RSNA Pulmonary Embolism Detection: Largest Public CT Scan Collection

RSNA assembled this dataset in 2020 for the RSNA STR Pulmonary Embolism Detection AI Challenge. It contains more than 12,000 CT pulmonary angiography (CTPA) studies contributed by five international research centers. Over 80 expert thoracic radiologists from the Society of Thoracic Radiology provided detailed clinical annotations.

Use Cases

• Train computer vision models for pulmonary embolism detection based on annotated CT scans.
• Benchmark AI algorithm performance for a specific medical imaging challenge.
• Study radiological features of pulmonary embolism based on expert-labeled clinical annotations.

Strengths

• More than 12,000 CT pulmonary angiography studies, described as the largest publicly available annotated PE dataset.
• Annotations provided by over 80 expert thoracic radiologists recruited in collaboration with the Society of Thoracic Radiology.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Radiological Society of North America (RSNA)

Collection Method

CTPA studies were contributed by five international research centers and labeled by expert radiologists for an AI challenge.

Time Range

Dataset assembled in 2020.

Freshness

Dataset was assembled in 2020; current update status is unknown.

Geography

Data contributed by five international research centers; specific countries are not listed.