A Landmark Detection Approach Applied to Robust Estimation of the Exposure Index in Digital Radiography

- We estimate the exposure index (EI), an X-ray image quality measure, by detecting clusters of anatomical landmarks.
- The landmarks are detected with an unsupervised approach that uses both global spatial information and local analysis.
- The search of landmark positions is sparsely conducted by visiting salient points.
- The results indicate that automatically computed EI values well correspond to those obtained with manual interaction.

PurposeThe exposure index is an important measure used in digital radiography to control the dose at the detector. This value should be computed in regions of interest that are adapted to each patient's anatomy and pose.Material and methodsWe propose to define automatically these regions based on anatomical landmarks in the main structures of interest (head, thoracic spine, lungs, lumbar spine, pelvis, femurs, knees, tibiae). This task is achieved by combining the global information on the size and the positions of the anatomical structures on the one hand, with local analysis on the other hand.ResultsExperimental results, on a varied database of 82 full-body acquisitions, demonstrate the interest of the proposed approach, with less errors than existing approaches, in particular on frontal view acquisitions. The method is also robust to variations in patient's conditions and to the potential presence of metallic objects.ConclusionThe approach proposed in this paper allows consistently estimating exposure index values associated with different X-ray acquisitions. This suggests that the application of the proposed method to clinical practice is promising.

58