MAPSMR: Multi-Organ Post-Surgical MRI Benchmark Dataset

A multi-organ, post-surgical MRI benchmark dataset focused on organ absence and altered anatomy after common abdominal and pelvic surgeries. The dataset includes cases such as cholecystectomy, prostatectomy, nephrectomy, colectomy, and hepatectomy, with annotations identifying surgically absent organs and post-treatment anatomical changes. It is hosted on AWS Open Data and provided by GE Healthcare under a CC-BY-NC-ND-4.0 license.

Use Cases

• Train segmentation models to identify surgically absent organs based on the annotation labels.
• Develop anomaly detection algorithms for recognizing post-treatment anatomical changes mentioned in the description.
• Benchmark image classification models on multi-organ, post-surgical MRI data.
• Study the anatomical variability introduced by common abdominal and pelvic surgical procedures.

Strengths

• Focuses on a specific and clinically relevant scenario: post-surgical anatomy with organ absence.
• Includes annotations for surgically absent organs and anatomical changes, which are valuable for supervised learning.
• Covers multiple common surgical procedures (e.g., cholecystectomy, prostatectomy, nephrectomy).

Limitations

• Row count and dataset size are unknown, which may limit suitability assessment for large-scale model training.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

GE Healthcare

Collection Method

Likely collected from clinical imaging studies, but the specific gathering method is not detailed.

Time Range

null

Freshness

Last updated date is unknown.

Geography

null