↓ Skip to main content
Hakan Ates

Lung Disease Prediction from Chest X-rays (Xception)

·273 words·2 mins
Coursework Python TensorFlow Keras Xception Transfer Learning
Hakan Ates
Author
Hakan Ates
I build full-stack applications and LLM-powered tools.
Table of Contents
Course project for Human Data Analytics (University of Padua): an Xception classifier for lung disease in chest X-ray images, plus an ablation that measures what ImageNet pretraining is worth on a small medical dataset.

Highlights
#

  • Fine-tuned an ImageNet-pretrained Xception in TensorFlow/Keras to classify lung disease from 4,575 chest X-ray images, reaching 94.53% accuracy with 0.945 F1.
  • Quantified the value of transfer learning by training the identical architecture from scratch, which reached only 85.56% accuracy, 9 points below the pretrained model.
  • Published the full experiment as a public Kaggle notebook.

How it works
#

flowchart TD
    A["Chest X-ray dataset
4,575 images, balanced classes"] --> B["Preprocessing & cleaning"]
    B --> C["Xception
ImageNet weights"]
    C --> D["Fine-tuning"]
    D --> E["Evaluation
94.53% acc, F1 0.945"]
    B --> F["Xception
from scratch"]
    F --> G["85.56% accuracy"]

Case Study
#

Problem. The task is computer-aided classification of lung disease from chest X-ray images. Labeled medical imaging data is scarce; with only 4,575 labeled images, the question is how much of the final accuracy comes from ImageNet pretraining rather than from the X-rays themselves.

Approach. The project used the Xception architecture in TensorFlow/Keras. The central methodological choice was a clean ablation: train the exact same network twice, once from random initialization and once from ImageNet weights with fine-tuning, so the accuracy difference is attributable to pretraining. Before training, the dataset needed preprocessing and cleaning to deal with issues such as missing metadata.

Outcome. The fine-tuned model reached 94.53% accuracy, with precision 0.949, recall 0.945 and F1 0.945. The from-scratch model stopped at 85.56%, a 9-point gap.

Links. Project report (PDF, Google Drive) · Kaggle notebook: lung-disease-prediction-from-chest-x-ray-xception

Stack
#

Python, TensorFlow, Keras, Xception, Kaggle Notebooks