DenseNet121 - Pediatric Pneumonia Detection
Model Description
This is a fine-tuned DenseNet121 model trained to classify chest X-rays into two categories: NORMAL and PNEUMONIA. It was developed as part of a precision diagnostics AI pipeline to assist clinical workflows.
To handle the severe class imbalance inherent in the dataset, dynamic class weights were applied to the PyTorch CrossEntropyLoss function, heavily penalizing false negatives to prioritize patient safety.
Intended Uses & Limitations
- Intended Use: As an auxiliary tool for clinical triage and radiologist workflow acceleration. It is designed to be paired with explainability tools (like Grad-CAM) to provide visual context.
- Limitations: This model is a research prototype and is not FDA-approved. It should not be used as a standalone diagnostic tool.
Training Data
Trained on the Kaggle Chest X-Ray Images (Pneumonia) dataset. All images were normalized and resized to 224x224. Light data augmentation (rotation and color jittering) was applied to the training set to prevent overfitting.
Evaluation Results
The model was evaluated on a completely unseen test dataset consisting of 624 images.
- Overall Accuracy: 86.4%
- Pneumonia Recall (Sensitivity): 94.6% (Successfully identified 369 out of 390 sick patients)
The high recall indicates the model heavily prioritizes catching pathology, treating false positives as an acceptable clinical trade-off requiring secondary physician review.