Ligamentum Teres Injury

Purpose

Ligamentum teres injury detection

Tag(s)

 

Panel

 Musculoskeletal

TOUCH-AI ID

 TAI-05180005

Originator

 Woojin Kim

Panel Chair

 Jay Patti

Panel Reviewers

 Musculoskeletal Panel

License

 Creative Commons 4.0

Status  Public Commenting

Clinical Implementation


Value Proposition

The ligamentum teres (LT) is an important stabilizer of the hip joint. An LT injury can be easily missed by radiologists despite it being one of the common causes of hip and groin pain, particularly in athletes. Radiologists would benefit from an algorithm that segments the LT and detects its abnormality. An AI algorithm meeting this use case would help to reduce the false negative rate, patient risk, and medical-legal risk for the radiologists.

Narrative(s)

A 25-year-old patient with a sudden twisting injury of the hip presents with severe hip pain. The initial radiographs of the hip were negative. Subsequently, an MRI of the hip was obtained. The AI algorithm evaluates the MR images, identifies the LT, and determines it as normal, abnormal, or indeterminate. The abnormal LT can be further subdivided into tendinopathy, partial tear, and full-thickness tear. The radiologist is informed of these findings at the time of interpretation.

Workflow Description

Images obtained from MRI or MR arthrography are sent to PACS/viewer and the AI model. The images are analyzed by the AI model. The model categorizes the LT as either normal, abnormal, or indeterminate. A message is sent to both the PACS/viewer and the reporting solution from the model with the classification information. If the type of injury (ie, tendinopathy, partial tear, full-thickness tear) is also identified, such information can also be sent to PACS/viewer and the reporting solution to highlight the region the engine identified.

Considerations for Dataset Development


Procedures(s): {MRI of the hip, MR arthrography of the hip, and MRI of the pelvis}

View(s): {MRI/A: coronal, axial, and sagittal}

 

Sex at Birth: {Male, Female}

 

Age (years): [0,90]

 

MRI Technique: MR arthrography will likely have the highest accuracy, followed by MRI of the hip, then MRI of the pelvis

 

Planes of Imaging: All three planes should be evaluated, though LT injuries are most often seen on coronal and axial images

Technical Specifications


Inputs

DICOM Study

Procedure

MRI/A, Hip; MRI, Pelvis

Views

Coronal, axial, sagittal

Data Type

DICOM

Modality

MRI/A

Body Region

Pelvis

Anatomic Focus

Hip

 

Primary Outputs

Ligamentum Teres Status

RadElement ID

RDE235

Definition

Status of the LT

Data Type

Categorical

Value Set

0–Unknown

1–Normal

2–Abnormal

Units

N/A

Secondary Outputs

Ligamentum Teres Abnormality Classification

RadElement ID

RDE236

Definition

If LT is abnormal, classify the injury

Data Type

Categorical

Value Set

0–Unknown

1–Tendinopathy

2–Partial tear

3–Full-thickness tear

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.