Mini DDSM: Breast Cancer Mammography Images with Patient-Level Split

A Kaggle-hosted subset of the Digital Database for Screening Mammography (DDSM). The dataset appears to contain mammogram images related to breast cancer, split according to patient-level identifiers to prevent data leakage. The original DDSM is a widely used resource for developing computer-aided diagnosis systems.

Use Cases

• Train an image classifier to detect breast cancer lesions (inferred from domain, verify after download)
• Benchmark model performance using a patient-level data split to prevent overfitting (inferred from domain, verify after download)
• Develop segmentation models for mammogram anomaly detection (inferred from domain, verify after download)

Strengths

• Published on Kaggle, a major platform for data science and machine learning.
• Implements a patient-level data split, which is a critical practice for realistic medical ML evaluation.

Limitations

• Metadata is minimal; actual content requires verification after download.
• Row count, file formats, and column details are unknown, which may limit suitability assessment.
• License, author, and last update date are unknown.

Provenance

Source

Digital Database for Screening Mammography (DDSM)

Collection Method

Likely a curated subset or split of the original DDSM database.

Time Range

Temporal coverage of the original DDSM is unknown for this subset.

Freshness

Last updated date is unknown; freshness unverified.

Geography

Spatial coverage is unknown.