Machine learning in 3D auto-filling alveolar cleft of CT images to assess the influence of alveolar bone grafting on the development of maxilla

Abstract

Background Machine learning based auto-segmentation of 3D images has been developed rapidly in recent years. However, the application of this new method in the research of patients with unilateral cleft lip and palate (UCLP) is very limited. In this study, a machine learning algorithm utilizing 3D U-net was used to automatically segment the maxilla, fill the cleft and evaluate the alveolar bone graft in UCLP patients. Cleft related factors and the surgery impact on the development of maxilla were analyzed. Methods Preoperative and postoperative computed tomography images of 32 patients (64 images) were obtained. The deep-learning-based protocol was used to segment the maxilla and defect, followed by manual refinement. Paired t-tests and Mann-Whitney tests were performed to reveal the changes of the maxilla after surgery. Two-factor, two-level analysis for repeated measurement was used to examine the different trends of growth on the cleft and non-cleft sides of the maxilla. Pearson and Spearman correlations were used to explore the relationship between the defect and the changes of the maxillary cleft side. Results One-year after the alveolar bone grafting surgery, different growth amount was found on the cleft and non-cleft sides of maxilla. The maxillary length (from 34.64 ± 2.48 to 35.67 ± 2.45 mm) and the alveolar length (from 36.58 ± 3.21 to 37.63 ± 2.94 mm) increased significantly only on the cleft side while the maxillary anterior width (from 11.61 ± 1.61 to 12.01 ± 1.41 mm) and posterior width (from 29.63 ± 2.25 to 30.74 ± 2.63 mm) increased significantly only on the non-cleft side after surgery. Morphology of the cleft was found to be related to the pre-surgical maxillary dimension on the cleft side, while its correlation with the change of the maxilla after surgery was low or not statistically significant. Conclusion The auto-segmentation of the maxilla and the cleft could be performed very efficiently and accurately with the machine learning method. Asymmetric growth was found on the cleft and non-cleft sides of the maxilla after alveolar bone graft in UCLP patients. The morphology of the cleft mainly contributed to the pre-operation variance of the maxilla but had little impact on the maxilla growth after surgery.

Deep learning‐based automatic segmentation of bone graft material after maxillary sinus augmentation

“…Deep learning has been widely applied in medical image identification, segmentation, and registration due to its promising performance with high precision and efficiency (Xu et al, 2022). Deep learning-based methods have been successfully implemented to segment 3D maxillofacial anatomical structures, such as teeth (Cui et al, 2022), mandible , maxillae (Zhang et al, 2023), zygoma bone (Tao et al, 2023), and maxillary sinuses (Xu et al, 2020) from CBCT images. It has been reported that human radiologists obtained a lower accuracy and segmentation efficiency in teeth and alveolar bone segmentation than in deep learning models (Cui et al, 2022).…”