Odontoid Fracture

Purpose

Detect odontoid fracture on cervical spine trauma radiographs

Tag(s)

 

Panel

Musculoskeletal

TOUCH-AI ID

TAI-05180006

Originator

Dan Chernoff

Panel Chair

Jay Patti

Panel Reviewers

Musculoskeletal Panel

License

Creative Commons 4.0

Status Public Commenting

Clinical Implementation


Value Proposition

Odontoid fracture is a potentially devastating injury that is often subtle and underreported on cervical spine radiographs by radiologists and emergency physicians. AI meeting this use case would help to reduce the false negative rate, patient risk, and medicolegal risk for physicians and facilities involved in the care of trauma patients.

Narrative(s)

A 25-year-old patient presents with head and neck trauma, and a cervical spine 3-view series (AP, lateral, and odontoid view) is taken in the emergency room. An algorithm evaluates the lateral and odontoid views and categorizes the odontoid process as intact or fractured. The physician is informed of this categorization at the time of interpretation.

Workflow Description

Images are obtained from the modality and sent to PACS and the AI engine. The images are analyzed by the engine. The system categorizes the odontoid as normal or fractured using a binary classifier. A message is sent to PACS from the engine with the classification information.

Considerations for Dataset Development


Procedures(s): X-ray, cervical spine

View(s): {Lateral, AP, Odontoid}

 

Sex at Birth: {Male, Female}

 

Age (years): older than 15

 

Developmental Anomalies:  {os odontoideum, unossified synchondrosis}

 

Other: Corticated margins

Technical Specifications


Inputs

DICOM Study

Procedure

XRAY, cervical spine

Views

Lateral, AP, Odontoid

Data Type

DICOM

Modality

XRAY

Body Region

Spine

Anatomic Focus

Spinal Cord

 

Primary Outputs

Odontoid Fracture

RadElement ID

RDE239

Definition

Define odontoid as intact or fractured

Data Type

Categorical

Value Set

0–Unknown

1–Fractured

2–Intact

Units

N/A

Public Commenting


Use cases are meant to be a primary vehicle for distributing clinical information to the developer community. They pinpoint precise scenarios within radiology workflows where potential automation could add noticeable value and establish standards for interpreting and passing corresponding common data elements. Implementing effective standards requires the perspective from all stakeholders. So to that end, we encourage your feedback on use cases.

To submit comments, please email DSIUseCases@acr.org with the use case title(s) and relevant comments by January 1, 2019. If more convenient, you may also download this use case and comment directly on the PDF. Just attach the PDF copy on the email.