Deep Learning-Based Automated Anatomical Landmark Detection and Saw Blade Size Prediction for Canine Tibial Plateau...

To develop and validate a fully automated deep learning workflow that localizes key anatomical landmarks on standard canine hindlimb lateral radiographs, derives the tibial plateau angle (TPA), and recommends a saw blade size for tibial plateau leveling osteotomy (TPLO) preoperative planning.

Retrospective validation study.

Two hundred annotated lateral radiographs obtained from 130 dogs representing 14 breeds, with body weights ranging from 2.4 to 38.0 kg.

A customized four-stage U-Net was trained using three complementary grayscale representations (normalized, contrast-enhanced, and gamma-adjusted images) to detect five TPLO-related landmarks. A deterministic geometric module then calculated TPA and mapped the derived osteotomy geometry to the nearest clinically available saw blade class.

The mean absolute error for TPA prediction was 1.34 ± 1.73°, and the median absolute error was 0.75°. Overall, 164/200 cases (82.0%) were within 2° and 188/200 cases (94.0%) were within 4.8° of the surgeon reference. Mean bias was -0.39°, the 95% limits of agreement ranged from -4.62° to 3.85°, and Pearson's correlation coefficient was 0.87. For saw blade size prediction, mean absolute error was 0.32 ± 0.85 mm, exact agreement was achieved in 175/200 cases (87.5%), and all predictions remained within one adjacent class.

The proposed pipeline provided clinically useful automated estimates of TPA and saw blade size from routine lateral radiographs. However, occasional high-impact landmark failures remained, indicating that the system should be positioned as an interpretable decision-support tool that requires surgeon verification rather than as an unsupervised autonomous planning system.