Fig. 5: Differences and distance error analysis between manually annotated and SA-ai automatically segmented intrasinus bone graft material. | npj Digital Medicine

Fig. 5: Differences and distance error analysis between manually annotated and SA-ai automatically segmented intrasinus bone graft material.

From: A deep learning based automated maxillary sinus segmentation and bone grafts analysis in CBCT images

Fig. 5: Differences and distance error analysis between manually annotated and SA-ai automatically segmented intrasinus bone graft material.

a, c, e Multi-planar views (coronal, sagittal, and axial) showing the superposition of expert manual annotations (red contour) and SA-ai automated segmentation (green contour). White arrows indicate areas of minor discrepancy. b, d, f Corresponding 3D distance error heat maps quantifying the spatial deviation between the manual and automated surface meshes. The color scale transitions from blue (0.0 mm error) to red (>3.0 mm error).

Back to article page