/3D-Unet-for-Segmentation-of-Lung-lobes-in-CT-volumes

3D U-Net for Segmentation of Lung lobes in CT volumes - Keras/Tensorflow

Primary LanguageJupyter Notebook

3D-Unet Segmentation of Lung lobes in CT volumes

This project aims at predicting segmented images based on CT scans of Lungs (3d volumes).

I uploaded the .py files and a Google Colab notebook where I trained the 3d-Unet model on the free GPU.

Files:

  1. Data3D.py: Data Preprocessing

  2. 3D UNet.py: model design, training, testing and evaluation.

Dataset:

format = (slices x rows x columns)

scans = 51 .nrrd files of size 256x256x256.

masks = 51 .nrrd files of size 256x256x256.

Original size:

Patches of size 128x128x128:

Code:

  1. Importing files and data preprocessing
  2. Patch Extraction
  3. Model
  4. Training
  5. Cross validation
  6. Testing
  7. Loss and Loss Validation Plots
  8. Comparing predicted segmantation with scans and masks
  9. Future work for improving results

Keras/TensorFlow API