Multiple-Organ-Segmentation

Prayushi Mathur

Prayushi Mathur

Kota, Rajasthan

0 0
  • 0 Collaborators

This project is about Biomedical Organ Segmentation on multiple organs using V-net model. Each of the 13 organs were segmented using different colours. It can help doctors to address the challenging task of detecting the type and location of the organ in the human body. ...learn more

Project status: Concept

Artificial Intelligence

Intel Technologies
DevCloud

Code Samples [1]

Overview / Usage

The process of Multiple Organ Segmentation is the process of separating multiple organs by specifying their boundary from other organ tissues. In the technical terms, this process gives the pixel-wise identification of the type of organ present in the MRI/CT images. This further can help the doctor to detect the type and location of the organ in the human body which is challenging task due to irregular form and confusing boundaries of multiple organs. The results include the following information:

  • Loss
  • Dice-coefficient

Methodology / Approach

The base model used here was V-net.

  • It is a three dimensional model.
  • The model can segment the following organs in a CT/MRI scan: (1) spleen (2) right kidney (3) left kidney (4) gallbladder (5) esophagus (6) liver (7) stomach (8) aorta (9) inferior vena cava (10) portal vein and splenic vein (11) pancreas (12) right adrenal gland (13) left adrenal gland
  • It contains residual connections along with skip connections.
  • Input contains 1-channels
  • Output contains 13 channels containing the above mentioned organs.

Technologies Used

We have used Intel Dev Cloud with OpenVINO, Python, OpenCV and Tensorflow.

Repository

https://github.com/Prayushi9/Multi-Organ-Segmentation

Comments (0)