LiTS Dataset: Preprocessed 256x256 Liver and Tumor Segmentation Images

Preprocessed 256x256 PNG images and masks for medical image segmentation tasks. The dataset is hosted on Kaggle, but the author, organization, and original source are unknown. The size, row count, and last update date are also unspecified.

Use Cases

• Training semantic segmentation models based on provided image-mask pairs.
• Benchmarking liver segmentation algorithms using preprocessed 256x256 images.
• Developing tumor detection and delineation tools for medical imaging.
• Pre-training models for other abdominal organ segmentation tasks.

Strengths

• Images are preprocessed to a consistent 256x256 resolution, which can simplify model input pipelines.
• The description explicitly states the data is formatted for medical image segmentation tasks.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

Kaggle

Collection Method

Preprocessed from an unspecified original source.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

null