shahin-imtiaz / Instance-Segmentation-using-UNet-and-Dice-Similarity-Coefficient

Deep learning model for identifying cell nuclei from histology images using UNet.

Instance-Segmentation-using-UNet-and-Dice-Similarity-Coefficient

Develop a deep learning model for identifying cell nuclei from histology images. The model should have the ability to generalize across a variety of lighting conditions,cell types, magnifications etc. The generated mask should have the same size as that of the corresponding raw image.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

1. Python (used 3.6.6)
2. Numpy
3. Tensorflow
4. Keras
5. Skimage
6. Scipy
7. Sklearn
8. Pickle

Dataset

The data can be downloaded from Kaggle [Dataset]: https://www.kaggle.com/c/data-science-bowl-2018/data

Installation

1. Run pip install -r requirements.txt requirements.txt file can be found in Other Folder
2. Update the path PATH, TEST_PATH, OUTPUT_PATH in the ipynb
3. Run the ipynb notebook
4. Output will be saved in the OUTPUT_PATH

Built With

1. Jupyter Notebook