## Welcome to the Pneumonia Classification and Localization Challenge!

Pneumonia is a leading cause of death worldwide and a major diagnostic challenge in clinical practice. Symptoms like cough, fever, and shortness of breath overlap with other conditions, making accurate and timely diagnosis difficult. Delays can lead to worsened outcomes and overuse of broad-spectrum antibiotics.

This competition focuses on building AI tools to assist in early, non-invasive pneumonia diagnosis using chest X-ray images. By automating classification and localization, these tools can reduce radiologists’ workload and improve access to high-quality diagnostics, particularly in resource-limited settings.

## The Challenge
Your goal is to develop a model that can:
1. Classify chest X-rays as showing pneumonia or not.
2. Localize the pneumonia when present using bounding boxes.

Participants will train and evaluate their models on real clinical data from two distinct sources, each with its own format and labeling strategy.

The final evaluation will consider both classification performance (e.g., AUC) and localization accuracy (e.g., Intersection over Union, or IoU), reflecting real-world diagnostic needs.