CT Scans For Abdominal And Lung Foundation Model Training

10,000+ CT scans are provided for foundation model pretraining. The dataset supports downstream tasks including abdominal disease classification, abdominal lesion segmentation, abdominal organ segmentation, and lung lesion segmentation. It was created by FLARE-MedFM for the MICCAI FLARE25 challenge.

Use Cases

• Pretrain a 3D vision transformer on 10,000+ CT scans for transfer learning to medical imaging tasks
• Fine-tune models for multi-label abdominal disease classification using the provided task labels
• Develop segmentation models for abdominal organs using the abdominal organ segmentation task data
• Train lesion detection models for both abdominal and lung regions using the segmentation task annotations

Strengths

• Contains over 10,000 CT scans for model pretraining
• Designed for multiple specific downstream tasks including classification and segmentation
• Official dataset for the MICCAI FLARE25 challenge Task 4

Limitations

• Specific column structure, sample data, and file formats are not described in the provided input
• Dataset size and exact row count beyond '10,000+' are unknown
• Potential class imbalance or label noise is not detailed

Provenance

Source

FLARE-MedFM for the MICCAI FLARE25 challenge

Collection Method

Official dataset for CT image foundation model development

Time Range

null

Freshness

Last updated July 3, -2025.

Geography

null