Maxillary Sinus

An accurate three-dimensional (3D) segmentation of the maxillary sinus is crucial for multiple diagnostic and treatment applications. Yet, it is challenging and time-consuming when manually performed on a cone-beam computed tomography (CBCT) dataset. Recently, convolutional neural networks (CNNs) have proven to provide excellent performance in the field of 3D image analysis. Hence, this study developed and validated a novel automated CNN-based methodology for the segmentation of maxillary sinus using CBCT images. A dataset of 264 sinuses were acquired from 2 CBCT devices and randomly divided into 3 subsets: training, validation, and testing. A 3D U-Net architecture CNN model was developed and compared to semi-automatic segmentation in terms of time, accuracy, and consistency. The average time was significantly reduced (p-value < 2.2e-16) by automatic segmentation (0.4 min) compared to semi-automatic segmentation (60.8 min). The model accurately identified the segmented region with a dice similarity co-efficient (DSC) of 98.4%. The inter-observer reliability for minor refinement of automatic segmentation showed an excellent DSC of 99.6%. The proposed CNN model provided a time-efficient, precise, and consistent automatic segmentation which could allow an accurate generation of 3D models for diagnosis and virtual treatment planning.

The detection of maxillary sinus wall is important in dental fields such as implant surgery, tooth extraction, and odontogenic disease diagnosis. The accurate segmentation of the maxillary sinus is required as a cornerstone for diagnosis and treatment planning. This study proposes a deep learning-based method for fully automatic segmentation of the maxillary sinus, including clear or hazy states, on cone-beam computed tomographic (CBCT) images. A model for segmentation of the maxillary sinuses was developed using U-Net, a convolutional neural network, and a total of 19,350 CBCT images were used from 90 maxillary sinuses (34 clear sinuses, 56 hazy sinuses). Post-processing to eliminate prediction errors of the U-Net segmentation results increased the accuracy. The average prediction results of U-Net were a dice similarity coefficient (DSC) of 0.9090 ± 0.1921 and a Hausdorff distance (HD) of 2.7013 ± 4.6154. After post-processing, the average results improved to a DSC of 0.9099 ± 0.1914 and an HD of 2.1470 ± 2.2790. The proposed deep learning model with post-processing showed good performance for clear and hazy maxillary sinus segmentation. This model has the potential to help dental clinicians with maxillary sinus segmentation, yielding equivalent accuracy in a variety of cases.

Bone regeneration originates from proliferation and differentiation of osteoprogenitors via either endochondral or intramembranous ossification; and the regeneration capacities decline with age and estrogen loss. Maxillary sinus floor lifting (MSFL) is a commonly used surgical procedure for guiding bone regeneration in maxilla. Radiographic analysis of 1210 clinical cases of maxilla bone regeneration after MSFL revealed that the intrasinus osteogenic efficacy was independent of age and gender, however; and this might be related to the Schneiderian membrane that lines the sinus cavity. In view of the particularity of this biological process, our present study aimed to elucidate the underlying mechanism of MSFL-induced bone regeneration. We first established a murine model to simulate the clinical MSFL. By single-cell RNA-sequencing and flow cytometry-based bulk RNA-sequencing, we identified a novel Krt14+Ctsk+ subset of cells that display both epithelial and mesenchymal properties and the transcriptomic feature of osteoprogenitors. Dual recombinases-mediated lineage tracing and loss-of-function analyses showed that these Krt14+Ctsk+ progenitors contribute to both MSFL-induced osteogenesis and physiological bone homeostasis by differentiating into Krt14-Ctsk+ descendants which show robust osteogenic capacity. In addition, we detected a similar population of Krt14+Ctsk+ cells in human samples of Schneiderian membrane, which show a highly similar osteogenic potential and transcriptomic feature to the corresponding cells in mice. The identification of this Krt14+Ctsk+ population, featured by osteoprogenitor characteristics and dual epithelial-mesenchymal properties, provides new insight into the understanding of bone regeneration and may open more possibilities for clinical applications.

ObjectivesWhile maxillary sinus fungal balls (MSFB) can be associated with odontogenic conditions (MSFBO), MSFBO clinical and dental features have not been compared to odontogenic sinusitis (ODS). This multicenter study aimed to compare characteristics of MSFB, MSFBO, and ODS.MethodsA multicenter international retrospective cohort study was conducted on adults with MSFBs and ODS who underwent sinus surgery. First in MSFBs, it was determined whether different dental conditions were more likely in FB versus non-FB sides. Second, clinical features and dental pathologies were compared between MSFBO and ODS. For analyses, dental conditions were considered individually and as two groups: infectious pathologies and dental/oral procedures with indwelling metallic materials.ResultsAfter exclusions, there were 203 MSFBs and 163 ODS. Among MSFBs, 141 were MSFBOs. FB sides were associated with sinus protrusion of root canal treatment (RCT) materials (p = 0.040) and dental implants (p = 0.040). Compared to MSFBO, ODS patients were younger, more likely to have MS purulence (OR = 40.9, p ConclusionCompared to MSFBs, MSFBOs were associated with RCT extrusion and implant protrusion. Compared to MSFBOs, ODS was more likely purulent and associated with infectious dental pathologies. While ODS is often distinct from MSFBO, the two conditions can coexist, and surgeons must determine whether patients have infectious dental pathology requiring treatment with both conditions.Level of evidence: 4