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

OBJECTIVES: To investigate the accuracy and reliability of deep learning in automatic graft material segmentation after maxillary sinus augmentation (SA) from cone-beam computed tomography (CBCT) images. MATERIALS AND METHODS: One hundred paired CBCT scans (a preoperative scan and a postoperative scan) were collected and randomly allocated to training (n = 82) and testing (n = 18) subsets. The ground truths of graft materials were labeled by three observers together (two experienced surgeons and a computer engineer). A deep learning model including a 3D V-Net and a 3D Attention V-Net was developed. The overall performance of the model was assessed through the testing data set. The comparative accuracy and inference time consumption of the model-driven and manual segmentation (by two surgeons with 3 years of experience in dental implant surgery) were conducted on 10 CBCT scans from the test samples. RESULTS: The deep learning model had a Dice coefficient (Dice) of 90.36 ± 2.53%, a 95% Hausdorff distance (HD) of 1.59 ± 0.82 mm, and an average surface distance (ASD) of 0.38 ± 0.11 mm. The proposed model only needed 7.2 s, while the surgeon took 19.15 min on average to complete a segmentation task. The overall performances of the model were significantly superior to those of surgeons. CONCLUSIONS: The proposed deep learning model yielded a more accurate and efficient performance of automatic segmentation of graft material after SA than that of the two surgeons. The proposed model could facilitate a powerful system for volumetric change evaluation, dental implant planning, and digital dentistry.

Effects of different grafting materials on volumetric changes in the Schneiderian membrane following lateral maxillary sinus floor elevation: a preliminary study.

OBJECTIVES: To investigate the potential influence of different grafting materials on maxillary sinus membrane dimensions and ostium patency following lateral sinus floor elevation (SFE) as assessed using cone-beam computed tomography (CBCT). MATERIALS AND METHODS: A total of 40 sinuses in 40 patients were included. Twenty sinuses were referred for SFE with deproteinized bovine bone mineral (DBBM), and the remaining 20 sinuses were grafted with calcium phosphate (CP). CBCT was performed prior to and 3 to 4 days after surgery. The dimensions of the Schneiderian membrane volume and ostium patency were evaluated, and potential relationships between volumetric changes and any associated factors were analyzed. RESULTS: The median increase in membrane-whole cavity volume ratios was 43.97% in the DBBM group and 67.58% in the CP group, demonstrating no statistically significant difference (p = 0.17). The rates of increased obstruction after SFE were 11.1% for the DBBM group versus 44.4% for the CP group (p = 0.03). The graft volume was found to be positively correlated with the postoperative membrane-whole cavity volume ratio (r = 0.79; p < 0.01) and the membrane-whole cavity volume ratio increase (r = 0.71; p < 0.01). CONCLUSIONS: The two grafting materials seem to have a similar effect on transient volumetric changes in the sinus mucosa. However, the choice of grafting material should still be made with caution since sinuses grafted using DBBM exhibited less swelling and less ostium obstruction.

[The feasibility of zygomatic implant quad approach in patients with tooth agenesis: a radiographic analysis].

PURPOSE: The aim of this study was to analyze the feasibility of zygomatic implant quad approach in patients with tooth agenesis. METHODS: Based on the data from cone-beam CT (CBCT), twenty one patients with tooth agenesis who were planned to receive zygomatic implant quad approach were enrolled. The radiographic bone-to-implant contact (rBIC) of each zygomatic implant placed virtually in patients' zygomatic segment was measured. SPSS 25.0 software package was used for statistical analysis. RESULTS: Twenty patients' plans of zygomatic implant quad approach were completed (12 men and 8 women). A total of 80 zygomatic implants were placed virtually and the average rBIC of zygomatic segment was (13.85±3.29) mm. The rBIC values of 40 mesial zygomatic implants and 40 distal zygomatic implants were (13.80±3.74) mm and (13.90±2.81) mm, respectively(P>0.05). The average rBIC in male of 24 mesial zygomatic implants and 24 distal zygomatic implants were(14.21±4.08) mm and(14.31±3.18) mm, respectively, slightly higher than those in female of 16 mesial zygomatic implants and 16 distal zygomatic implants, which were (13.18±3.18) mm and (13.29±2.10) mm, respectively. There was no significant difference between the two groups (P>0.05). The average rBIC of 15 extra sinus zygomatic implants, 46 against sinus lateral wall zygomatic implants and 19 intra-sinus zygomatic implants were (16.27±2.95), (13.87±3.10) and (11.88±2.78) mm, respectively. There was significant difference between the extra sinus zygomatic implants and the other two(P<0.05). CONCLUSIONS: It is feasible to plan zygomatic implant quad approach for patients with tooth agenesis. Zygomatic implants can get adequate rBIC in zygomatic segment and to provide sufficient support and retention of the superstructure.