Deep learning for segmentation of ischemic stroke lesions from MRI scans
Convolutional Neural Networks (CNN) such as U-Net have been extensively used for medical image segmentation tasks. However, CNNs have limitations in learning global feature representations in images due to their local receptive fields. This prompted researchers to look at other methods to improve...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/166455 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | Convolutional Neural Networks (CNN) such as U-Net have been extensively used for medical
image segmentation tasks. However, CNNs have limitations in learning global feature
representations in images due to their local receptive fields. This prompted researchers to
look at other methods to improve the modelling of global dependencies. In recent years,
transformer-like architectures with self-attention mechanisms for modelling long-range
dependencies have shown better performance than CNN-based architectures in computer
vision applications.
In this project, deep learning techniques involving transformer-like architectures were
explored for ischemic stroke lesion segmentation from Magnetic Resonance Imaging (MRI)
scans. Specifically, this study focused on using the hybrid CNN-Transformer network, UNet
Transformers (UNETR), to compare with pure CNN architectures. Furthermore, to address
the issue of transformers needing large amounts of labelled data to perform well, the
self-supervised learning method, Self-Distillation with No Labels (DINO), was utilised for
network pre-training. In order for the DINO approach to work on the 3D-based UNETR
architecture, we have modified the method to accept 3D images as input.
We demonstrated that with the pre-trained DINO weights, the ischemic stroke lesion
segmentation performance of UNETR improved when supervised learning was performed on
the Anatomical Tracings of Lesions After Stroke - Release 1.2 (ATLASR1.2) dataset. |
---|