Ultrasound (US) is a more cost-effective, accessible, and available imaging technique to assess anterior talofibular ligament (ATFL) injuries compared with magnetic resonance imaging (MRI). However, challenges in using this technique and increasing demand on qualified musculoskeletal (MSK) radiologists delay the diagnosis. Using datasets from multiple clinical centers, the investigators aimed to develop and validate a deep convolutional network (DCNN) model that automates classification of ATFL injuries using US images with the goal of providing interpretable assistance to radiologists and facilitating a more accurate diagnosis of ATFL injuries.

The investigators collected US images of ATFL injuries which had arthroscopic surgery results as reference standard form 13 hospitals across China;Then the investigators divided the images into training dataset, internal validation dataset, and external validation dataset in a ratio of 8:1:1; the investigators chose an optimal DCNN model to test its diagnostic performance of the model, including the diagnostic accuracy, sensitivity, specificity, F1 score. At last, the investigators compared the diagnostic performance of the model with 12 radiologists at different levels of expertise.

Inclusion Criteria:

• age > 18 years old
• patients who had experienced an first-episode, acute ankle sprain and received US examination within 14 days post injury
• patients who had a corresponding arthroscopic surgery result for classification of the ATFL injury.

Exclusion Criteria:

• patients who had a previous history of ankle open trauma or ankle joint surgery
• there were any soft-tissue or bone tumors in the ankle
• there was concurrent with any other rheumatoid arthritis
• the image quality was low or there were severe artifacts (eg, anisotropic artifacts)

As mentioned above