Medical-CT-Segmentation-DeepLearning

The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.

End-to-end Python CT volume preprocessing pipeline to convert raw DICOMs into clean 3D numpy arrays for ML. From paper Draelos et al. "Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes."

Deep CNN for performing 3D super resolution on CT/MRI scans

Code for various probabilistic deep learning models

Adopted a convolutional neural network for COVID-19 testing. Examined the performance of different pre-trained models on CT testing and identified that larger, out-of-field datasets boost the testing power of the models.