Landmark-free Assessment of Lower-limb Alignment with Implicit Neural Shape Functions from Knee Radiographs
Researchers have developed a new method for assessing lower-limb alignment from knee radiographs using Implicit Neural Shape Functions (INSF). This approach avoids the need for explicit anatomical landmark identification, instead encoding anatomical shapes into a latent space to directly predict alignment measurements. The INSF method was trained on a dataset of 566 knee radiographs and evaluated on both internal and external datasets, showing performance comparable to existing landmark-based techniques. AI