Chest X-Ray Images for Binary Anomaly Detection and CNN Training

A dataset of chest X-ray images processed for binary classification tasks (Normal vs. Anomaly). It was created by inGeniia for a Deep Learning course, teaching Convolutional Neural Networks and Transfer Learning with models like YOLO11 in classification mode. The dataset was last updated on December 8, 2025.

Use Cases

• Train binary classification models to distinguish normal from anomalous chest X-rays based on the described task.
• Teach Convolutional Neural Network (CNN) architectures using a focused medical imaging dataset.
• Demonstrate Transfer Learning techniques by fine-tuning pre-trained models like YOLO11 for classification.
• Apply data augmentation techniques to medical images to improve model generalization, as suggested by the description.

Strengths

• Designed for a specific pedagogical purpose in a Deep Learning course, providing a clear use case.
• Images have been processed with data augmentation techniques, as mentioned in the description.
• Last update timestamp (2025-12-08 20:01:22) is explicitly provided.

Limitations

• Description metadata is limited; actual data quality, size, and augmentation specifics require manual inspection after download.
• Row count, file formats, and column-level documentation are absent, which may limit suitability assessment.
• Data may reflect source and processing bias inherent to its original extraction from Kaggle and subsequent augmentation.

Provenance

Source

inGeniia

Collection Method

Images were originally extracted from Kaggle and processed with data augmentation techniques.

Freshness

Last updated 2025-12-08 20:01:22