Case study · 2024
Radiography Image Classification
A multi-class chest X-ray classifier paired with an interpretability dashboard for non-technical review.
- Discipline
- Machine learning · Computer vision
- Technology
- TensorFlow · Keras · MobileNetV2 · Streamlit · Grad-CAM
Overview
I trained a transfer-learning pipeline on approximately 17,000 chest X-ray images, then built a Streamlit interface that exposed both predictions and Grad-CAM attention regions.
System map
How the pieces connect
The challenge
What made the problem worth solving
Radiography datasets are difficult for two connected reasons: classes are not distributed evenly, and a model score alone does not show a reviewer why the network made its decision.
The approach
Turning the problem into an engineering plan
- 01
Used MobileNetV2 transfer learning to start from strong visual features instead of training an entire convolutional network from scratch.
- 02
Applied Focal Loss so difficult and underrepresented examples had more influence during training.
- 03
Added Grad-CAM overlays in a Streamlit dashboard to surface the image regions contributing to a prediction.
Result
The project became more than a model notebook: it was a reviewable ML system with a clear path from input image to prediction and visual explanation.