Repo for Tang et al, bioRxiv 454793 (2018)
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
1.1) Preprocessing - Reinhard Normalization and WSI Tiling.ipynb
1.2) Preprocessing - Plaque Detection and Image Cropping.ipynb
1.3) Preprocessing - Dataset Splitting and Size Filtering.ipynb
2.1) CNN Models - Model Training and Development.ipynb
2.2) CNN Models - Test Cases.ipynb
3) Visualization - Prediction Confidence Heatmaps.ipynb
4.1) Saliency Mapping - Feature Occlusion.ipynb
4.2) Saliency Mapping - Guided Grad-CAM.ipynb
5.1) Whole Slide Scoring - Tissue Area WSI Segmentation.ipynb
5.2) Whole Slide Scoring - Prediction Confidence Segmentation.ipynb
5.3) Whole Slide Scoring - CNN Score vs. CERAD-like Scores.ipynb
CNN_model_parameters.pkl
LICENSE.txt
README.md
normalize.py
vips_utils.py

README.md

Interpretable Classification of Alzheimer's Disease Pathologies with a Convolutional Neural Network Pipeline

bioRxiv 454793

DOI: https://doi.org/10.1101/454793

This repository accompanies the publication above. Specifically, we include notebooks to reproduce all image processing and processing, training of convolutional neural networks, confidence visualizations, and saliency maps.

Code requires:

python                    3.6.5                hc3d631a_2  
ipython                   6.4.0                    py36_0  
jupyter                   1.0.0                    py36_4  
matplotlib                2.2.2            py36h0e671d2_1  
numpy                     1.14.3           py36hcd700cb_1  
pandas                    0.23.0           py36h637b7d7_0  
scikit-learn              0.19.1           py36h7aa7ec6_0     
scikit-image              0.13.1           py36h14c3975_1    
scipy                     1.1.0            py36hfc37229_0  
pytorch                   0.4.0           py36_cuda8.0.61_cudnn7.1.2_1    pytorch   
torchvision               0.2.1                    py36_1    pytorch   
libopencv                 3.4.1                h1a3b859_1   
opencv                    3.4.1            py36h6fd60c2_2  
py-opencv                 3.4.1            py36h0676e08_1  
pyvips                    2.1.2                     <pip>
tqdm                      4.23.4                   py36_0