Skip to content

asharma8602/Brain-Image-Segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation


Brain Segmentation

Getting Started

To get a local copy up and running follow these simple steps.

Prerequisites

The requirements.txt must be installed if you run on a local system; otherwise, installing libraries is not required if you run on Google Collab.

Installation

  1. Clone the project

    git clone https://github.com/asharma8602/Brain-Image-Segmentation
  2. Before running the Python Notebook on your local system.

    pip install -r requirements.txt

Directory Structure

├───Train_Images
└───Train_Labels
    ├───Contours
    ├───Distance_Maps
    └───Masks

Model Details

Data-set

Indian Brain Segmentation Dataset (IBSD) consists of high-quality 1.5T T1w MRI data of 114 subjects generated under fixed imaging protocol along with corresponding manual annotation data of 14 sub-cortical structures done by expert radiologists. The number of MR scans in the dataset consists of an approximately equal number of male and female subjects belonging to a young age group (20-30 years). This data has been used to create a template for the young Indian population.

Data Preprocessing

  1. Reading MRI data of 113 subjects in the form of NiFti Images.

  2. Combining 14 labels to establish a binary classification Psi-net.

  3. Saving 192 slices per subject to adjust the data corresponding to Psi-net architecture.

  4. Conversion of labels to Binary Masks which further being converted to Contours and finally obtaining Distance Maps for them.

Data Loader

A custom data-loader function is designed with following functions.

  1. loadimage - Loading input image
  2. loadmask - Loading mask of corresponding label
  3. loadcont - Loading contour of corresponding label
  4. loaddist - Loading distance map of corresponding label

Citations

@article{Murugesan2019PsiNetSA,
  title={Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation},
  author={Balamurali Murugesan and Kaushik Sarveswaran and Sharath M. Shankaranarayana and Keerthi Ram and Mohanasankar Sivaprakasam},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.04099}
Jayanthi Sivaswamy, Alphin J Thottupattu, Mythri V, Raghav Mehta, R Sheelakumari, & Chandrasekharan Kesavadas. (2021, November 8). 
Indian Brain Segmentation Dataset(IBSD). 
Zenodo. https://doi.org/10.5281/zenodo.5656776

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages