Trauma Fracture Detection
| Purpose | Detect all fractures on CT chest, abdomen, and pelvis performed for trauma |
| Tag(s) |
|
| Panel | Musculoskeletal |
| Define-AI ID | 18050017 |
| Originator | Dan Chernoff |
| Panel Chair | Jay Patti |
| Panel Reviewers | Musculoskeletal Panel |
| License | |
| Status | Public Commenting |
Clinical Implementation
Value Proposition
Many fractures, some of which are obvious in retrospect, are missed on trauma CT.Narrative(s)
A 25-year-old patient presents with blunt-force trauma from a fall off of a ladder. CT of the chest, abdomen, and pelvis is performed to determine if internal bleeding or organ injury is present. Fracture detection is generally less critical to immediate care of the patient and can be overlooked.Workflow Description
The CT thin slice data set is preprocessed for bone segmentation and sent to the AI engine, which identifies likely fractures (unknown number) and marks these for extra scrutiny by the radiologist (analogous to computer-aided detection marks in mammography).Considerations for Dataset Development
Procedures(s): {CT, Chest/Abdomen/Pelvis}
View(s): {AP, PA/Lat, inclination e.g., upright, semi-upright, supine}
Sex at Birth: {Male, Female}
Age: preference for skeletally mature
Anatomy Altering Conditions: {Diabetes, Charcot Joint}
Position: {weight bearing, non-weight bearing}
Technical Specifications
Inputs
DICOM Study
| Procedure | CT, Chest/Abdomen/Pelvis |
| Views | AP, PA/Lat, inclination e.g., upright, semi-upright, supine |
| Data Type | DICOM |
| Modality | CT |
| Body Region | Chest, Abdomen, or Pelvis |
Primary Outputs
Fracture Detection
| RadElement ID | RDE263 |
| Definition | Detect the presence of a fracture |
| Data Type | Categorical |
| Value Set | 0-Unknown 1-Fracture 2-No Fracture |
| Units | N/A |
Related Datasets
No known related public datasets at this time, please us alert us if you know of any.