Brain Tumor Segmentation Tool

I have developed this Brain Tumor Segmentation (BTS) research tool under my industrial training project in collaboration with Manipal University. It is used to locate and identify brain tumors from MRI data. The segmentation techniques uses Deep Learning along with Fuzzy Logic techniques to produces the most accurate classifications and can distinguish among the four different types of tumor tissues. The accuracy of this tool was measured using Dice Coefficient and the results can be seen in the graph below.

Dice Similarity Coefficient for 50 randomly selected MRI images of brain as classified by BTS tool

Technologies Used

  • Computer Vision
  • Machine Learning (clustering)
  • Fuzzy Logic
  • Python
  • Unix Shell Scripting