Skip to content

Latest commit

 

History

History
93 lines (64 loc) · 4.41 KB

README.md

File metadata and controls

93 lines (64 loc) · 4.41 KB

InCCsight

InCCsight is an open-source desktop software that enables processing, exploration, and visualization of Diffusion Tensor Imaging (DTI) data for analysis of the Corpus Callosum (CC). The software is portable and interactive, offering advanced features for CC analysis in DTI, both at an individual and group level. It incorporates three different segmentation techniques and five parcelation techniques, allowing for comparison of data generated by different methods.

One of the notable features of InCCsight is its Volumetric Segmentation method based on Convolutional Neural Networks (CNN), providing an advanced and effective approach for CC segmentation. Additionally, the software provides the ability to visualize the Corpus Callosum in 3D, adding a visual dimension to the analysis process.

As an open-source solution, InCCsight is an accessible tool for the scientific and research community, promoting collaboration and advancement of knowledge in the field of DTI analysis of the Corpus Callosum. With its user-friendly interface and advanced features, InCCsight is a powerful choice for DTI data analysis related to the Corpus Callosum.

Considerations

This software was developed through the MICLab, check out our Github!

Article: The article that explains the development and operation of the tool was published by Computer & Graphics. You can check out this article here. In case of using the software, please cite this article:

Caldeira, Thais, et al. "inCCsight: A software for exploration and visualization of DT-MRI data of the Corpus Callosum." Computers & Graphics 99 (2021): 259-271.

For an overview of the tool, we have a video showing the process and use: InCCsight

Installing

  • É necessário ter instalado o NPM ou o YARN no computador *

From Source

To install the tool directly from the source (Github) and have access to the codes:

  1. In the terminal, type git clone https://github.com/MICLab-Unicamp/inCCsight
  2. Walk to the location where the download was performed and execute the command: npm install
  3. Walk using "cd methods" and use python -m venv venv -> pip install -r requirements.txt in each method (This install all libraries necessary for use the methods) (Obs: Soon this step will be automated)
  4. Types of Use:
    1. User: Use the yarn electron:build command. This will turn the tool into a Windows, Linux and Mac executable.
    2. Developer: use the yarn electron:serve command. This will launch the tool as a developer, allowing you to make changes to the code and preview them in real time.

After installation, the first time you open the tool it may take a while to start as the anti-virus will check the security.

Use

How create a new method

To create a new method within the Software, the user must:

  • Have a folder with the name of the method.

  • A "main.py" file inside the folder.

  • The "main.py" file must have the following code to read the data:

      import argparse
  import glob
  import os
  import your_segmentation_method

  parser = argparse.ArgumentParser()
  parser.add_argument('-p', '--parent', nargs='*', dest='parents')

  args = parser.parse_args()
      
  # Read files
  folder_mri = args.parents

  all_subjects = []

  for folder in folder_mri:
      subjects = glob.glob(os.path.join(folder, "*"))

      for subject in subjects:
          all_subjects.append(subject)

  your_segmentation_method.segment(all_subject)

  • Your method must receive a list with the path of each subject to be processed.

  • For the data to be displayed in the graphics and tables of the interface, the code must generate a CSV file in the "../methods/csv" folder

Example

Contribuição

Contact

License

Warnings

No Linux, em package.json, adicionar os scripts: "start": "react-scripts --openssl-legacy-provider start", "build": "react-scripts --openssl-legacy-provider build"

No Windows: "start": "react-scripts start", "build": "react-scripts build"

Issues

  • Fix responsiveness of Screen
  • Check the functioning of the quality control
  • Test on MAC
  • Create a branch for dev and for final user