Figure 4 | Scientific Reports

Figure 4

From: Detecting medial patellar luxation with ensemble deep convolutional neural network based on a single rear view image of the hindlimb

Figure 4

Comparison of medial patellar luxation (MPL) detection between the proposed model and human experts. The figure displays five instances where the proposed model exhibited incorrect detection results. The ground-truth (GT) annotations and the five veterinarians’ (V1–V5) expertise were used for benchmarking and comparison with human detection performance. (2-Column).

Back to article page