MATLAB source code for developing Ground Truth Dataset, Semantic Segmentation, and Evaluation for the Lumbar Spine MRI Dataset

Published: 3 April 2019| Version 2 | DOI: 10.17632/8cp2cp7km8.2
Contributors:
Sud Sudirman,
Ala Al Kafri,
friska natalia,
Hira Meidia,
Nunik Afriliana

Description

This file contains the MATLAB source code for developing Ground Truth Dataset, Semantic Segmentation, and Evaluation for Lumbar Spine MRI Dataset. It has the file structure necessary for the execution of the code. Please download the MRI Dataset, and the Label Image Ground Truth Data for Lumbar Spine MRI Dataset separately and unzip them inside the same installation folder. Links to their repository are provided in the Related Links section below. Please refer to instruction.docx file included in the package on how to install and use this source code. You can download and read the research papers detailing our methodology on boundary delineation for lumbar spinal stenosis detection using the URLs provided in the Related Links at the end of this page. You can also check out other dataset related to this program from that section. We kindly request you to cite our papers when using our data or program in your research.

Files

Steps to reproduce

Please follow the instructions set in instruction.docx. Dataset needed (see Related Links for download links) - MRI_Data - Manual_Label_Data - Ground_Truth_Data (optional) Additional programs and MATLAB library needed: - Matlab version 2018a or later - VGG16 (https://uk.mathworks.com/matlabcentral/fileexchange/61733-deep-learning-toolbox-model-for-vgg-16-network) - Cohen's Kappa (https://uk.mathworks.com/matlabcentral/fileexchange/15365-cohen-s-kappa) - Natural-Order Filename Sort (https://uk.mathworks.com/matlabcentral/fileexchange/47434-natural-order-filename-sort)