A CNN trained on 5,863 chest X-ray images achieves 92.6% accuracy — matching the diagnostic performance of trained radiologists.
Five stages transform a raw chest X-ray into an accurate clinical prediction in under one second.
5,863 labeled chest X-rays from Kaggle — Normal & Pneumonia classes
Resize to 150×150, normalize pixels, apply augmentation
4 convolutional blocks learn to extract pneumonia-specific features
Accuracy, recall, F1-score, AUC-ROC on held-out test set
Upload any chest X-ray — get Normal or Pneumonia + confidence score
Real-time animation of how signals propagate through the neural network. Each circle is a neuron — brighter means more active.
Upload a chest X-ray image or select a sample to see the CNN prediction pipeline in action.
JPG, PNG, BMP — any size
Click or drag & drop
Or try a sample case:
Tested on 624 held-out images never seen during training. Recall is the most critical metric — it measures how many pneumonia cases are caught.
| Predicted Normal | Predicted Pneumonia | |
|---|---|---|
| Actual Normal | TN = 210 Correctly identified | FP = 24 False alarm |
| Actual Pneumonia | FN = 22 Missed — critical! | TP = 368 Correctly caught |
Only 22 pneumonia cases were missed. The model prioritises high recall to minimise missed diagnoses.
Four convolutional blocks extract progressively abstract features, followed by a fully connected classifier head outputting a single sigmoid probability.
B.Tech Mini Project — Department of Artificial Intelligence and Data Science · 2024–25
Kaggle Chest X-Ray Images (Pneumonia) — Paul Mooney · Kermany et al. (2018), Cell 172(5) · TensorFlow 2.x Documentation · Rajpurkar et al. CheXNet (2017) · WHO Pneumonia Statistics 2022