Maxillary sinus floor augmentation comparing removing versus retaining antral pseudocyst: A retrospective cohort study

Accuracy of a Cascade Network for Semi-Supervised Maxillary Sinus Detection and Sinus Cyst Classification

OBJECTIVE

Maxillary sinus mucosal cysts represent prevalent oral and maxillofacial diseases, and their precise diagnosis is essential for surgical planning in maxillary sinus floor elevation. This study aimed to develop a deep learning-based pipeline for the classification of maxillary sinus lesions in cone beam computed tomography (CBCT) images to provide auxiliary support for clinical diagnosis.

METHODS

This study utilized 45 136 maxillary sinus images from CBCT scans of 541 patients. A cascade network was designed, comprising a semi-supervised maxillary sinus area object detection module and a maxillary sinus lesions classification module. The object detection module employed a semi-supervised pseudo-labelling training strategy to expand the maxillary sinus annotation dataset. In the classification module, the performance of Convolutional Neural Network and Transformer architectures was compared for maxillary sinus mucosal lesion classification. The object detection and classification modules were evaluated using metrics including Accuracy, Precision, Recall, F1 score, and Average Precision, with the object detection module additionally assessed using Precision-Recall Curve.

RESULTS

The fully supervised pseudo-label generation model achieved an average accuracy of 0.9433, while the semi-supervised maxillary sinus detection model attained 0.9403. ResNet-50 outperformed in classification, with accuracies of 0.9836 (sagittal) and 0.9797 (coronal). Grad-CAM visualization confirmed accurate focus on clinically relevant lesion features.

CONCLUSION

The proposed pipeline achieves high-precision detection and classification of maxillary sinus mucosal lesions, reducing manual annotation while maintaining accuracy.

Automated Segmentation of Graft Material in 1-Stage Sinus Lift Based on Artificial Intelligence: A Retrospective Study

OBJECTIVES

Accurate assessment of postoperative bone graft material changes after the 1-stage sinus lift is crucial for evaluating long-term implant survival. However, traditional manual labeling and segmentation of cone-beam computed tomography (CBCT) images are often inaccurate and inefficient. This study aims to utilize artificial intelligence for automated segmentation of graft material in 1-stage sinus lift procedures to enhance accuracy and efficiency.

MATERIALS AND METHODS

Swin-UPerNet along with mainstream medical segmentation models, such as FCN, U-Net, DeepLabV3, SegFormer, and UPerNet, were trained using a dataset of 120 CBCT scans. The models were tested on 30 CBCT scans to evaluate model performance based on metrics including the 95% Hausdorff distance, Intersection over Union (IoU), and Dice similarity coefficient. Additionally, processing times were also compared between automated segmentation and manual methods.

RESULTS

Swin-UPerNet outperformed other models in accuracy, achieving an accuracy rate of 0.84 and mean precision and IoU values of 0.8574 and 0.7373, respectively (p < 0.05). The time required for uploading and visualizing segmentation results with Swin-UPerNet significantly decreased to 19.28 s from the average manual segmentation times of 1390 s (p < 0.001).

CONCLUSIONS

Swin-UPerNet exhibited high accuracy and efficiency in identifying and segmenting the three-dimensional volume of bone graft material, indicating significant potential for evaluating the stability of bone graft material.

Patient and implant-related risk factors for implant failure of one-stage lateral sinus floor elevation: A 2- to 10-year retrospective study

OBJECTIVES

This retrospective study aimed to evaluate the early and late implant failure rates of one-stage lateral sinus floor elevation (LSFE) and to identify the patient and implant-related risk factors associated with these failures.

MATERIALS AND METHODS

All patients treated with one-stage LSFE from January 2014 to December 2021 were evaluated for inclusion. A total of 618 patients with 936 implants met the inclusion criteria. Clinical and radiographic information about patient and implants was collected. Univariate and multivariate Cox proportional hazards frailty regression models were performed to identify risk factors for early and late implant failure.

RESULTS

The cumulative implant survival rate was 95.62% (95% CI 93.90%-97.68%), with 16 early implant failures and 25 late implant failures. The Cox analysis indicated that ≤3 mm residual bone height (RBH) was associated with a higher early failure rate. For late implant failure, smoking habit, ≤3 mm RBH, and certain implant brand were independent risk factors. Narrow sinus ostium, long infundibulum, and flat thickening of Schneiderian membrane might be non-independent risk factors for late implant failure. No significance was found in other variables, including age, periodontitis history, implant characteristics (position, diameter, length, protrusion length, marginal bone loss), surgeon experience, healing time, opposing dentition, and prosthesis.

CONCLUSIONS

One-stage LSFE is a predictable treatment for patients with atrophic maxilla. ≤3 mm RBH increased the risk of early implant failure, while smoking habit, ≤3 mm RBH, and certain implant brand were independent risk factors for late implant failure.

Radiographic outcomes of lateral sinus floor elevation at sites without perforations and sites with perforations managed with a resorbable membrane: A retrospective study

AIM

To evaluate the radiographic outcomes of lateral sinus floor elevation with simultaneous implant placement at sites without sinus membrane perforation (SMP) and sites with SMP managed with a resorbable membrane.

MATERIALS AND METHODS

One hundred and thirty-nine patients and 170 implants (56 perforation, 114 non-perforation) were included. Cone-beam computed tomography (CBCT) images were taken before surgery (T0), immediately after surgery (T1) and 6 months after surgery (T2). Post-operative augmentation parameters, including endo-sinus bone gain (ESBG) along the implant axis, mean new bone height (NBH) surrounding the implant and augmentation volume (AV), were measured at T1 and T2.

RESULTS

At T1, there were no significant differences in ESBG, NBH and AV between the two groups. At T2, although ESBG did not significantly differ between the two groups, NBH (8.50 ± 1.99 mm vs. 9.99 ± 2.52 mm, p = .039) and AV (519.37 ± 258.38 mm3 vs. 700.99 ± 346.53 mm3, p < .001) were significantly lower in the perforation group. The shrinkage of graft material from T1 to T2, including ΔESBG (p = .002), ΔNBH (p < .001) and ΔAV (p < .001), was higher in the perforation group.

CONCLUSIONS

SMP during LSFE with simultaneous implant placement is associated with greater resorption of the grafted area at a 6-month follow-up.

Survival analysis of implants placed simultaneously with lateral sinus floor elevation in severely atrophic maxilla: A 3- to 12-year retrospective cohort study

OBJECTIVES

To retrospectively evaluate whether implants placed simultaneously with lateral sinus floor elevation (LSFE) in severely atrophic maxilla (residual bone height [RBH] ≤3 mm) could achieve long-term survival and comprehensively analyze the factors influencing their survival rates.

MATERIALS AND METHODS

A total of 123 patients receiving LSFE and simultaneous implant placement from 2010 to 2019 and their 123 implants in sites with RBH ≤3 mm were included in this study. Basic characteristics of patients and implants were collected from the medical record system and cone-beam computed tomography (CBCT) images. Kaplan-Meier survival curves were applied to estimate cumulative survival rates (CSRs) and Cox proportional hazards regression models were used to detect factors influencing implant survival.

RESULTS

The 6-year and 12-year CSR of implants placed in sites with RBH ≤3 mm were 95.7% (95% confidence interval [CI]: 92.1%-99.5%) and 76.6% (95% CI: 58.1%-100%), respectively. Eight patients presented late implant failure. Univariate and multivariate Cox regression analyses demonstrated that RBH ≤2 mm (hazard ratio [HR]: 20.63, p = 0.000) and smoking habit (HR: 6.055, p = 0.024) were significantly associated with long-term implant survival. Specifically, the 10-year CSR of implants in sites with RBH ≤2 mm (53.3%, 95% CI: 27.5%-100%) was dramatically lower than those in sites with RBH >2 mm (92.9%, 95% CI: 81.7%-100%, p = 0.000).

CONCLUSIONS

Implants placed simultaneously with LSFE in sites with RBH ≤3 mm can achieve long-term survival. However, caution is required especially for implantation in sites with RBH ≤2 mm. Besides, the smoking habit is also considered a risk factor jeopardizing long-term implant survival.

Radiographic feature changes in an antral pseudocyst that existed prior to sinus floor augmentation and dental implant placement, 15 years after initial detection - a case report

INTRODUCTION AND IMPORTANCE

Maxillary sinus floor augmentation is acceptable and safe for bone augmentation prior to insertion of dental implants in atrophied maxillary bones. Anatomical variations and lesions of the maxillary sinus, including antral pseudocysts, are common radiological findings that can affect the outcomes of maxillary sinus augmentation. We show the changes in the radiological features of an antral pseudocyst that existed before maxillary sinus augmentation and 15 years after the insertion of dental implants.

CASE PRESENTATION

The patient was a 69-year-old male with an unremarkable medical history. The initial orthopantomogram revealed a very large antral pseudocyst in the left maxillary sinus. After upper left second molar extraction and maxillary sinus augmentation, two dental implants were inserted in regions 26 and 27. The pseudocyst had changed radiologically 15 years later, but a biopsy showed no characteristic changes, and the dental implants showed no functional failures.

CLINICAL DISCUSSION

We present a case of an antral pseudocyst that was not removed before or during sinus floor augmentation. A debate is ongoing regarding whether antral pseudocysts affect maxillary sinus augmentation, and various strategies have been applied to prevent intraoperative and postoperative complications, including removal of pseudocysts 3-12 months before maxillary sinus augmentation, removal during maxillary sinus augmentation, and leaving them alone when the floor is raised.

CONCLUSION

The present case showed a preexisting antral pseudocyst at maxillary sinus floor augmentation and insertion of the implants, which changed radiologically 15 years later, but did not affect the function of the dental implants.

Maxillary Antral Pseudocyst Drift after Osteotome Sinus Floor Elevation with Simultaneous Implant Placement: A Case Report and Literature Review

This report describes maxillary antral pseudocyst drift after maxillary sinus floor augmentation through osteotome sinus floor elevation with simultaneous implant placement. 3D Slicer was used to measure the pseudocyst and maxilla for the placement of the implants; follow-up visits were scheduled at 6, 12, and 22 months. No adverse effects were observed during or after surgery, and all implants exhibited osseointegration without mobility. At 6 months after surgery, the pseudocyst had moved posterolaterally from the preoperative position near the anterior medial maxillary sinus, then returned to its original position at 12 months. However, it had remigrated to the posterolateral position at 22 months. The preoperative volume of the pseudocyst was 3.795 mm³; it was 2.370, 3.439, and 2.930 mm³ at 6, 12, and 22 months after surgery, respectively. The changes in pseudocyst drift and volume did not have a substantial negative influence on the implants, presumably because of cystic attachment and the recurrence of multiple pseudocysts at different locations. The risks associated with changes in a pseudocyst can be avoided, if an appropriate treatment plan is selected.