-
Clinical Implant Dentistry and Related... Jun 2024Cone-beam computed tomography (CBCT) imaging of the maxillary sinus is indispensable for implantologists, offering three-dimensional anatomical visualization,... (Review)
Review
Cone-beam computed tomography (CBCT) imaging of the maxillary sinus is indispensable for implantologists, offering three-dimensional anatomical visualization, morphological variation detection, and abnormality identification, all critical for diagnostics and treatment planning in digital implant workflows. The following systematic review presented the current evidence pertaining to the use of artificial intelligence (AI) for CBCT-derived maxillary sinus imaging tasks. An electronic search was conducted on PubMed, Web of Science, and Cochrane up until January 2024. Based on the eligibility criteria, 14 articles were included that reported on the use of AI for the automation of CBCT-derived maxillary sinus assessment tasks. The QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool was used to evaluate the risk of bias and applicability concerns. The AI models used were designed to automate tasks such as segmentation, classification, and prediction. Most studies related to automated maxillary sinus segmentation demonstrated high performance. In terms of classification tasks, the highest accuracy was observed for diagnosing sinusitis (99.7%), whereas the lowest accuracy was detected for classifying abnormalities such as fungal balls and chronic rhinosinusitis (83.0%). Regarding implant treatment planning, the classification of automated surgical plans for maxillary sinus floor augmentation based on residual bone height showed high accuracy (97%). Additionally, AI demonstrated high performance in predicting gender and sinus volume. In conclusion, although AI shows promising potential in automating maxillary sinus imaging tasks which could be useful for diagnostic and planning tasks in implantology, there is a need for more diverse datasets to improve the generalizability and clinical relevance of AI models. Future studies are suggested to focus on expanding the datasets, making the AI model's source available, and adhering to standardized AI reporting guidelines.
PubMed: 38863306
DOI: 10.1111/cid.13352 -
Journal of the American Society of... May 2024Salivary gland lesions are routinely evaluated by fine-needle aspiration cytology (FNAC) preoperatively. The Milan System for Reporting Salivary Gland Cytopathology...
INTRODUCTION
Salivary gland lesions are routinely evaluated by fine-needle aspiration cytology (FNAC) preoperatively. The Milan System for Reporting Salivary Gland Cytopathology (MSRSGC) has standardized salivary gland FNAC reporting. Its application in major salivary glands (MSGs) has been well-established; however, its utility in minor salivary glands (MiSGs) is not well-known. We studied the utility of MSRSGC in MiSG FNAC.
MATERIALS AND METHODS
A retrospective search of MiSG FNACs from 2 academic institutions (2006-2023) was performed. FNACs were classified using the MSRSGC. Histologic data were reviewed and recorded. The risk of malignancy (ROM), risk of neoplasia (RON), diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated.
RESULTS
The series included 43 MiSG FNAC (24 males and 18 females), with a mean age of 55 years (range 10-92). Aspirated sites included the following: palate, buccal space, floor of mouth, lip, tongue, and maxillary sinus. FNACs were classified as nondiagnostic (1), nonneoplastic (3), atypia of undetermined significance (6), benign neoplasm (9), salivary gland neoplasm of uncertain malignant potential (15), suspicious for malignancy, (2) and malignant (7). The risk of neoplasia and risk of malignancy were 87% and 39%. The diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 100%, respectively.
CONCLUSIONS
Milan System for Reporting Salivary Gland Cytopathology offers valuable information for stratifying MiSG lesions. However, the distribution and the range of diagnostic entities encountered differ somewhat from those in MSGs. For instance, mucinous cyst contents may warrant unique consideration in MiSG; while an atypical classification is recommended in MSGs, the high prevalence of mucoceles in MiSG may tilt this group toward benignity.
PubMed: 38862316
DOI: 10.1016/j.jasc.2024.05.001 -
International Journal of Radiation... Jun 2024This study aims to examine the role of elective nodal irradiation (ENI) in clinically node-negative (cN0) sinonasal squamous cell carcinoma (SNSCC) and to define the...
PURPOSE
This study aims to examine the role of elective nodal irradiation (ENI) in clinically node-negative (cN0) sinonasal squamous cell carcinoma (SNSCC) and to define the optimal radiation fields for ENI.
METHODS AND MATERIALS
We retrospectively reviewed 368 cN0 SNSCC patients treated between 2009 and 2021. The study evaluated the impact of ENI on overall survival (OS), progression-free survival (PFS), regional-failure-free survival (RFS), and distant metastasis-free survival (DMFS), along with the coverage areas of ENI.
RESULTS
The majority of patients underwent surgery (n=316, 85.9%), with 75% (n=276) having tumors in the maxillary sinus or nasal cavity and 67.7% (n=249) presenting with T4 disease. Additionally, 32.3% (n=119) of the tumors were poorly differentiated. The 5-year OS, PFS, RFS, and DMFS rates were 59.3%, 54.0%, 57.6%, and 58.8%, respectively. ENI was performed in 217 patients (59%), with sixteen experiencing neck relapse during follow-up. While ENI did not enhance survival rates, it significantly reduced the overall regional-failure rate (7.9% vs. 1.8%, χ =7.98, p<0.01) and the cumulative incidence of regional failure (p=0.045). Additionally, the subgroups with maxillary sinus origin (2.33% vs. 13.51%, p=0.025), T4 stage (1.80% vs. 8.54%, p=0.028), and poor differentiation (2.44% vs. 13.51%, p=0.029) had higher cumulative incidences of regional failure in patients without ENI. No significant difference was observed in survival and regional failure rates between patients treated with ENI to levels Ib and II with or without level III, as well as between cN0 patients with non-midline crossing lesions receiving unilateral or bilateral ENI.
CONCLUSIONS
Despite no survival benefit, ENI significantly decreases the regional failure rate in cN0 SNSCC patients. For primary lesions not crossing the midline, ipsilateral ENI targeting levels Ib and II proves to be an effective strategy.
PubMed: 38862085
DOI: 10.1016/j.ijrobp.2024.05.029 -
Maxillofacial Plastic and... Jun 2024Odontogenic maxillary sinusitis (OMS) is widely acknowledged in both the dentistry and otolaryngology fields. Recently, iatrogenic odontogenic maxillary sinusitis cases...
BACKGROUND
Odontogenic maxillary sinusitis (OMS) is widely acknowledged in both the dentistry and otolaryngology fields. Recently, iatrogenic odontogenic maxillary sinusitis cases can be encountered frequently. The purpose of this study was to evaluate the effect of intraoral sinus irrigation using the small lateral window approach in patients with odontogenic maxillary sinusitis by comparing pre- and postoperative volumetric measurement of CBCT and symptoms. We surveyed 21 patients who visited the Oral and Maxillofacial Surgery Department at PNUDH from 2016 to 2022. All the patients' information was extracted from an electronic database. The patients with a follow-up period of 2 months or more were included. The three-dimensional volumetric measurement was performed using the ImageJ program (National Institute of Health, University of Wisconsin).
RESULTS
Among 21 patients, 16 (76.1%) were male, and 5 (23%) were female. The most common type of surgery was general anesthesia (16 cases) in which oroantral fistula was present in 7 cases. In the causes of maxillary sinusitis, there were seven implant-related patients, five patients of tooth extraction, seven patients of bone grafting, and two patients in other groups. Radiographic opacity decreased by 40.15% after sinus irrigation especially in bone graft and tooth extraction cases. Clinically, symptoms improved in 17 patients (80.9%).
CONCLUSION
By this study, it can be concluded that maxillary sinus irrigation using the small lateral window approach is a clinically and radiologically effective treatment method for odontogenic maxillary sinusitis.
PubMed: 38861059
DOI: 10.1186/s40902-024-00429-6 -
BMC Medical Imaging Jun 2024To construct the deep learning convolution neural network (CNN) model and machine learning support vector machine (SVM) model of bone remodeling of chronic maxillary...
OBJECTIVE
To construct the deep learning convolution neural network (CNN) model and machine learning support vector machine (SVM) model of bone remodeling of chronic maxillary sinusitis (CMS) based on CT image data to improve the accuracy of image diagnosis.
METHODS
Maxillary sinus CT data of 1000 samples in 500 patients from January 2018 to December 2021 in our hospital was collected. The first part is the establishment and testing of chronic maxillary sinusitis detection model by 461 images. The second part is the establishment and testing of the detection model of chronic maxillary sinusitis with bone remodeling by 802 images. The sensitivity, specificity and accuracy and area under the curve (AUC) value of the test set were recorded, respectively.
RESULTS
Preliminary application results of CT based AI in the diagnosis of chronic maxillary sinusitis and bone remodeling. The sensitivity, specificity and accuracy of the test set of 93 samples of CMS, were 0.9796, 0.8636 and 0.9247, respectively. Simultaneously, the value of AUC was 0.94. And the sensitivity, specificity and accuracy of the test set of 161 samples of CMS with bone remodeling were 0.7353, 0.9685 and 0.9193, respectively. Simultaneously, the value of AUC was 0.89.
CONCLUSION
It is feasible to use artificial intelligence research methods such as deep learning and machine learning to automatically identify CMS and bone remodeling in MSCT images of paranasal sinuses, which is helpful to standardize imaging diagnosis and meet the needs of clinical application.
Topics: Humans; Maxillary Sinusitis; Tomography, X-Ray Computed; Chronic Disease; Female; Bone Remodeling; Male; Support Vector Machine; Deep Learning; Middle Aged; Sensitivity and Specificity; Adult; Neural Networks, Computer; Aged; Artificial Intelligence
PubMed: 38858631
DOI: 10.1186/s12880-024-01316-2 -
Lin Chuang Er Bi Yan Hou Tou Jing Wai... Jun 2024NUT Carcinoma(NC) is a rare malignant tumor of unknown origin, which is highly aggressive. It is characterized by chromosome rearrangement accompanied by gene. The... (Review)
Review
NUT Carcinoma(NC) is a rare malignant tumor of unknown origin, which is highly aggressive. It is characterized by chromosome rearrangement accompanied by gene. The pathological manifestations were sudden and focal squamous in poorly differentiated or undifferentiated carcinoma. gene rearrangement can be used to diagnose NC. The prognosis of NUT cancer is poor. Clinically, there is no established treatment plan. treatment options mainly comprise surgery, radiotherapy and chemotherapy. A 74-year-old patient with NC of the nasal cavity and sinuses was reported. Her clinical presentation was right nasal congestion with facial swelling. Sinus CT and MRI showed soft tissue density in the right nasal cavity and maxillary sinus with bone destruction. After admission, the patient underwent nasal endoscopic biopsy, and the postoperative pathological FISH staining showed BRD4/NUT fusion t(15, 19). The tumor was significantly reduced after two courses of sequential chemoradiotherapy. Two months later, the patient underwent a partial maxillary resection due to the rapid regrowth of sinusoidal mass, invading the hard palate. The patient died 2 months after surgery due to multiple organ failure resulted from tumor metastasis, with a survival time of 11 months. The clinical characteristics, diagnosis and treatment of this case were reported and related literature was reviewed.
Topics: Humans; Aged; Female; Nasal Cavity; Nose Neoplasms; Neoplasm Proteins; Nuclear Proteins; Oncogene Proteins, Fusion; Carcinoma, Squamous Cell; Fatal Outcome; Carcinoma
PubMed: 38858120
DOI: 10.13201/j.issn.2096-7993.2024.06.014 -
Lin Chuang Er Bi Yan Hou Tou Jing Wai... Jun 2024To analyze the difference in 5-year survival between maxillary sinus adenoidal cystic carcinoma(maxillary sinus adenoid cystic carcinoma, MSACC) and squamous cell... (Comparative Study)
Comparative Study
[Comparison of 5-year survival rate and analysis of prognostic factors influencing the prognosis of adenoid cystic carcinoma and squamous cell carcinoma of the maxillary sinus: based on the SEER database].
To analyze the difference in 5-year survival between maxillary sinus adenoidal cystic carcinoma(maxillary sinus adenoid cystic carcinoma, MSACC) and squamous cell carcinoma(maxillary sinus squamous cell carcinoma, MSSCC) using the National Cancer Institute's Surveillance, Epidemiology, and End. database(SEER) and to explore the factors associated with the prognosis of the two tumors. The data of 161 patients with MSACC and 929 patients with MSSCC were collected from SEER database, and the 5-year overall survival rate(OS) and tumor specific survival rate(CSS) were compared between the two groups before and after propensity score matching. The forest map of multivariate Cox proportional hazard regression model was established to analyze the prognostic factors affecting the survival rate of patients with MSACC and MSSCC. There were statistical differences in 5-year OS and CSS between MSACC and MSSCC before and after propensity score matching(<0.001). Multivariate regression analysis showed that age, side of the disease, lymph node metastasis, operation and radiotherapy were the influencing factors of OS in MSACC, while age and operation were the influencing factors of CSS. Age, race, T grade, lymph node metastasis, systemic metastasis, surgery, radiotherapy and chemotherapy are the influencing factors of OS of MSSCC. Age, T grade, lymph node metastasis, systemic metastasis, surgery, radiotherapy and chemotherapy are the influencing factors of CSS. The 5-year survival rate of MSACC is higher than that of MSSCC. Surgery plays a positive role in the prognosis of the two kinds of tumors. The analysis results can provide some reference for their survival expectations and treatment choices.
Topics: Humans; Female; Male; Carcinoma, Adenoid Cystic; Prognosis; Carcinoma, Squamous Cell; SEER Program; Middle Aged; Survival Rate; Propensity Score; Maxillary Sinus Neoplasms; Maxillary Sinus; Proportional Hazards Models; Lymphatic Metastasis; Aged; Adult
PubMed: 38858112
DOI: 10.13201/j.issn.2096-7993.2024.06.006 -
International Journal of Computer... Jun 2024Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies,...
PURPOSE
Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS).
METHODS
Our approach uses a 3D convolutional autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D convolutional neural network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images.
RESULTS
The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an area under the precision-recall curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and masked autoencoding using SparK at 0.75.
CONCLUSION
A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly .
PubMed: 38850438
DOI: 10.1007/s11548-024-03172-5 -
JAMA Otolaryngology-- Head & Neck... Jun 2024Sinonasal squamous cell carcinoma (SNSCC) is the most commonly encountered cancer within the sinonasal cavity. Ongoing research has sought to ascertain the potential...
IMPORTANCE
Sinonasal squamous cell carcinoma (SNSCC) is the most commonly encountered cancer within the sinonasal cavity. Ongoing research has sought to ascertain the potential role of human papillomavirus (HPV) in the pathogenesis of SNSCC.
OBJECTIVE
To assess trends in HPV-associated and HPV-independent SNSCC over time, including assessment of clinical demographics, treatment patterns, and survival.
DESIGN, SETTING, AND PARTICIPANTS
This cohort study used patient data from the National Cancer Institute's Surveillance, Epidemiology, and End Results Program database between 1975 and 2018. Anatomic sites with a greater predilection for HPV positivity (ie, nasal cavity, ethmoid sinus) were used as a surrogate for HPV-associated SNSCC; meanwhile, patients with SNSCC in the other subsites were classified into the HPV-independent group. Data were analyzed from August 2022 to May 2023.
MAIN OUTCOMES AND MEASURES
Clinical demographics and mortality trends over time were described for the HPV-associated and HPV-independent groups and further stratified according to stage on presentation.
RESULTS
The study population consisted of 3752 patients with SNSCC (mean [SD] age at diagnosis, 65.7 [13.3] years; 2417 [64.4%] male), with 1983 (52.9%) having HPV-associated SNSCC and 1769 (47.1%) with HPV-independent SNSCC. Patients with HPV-associated subsites compared with patients with HPV-independent SNSCC were more likely to present with localized disease (838 [42.3%] vs 162 [9.2%]), whereas more patients in the HPV-independent group than HPV-associated group presented with regional disease (1018 [57.5%] vs 480 [24.2%]). Incidence-based mortality was stable over time within the HPV-associated group (0.32%) and, conversely, showed a significant decrease within the HPV-independent group (-2.29%). Patients with HPV-associated SNSCC had a higher 5-year overall survival when compared with the HPV-independent group (62% vs 35% [difference, 27 percentage points; 95% CI, 23-31 percentage points]). The better 5-year overall survival in the HPV-associated group vs HPV-independent group was present across all disease stages (localized: hazard ratio [HR], 2.67; 95% CI, 1.96-3.65; regional: HR, 1.53; 95% CI, 1.29-1.82; and distant: HR, 1.97; 95% CI, 1.52-2.55).
CONCLUSIONS AND RELEVANCE
This cohort study showed that the proportion of HPV-associated SNSCC rose over time associated with both a rise in the proportion of nasal cavity SNSCC and a decrease in HPV-independent maxillary sinus SNSCC. These data suggest that HPV-associated SNSCC has a distinct demographic and prognostic profile, given the improved survival seen in patients with HPV-associated SNSCC.
PubMed: 38842800
DOI: 10.1001/jamaoto.2024.1311 -
Nigerian Journal of Clinical Practice May 2024Panoramic radiography (PR) is available to determine the contact relationship between maxillary molar teeth (MMT) and the maxillary sinus floor (MSF). However, as PRs do...
Panoramic Radiography in the Evaluation of the Relationship of Maxillary Molar Teeth and Maxillary Sinuses on the Deep Learning Models Improved with the Findings Obtained by Cone Beam Computed Tomography.
BACKGROUND
Panoramic radiography (PR) is available to determine the contact relationship between maxillary molar teeth (MMT) and the maxillary sinus floor (MSF). However, as PRs do not provide clear and detailed anatomical information, advanced imaging methods can be used.
AIM
The aim of this study was to evaluate the diagnostic performance of deep learning (DL) applications that assess the relationship of the MSF to the first maxillary molar teeth (fMMT) and second maxillary molar teeth (sMMT) on PRs with data confirmed by cone beam computed tomography (CBCT).
METHODS
A total of 2162 fMMT and sMMT were included in this retrospective study. The contact relationship of teeth with MSF was compared among DL methods.
RESULTS
DL methods, such as GoogLeNet, VGG16, VGG19, DarkNet19, and DarkNet53, were used to evaluate the contact relationship between MMT and MSF, and 85.89% accuracy was achieved by majority voting. In addition, 88.72%, 81.19%, 89.39%, and 83.14% accuracy rates were obtained in right fMMT, right sMMT, left fMMT, and left sMMT, respectively.
CONCLUSION
DL models showed high accuracy values in detecting the relationship of fMMT and sMMT with MSF.
Topics: Humans; Cone-Beam Computed Tomography; Radiography, Panoramic; Deep Learning; Maxillary Sinus; Retrospective Studies; Female; Molar; Male; Adult; Maxilla; Middle Aged; Young Adult
PubMed: 38842718
DOI: 10.4103/njcp.njcp_220_24