Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Deep Learning Enabled Segmentation of Brain Tissue in MRI
This project aims to create deep learning based image segmentation algorithm for high-field mouse MRI data for advanced neuroimaging applications.
Keywords: image segmentation, biomedical imaging, magnetic resonance imaging
We acquire high-field mouse MRI data for advanced neuroimaging applications. As part of the analysis of such data, relevant brain tissue needs to be selected via a mask. For this process to be performed automatically, brain voxels need to be classified based on their signal intensity and position in the image. Nowadays, deep neural networks are the state-of-the-art methods for segmentation tasks in medical imaging field. In this project, we aim to create a deep learning enabled framework for segmentation of brain tissue in functional and structural MR images.
We acquire high-field mouse MRI data for advanced neuroimaging applications. As part of the analysis of such data, relevant brain tissue needs to be selected via a mask. For this process to be performed automatically, brain voxels need to be classified based on their signal intensity and position in the image. Nowadays, deep neural networks are the state-of-the-art methods for segmentation tasks in medical imaging field. In this project, we aim to create a deep learning enabled framework for segmentation of brain tissue in functional and structural MR images.
In this project, the student is expected to improve the performance of already implemented image segmentation architecture U-Net [1]. In addition, the student is expected to work independently and come up with better segmentation methods for this specific task.
[1] Olaf Ronneberger, Philipp Fischer, Thomas Brox, “U-Net: Convolutional Networks for
Biomedical Image Segmentation”, Medical Image Computing and Computer-Assisted
Intervention (MICCAI), Springer, 2015.
In this project, the student is expected to improve the performance of already implemented image segmentation architecture U-Net [1]. In addition, the student is expected to work independently and come up with better segmentation methods for this specific task.
[1] Olaf Ronneberger, Philipp Fischer, Thomas Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation”, Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, 2015.