Main Content
| |
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 |
Related Datasets
No known related public datasets at this time, please us alert us if you know of any.
