Local adaptive thresholding

Theoretical background¶

Local adaptive thresholding compute a threshold for each voxel using the intensity range of neighboring voxels. It contrast with the fixed global threshold that uses a single threshold for the entire image.

To use local adaptive thresholding with the default input settings, use the following command:

adaptive-local-threshold

Input parameter settings¶

HR-pQCT

The following input settings are used for the local adaptive thresholding:

lower_threshold: float = 190
upper_threshold: float = 450
structuring_element_size: int = 6,

Examples and workflows¶

Workflows that include local adaptive thresholding: local adaptive thresholding.

If you use this filter, please cite Kuczynski et al. (2026).

References¶

Kuczynski, M. T., Poncioni, S., Elmahdy, S., Baldesarra, E., Zysset, P., Manske, S. L., & Whittier, D. E. (2026). Improved segmentation accuracy in high-resolution peripheral quantitative computed tomography scans of carpal bones using adaptive local thresholding. JBMR Plus, 10(6). 10.1093/jbmrpl/ziag054