Cancer-Cells-Detection-Tracking

Detecting and Tracking cancer (HeLa) cells using Computer Vision techniques. The project also detects cell division and analyses cell motion such as speed, distance travelled etc. The project uses OpenCV3 for image processing.

View on GitHub

Cancer-Cells-Detection-Tracking

Detecting and Tracking cancer (HeLa) cells using Computer Vision techniques. The project also detects cell division and analyses cell motion such as speed, distance travelled etc. The project uses OpenCV3 for image processing.

Requirements

The application is intended to be run using Python 3.7+.

Execution Instructions

Run main.py to launch the application. The parameters of the application are sequence_directory and mode. sequence_directory is the relative path to directory containing the sequence of images. The mode parameter chooses the preprocessing and segmentation methods to be used, which depends on the imageset.

Modes:

python3 main.py path/to/sequence mode 

Examples:

python3 main.py path/to/DIC/sequence 0 
python3 main.py path/to/Fluo/sequence 1 
python3 main.py path/to/PhC/sequence 2

During the run of the application, you can pause the animation at any time by pressing the ‘Pause’ button, and continue the animation by pressing the ‘Continue’ button. After all images in the sequence have been processed and displayed, you can reset and start again from the beginning by pressing the ‘Rerun’ button.

You can left-click on any segmented cell in the image at any time to show the metrics of that particular cell at the time it is clicked.

Features

The image data to be used in the group project is taken from the international Cell Tracking Challenge (CTC) and is provided as sequences of images (one sequence for each timelapse microscopy recording). The data set contains multiple sequences from different biological experiments. The developed methods should work on all these data.