Skip to content

Segmentation of the heart, lungs and trachea on CT of the chest.

Notifications You must be signed in to change notification settings

mandrakedrink/ChestCTSegmentation

Repository files navigation

CT Chest Segmentation


Motivation

Automatic segmentation of medical images is an important step to extract useful information that can help doctors make a diagnosis. Lung segmentation constitutes a critical procedure for any clinical-decision supporting system aimed to improve the early diagnosis and treatment of lung diseases.

Data

Available here or here. This dataset was be modified from Lung segmentation dataset by Kónya et al., 2020 , https://www.kaggle.com/sandorkonya/ct-lung-heart-trachea-segmentation The code with dataset creation available here - dataset_creation.ipynb

More information about dataset can be read here.

Formulation of the problem:

Each pixel must be labeled “1” if it is part of one of the classes (lungs, heart, trachea), and “0” if not.

Solution

The code with the solution is available here - ct_chest_seg.ipynb

Results

   


Video with several examples.

About

Segmentation of the heart, lungs and trachea on CT of the chest.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published