Imaginea 2020 Inifnity Idea
Medical image processing and modeling:
- Segmentation
- Regression
- Classification
- Generation/Reconstruction
- Representation learning
- https://niftynet.io/
- https://itk.org/
- https://vtk.org/
- https://www.kaggle.com/schlerp/getting-to-know-dicom-and-the-data/data
- Dicom
- https://www.kaggle.com/schlerp/getting-to-know-dicom-and-the-data/data
- Nii
- http://paulbourke.net/dataformats/nii/
-
Realated to Lung
- http://networkrepository.com/lung-cancer.php
- https://archive.ics.uci.edu/ml/datasets/Lung+Cancer
- https://lndb.grand-challenge.org/Home/
- http://biogps.org/dataset/tag/lung%20cancer/
- https://www.cancerimagingarchive.net/ Needs to raise request for the dataset with a reason
-
Breast Cancer
-
Eye
- https://www.kaggle.com/paultimothymooney/kermany2018 5GB JPEG image classification
- https://www.kaggle.com/benjaminwarner/resized-2015-2019-blindness-detection-images 17GB image classification Base dataset
-
Chest
- https://www.kaggle.com/c/rsna-pneumonia-detection-challenge 4GB Dicom possible 2nd dataset
-
Covulutional Network References
-
UNet
-
Image PRocessing Pipelines:
-
UNet
-
Data loading
- Load 3D images from different image formats
- Anistropic voxels and special spatial information and patient information
-
Data prepration as test/test/validation
-
Image data loading and sampling
-
Data augmentation
-
DL Model Architecture
-
DL framewok
-
Metrics to evaluate
-
Prediction
- AWS
- S3
- EMR
- Apache Spark
- MLFLOW
- Tensorflow
- Kubernets (?)