Orientation Normalization Algorithm for Mandibular Condyle in the Small Field-of-View CBCT Images Based on Morphology Analysis.

Objectives: Due to the difference between the natural head position during scan and the orientation of CBCT display required for diagnosis, radiologists need to manually adjust the image orientation during clinical diagnosis. To eliminate this difference, this study explored orientation normalization algorithm for mandibular condyle in the small field-of-view (FoV) cone beam computed tomography (CBCT) images.

Methods: Based on the morphology analysis, we designed principal component analysis (PCA) based orientation normalization algorithm for condyle in the small FoV CBCT images. The algorithm involves first locating the reference center, defined as the center coordinates of the condylar head in the maximum axial plane, through segmentation and centroid calculation. Subsequently, the maximum principal orientations in the axial, coronal, and sagittal planes are extracted using PCA algorithm. Finally, the condyle orientation is normalized by using rotation transformation matrices derived from condylar head center localization and principal orientation extraction.

Results: Our algorithm was evaluated on two CBCT image datasets with 692 scans, and multiple experiments were designed from aspects of algorithm accuracy and stability. Experimental results demonstrate that images with orientation normalization are consistent with the radiologists expected perspective from both qualitative and quantitative aspects. The normalized results of CBCT images taken at multiple time-points also further confirm that our method has good stability.

Conclusion: Based on the morphological characteristics, medical image processing algorithm can achieve accurate and stable orientation normalization for condyle in the small FoV CBCT images.