KidneyStoneTR-Seg: Kidney Segmentation Masks for Abdominal CT Images

2.1 GB of abdominal CT images paired with pixel-wise kidney segmentation masks, organized into cross-validation and holdout subsets. The dataset was created by COŞKU ÖKSÜZ and last updated in June 2026. It is supported by The Scientific and Technological Research Council of Türkiye (TÜBİTAK) under Grant No. 123E442.

Use Cases

• Train automated kidney segmentation models based on the provided pixel-wise kidney masks.
• Benchmark segmentation algorithms based on the patient-level cross-validation folds.
• Develop segmentation-based preprocessing pipelines for kidney-related computer-aided diagnosis systems.
• Evaluate lightweight and efficient medical image segmentation models based on the independent holdout set.

Strengths

• Includes patient-level separation between training and testing subsets for fair model evaluation.
• Provides a structured cross-validation setup with five folds and an independent holdout set.
• Contains original CT images and corresponding binary segmentation masks.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last updated 2026-06-03 09:21:25; freshness should be verified.

Provenance

Source

COŞKU ÖKSÜZ via figshare.

Collection Method

Likely derived from the KidneyStoneTR abdominal CT dataset, with added segmentation masks.

Freshness

Last updated 2026-06-03 09:21:25.