SEGMENTATION OF PROSTATE T2 WEIGHTED MAGNETIC RESONANCE IMAGING USING ENCODER-DECODER CONVOLUTIONAL NEURAL NETWORKS
Segmentation of prostate in T2 weighted (T2W) magnetic resonance imaging (MRI) images is an important step in the automatic diagnosis of prostate cancer to enable better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | http://utpedia.utp.edu.my/20517/1/Zia%20Ullah%20Khan_17004635.pdf http://utpedia.utp.edu.my/20517/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Segmentation of prostate in T2 weighted (T2W) magnetic resonance imaging (MRI) images is an important step in the automatic diagnosis of prostate cancer to enable
better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation of the prostate gland in MRI
images. The main challenges of prostate gland segmentation are blurry prostate boundary and variability in prostate anatomical structure. This work is a framework of four encoder-decoder convolutional neural networks (CNNs) in the prostate gland segmentation in the T2W MRI image. The four selected CNNs are FCN, SegNet,
U-Net, and DeepLabV3+, which are initially proposed for the segmentation of road scenes, biomedical, and natural images. |
|---|