Fig. 7From: Deep learning-based automatic-bone-destruction-evaluation system using contextual information from other jointsVisualization results of prediction by each classification model of target joints in X-ray images. Each bounding box represents the detected target joints. The color of the bounding box indicates how the classification results compare to ground-truth (GT). Blue indicates GT is non-intact, and prediction is non-intact (true positive). White indicates GT is intact, and prediction is intact (true negative). Red indicates GT is non-intact, and prediction is intact (false negative). A The results for erosion and B for JSN. GT, ground-truth; JSN, joint space narrowing; SISO, single-input single-output; MIMO, multiple-input multiple-outputBack to article page