universitas Ahmad Dahlan.
PY - 2020
Y1 - 2020
N2 - A brain tumor is one of a deadly disease that needs high accuracy in its medical surgery. Brain tumor detection can be done through magnetic resonance imaging (MRI). Image segmentation for the MRI brain tumor aims to separate the tumor area (as the region of interest or ROI) with a healthy brain and provide a clear boundary of the tumor. This study classifies the ROI and non-ROI using fully convolutional network with new architecture, namely UNet-VGG16. This model or architecture is a hybrid of U-Net and VGG16 with transfer Learning to simplify the U-Net architecture. This method has a high accuracy of about 96.1% in the learning dataset. The validation is done by calculating the correct classification ratio (CCR) to comparing the segmentation result with the ground truth. The CCR value shows that this UNet-VGG16 could recognize the brain tumor area with a mean of CCR value is about 95.69%.
AB - A brain tumor is one of a deadly disease that needs high accuracy in its medical surgery. Brain tumor detection can be done through magnetic resonance imaging (MRI). Image segmentation for the MRI brain tumor aims to separate the tumor area (as the region of interest or ROI) with a healthy brain and provide a clear boundary of the tumor. This study classifies the ROI and non-ROI using fully convolutional network with new architecture, namely UNet-VGG16. This model or architecture is a hybrid of U-Net and VGG16 with transfer Learning to simplify the U-Net architecture. This method has a high accuracy of about 96.1% in the learning dataset. The validation is done by calculating the correct classification ratio (CCR) to comparing the segmentation result with the ground truth. The CCR value shows that this UNet-VGG16 could recognize the brain tumor area with a mean of CCR value is about 95.69%.
KW - Fully convolution network
KW - Image segmentation
KW - Transfer learning
KW - U-Net
KW - VGG16
UR - http://www.scopus.com/inward/record.url?scp=85084261706&partnerID=8YFLogxK
U2 - 10.12928/TELKOMNIKA.v18i3.14753
DO - 10.12928/TELKOMNIKA.v18i3.14753
M3 - Article
AN - SCOPUS:85084261706
SN - 1693-6930
VL - 18
SP - 1310
EP - 1318
JO - Telkomnika (Telecommunication Computing Electronics and Control)
JF - Telkomnika (Telecommunication Computing Electronics and Control)
IS - 3
ER -