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	Creative Commons 4.0
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.