You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Single-file PyTorch pipeline for pathogen class prediction on MIMIC-III/IV EHR data. Hybrid Conv1D+BiLSTM+numeric model, streaming CSV ETL without pandas, ECE calibration, ROC/PR-AUC, and subgroup bias checks. Research and education only.
A deep learning project to classify Pneumonia vs Normal from chest X-ray images using CNNs. Based on the "Chest X-Ray Images (Pneumonia)" dataset from Kaggle with structured train/val/test splits and two class labels. Built for fast prototyping and clean deployment.
This project utilizes (CNN) to accurately classify X-Ray images for pneumonia detection. It explores three different approaches to handle data imbalance and achieve optimal model performance. The project includes detailed evaluation metrics and use Streamlit which enables a seamless classification.
Binary classification of chest X-rays (Pneumonia vs Normal) using CNN and hand-crafted features (PHOG, Gabor, Fourier, DCT). Includes a web App for real-time prediction