Background: Distinguishing benign inverted papilloma (IP) tumors from those that have undergone malignant transformation to squamous cell carcinoma (IP-SCC) is important but challenging to do preoperatively. Magnetic resonance imaging (MRI) can help differentiate these 2 entities, but no established method exists that can automatically synthesize all potentially relevant MRI image features to distinguish IP and IP-SCC. We explored a deep learning approach, using 3-dimensional convolutional neural networks (CNNs), to address this challenge.Methods: Retrospective chart reviews were performed at 2 institutions to create a data set of preoperative MRIs with corresponding surgical pathology reports.The MRI data set included all available MRI sequences in the axial plane, which were used to train, validate, and test 3 CNN models. Saliency maps were generated to visualize areas of MRIs with greatest influence on predictions. Results: A total of 90 patients with IP (n = 64) or IP-SCC (n = 26) tumors were identified, with a total of 446 images of distinct MRI sequences for IP (n = 329) or IP-SCC (n = 117). The best CNN model, All-Net, demonstrated a sensitivity of 66.7%, specificity of 81.5%, overall accuracy of 77.9%, and receiver-operating characteristic area under the curve of 0.80 (95% confidence interval, 0.682-0.898) for test classification performance. The other 2 models, Small-All-Net and Elastic-All-Net, showed similar performance levels. Conclusion:A deep learning approach with 3-dimensional CNNs can distinguish IP and IP-SCC with moderate test classification performance. Although CNNs demonstrate promise to enhance the prediction of IP-SCC using MRIs, more data are needed before they can reach the predictive value already established by human MRI evaluation.
Background: Craniopharyngiomas have traditionally been treated via open transcranial approaches. More recent, endoscopic endonasal approaches have been increasingly used; however, there has been limited evaluation of long-term outcomes for this approach. Methods: A retrospective review was performed to analyze patients with pediatric craniopharyngioma undergoing endonasal endoscopic resection from 2012 to 2020. Demographic information, clinicopathologic factors, and outcomes including follow-up and recurrences were analyzed. Results: All 42 patients, with a mean age of 8.0 years, were included. The median follow-up time was 49 months. Mean tumor diameter was 3.6 cm. All of the tumors had sellar and suprasellar components. The most common presenting symptoms were headaches (64.3%), visual changes (59.5%), and nausea/vomiting (38.1%). Most patients (73.3%) had resolution of their presenting symptoms by their first postoperative visit. Vision improved or remained normal in 69.0% of patients. Postoperatively, incidence of panhypopituitarism or diabetes insipidus developed in 89.7% and 77.8% of patients, respectively. The postoperative cerebrospinal fluid leak rate was 7.1%. The recurrence rate was 9.5%. Conclusion: Endoscopic endonasal resection for pediatric craniopharyngiomas can achieve high rates of resection with low rates of disease recurrence when compared with the outcomes of open transcranial resection reported in the literature. However, hypothalamic-pituitary dysfunction remains a significant postoperative morbidity in both approaches.
Background Orbital, intracranial, and osseous extra-sinus complications can arise from bacterial or fungal sinusitis. Odontogenic sinusitis (ODS) can cause extra-sinus complications, but its prevalence remains poorly characterized. Objective To determine the frequency of ODS as a cause of operative extra-sinus infectious complications and describe clinical features of all complicated sinusitis cases. Methods A multi-institutional retrospective review was performed on all operative sinusitis-related extra-sinus complications from 2011 to 2020. ODS was diagnosed by sinus computed tomography (CT) and dental evaluations when available. Demographics, complication types, sinusitis etiologies, and various clinical features were analyzed. Results Forty-five patients were included (mean age 55.5 years, 56% male). Of the extra-sinus complications, 40% were orbital only, 22% intracranial only, 13% osseous only, and 25% involved combined complications. The 2 most common causes of extra-sinus complications were ODS (40%) and mucopyocele (27%). When invasive fungal etiologies were excluded, and only unilateral maxillary opacification on CT was considered, nearly 60% of extra-sinus complications were due to ODS. Unilateral maxillary sinus opacification on CT was present in 100% of complicated ODS compared to 44% of nonodontogenic cases, and oral anaerobes were only identified in ODS cases. No complicated ODS patients underwent dental interventions during hospitalization. Conclusion ODS was the most common cause of operative extra-sinus infectious complications. Clinicians should consider ODS high on the differential diagnosis of all patients presenting with complicated sinusitis, especially when sinusitis is unilateral and invasive fungal infection is not suspected.
Background: Aspirin exacerbated respiratory disease (AERD) is an inflammatory condition that consists of eosinophilic asthma, chronic rhinosinusitis with nasal polyps, and respiratory reactions to cyclooxygenase-1 inhibitors. Aspirin therapy after aspirin desensitization (ATAD) is the most extensively studied treatment paradigm for AERD. Objective: The objective was to identify which time point of ATAD was most predictive of long-term outcomes as measured by the 22-item Sino-Nasal Outcome Test (SNOT-22). Methods: A retrospective chart review was conducted of patients at a single institution who underwent endoscopic sinus surgery, followed by ATAD, and had remained on ATAD for 2 consecutive years. SNOT-22 scores were recorded at predesensitization as well as at the 3-, 6-, 12-, and 24-month postdesensitization time points. The patients were separated into two cohorts at each of the data collection time points based on whether their SNOT-22 scores were < 20 (responders) or ≥ 20 (nonresponders). Responder status was compared between each time point and at 24-month postdesensitization. The odds ratios (OR) were then calculated between the two groups at each of the following time points: postsurgery/predesensitization, and 3-, 6-, and 12-month postdesensitization. Results: There were 70 patients who met the inclusion criteria of having 24-month postdesensitization SNOT-22 scores available. Responder status at 6 months after surgery had the most predictive OR 16.5 (95% confidence interval, 3.71‐73.44) for long-term outcomes at 24 months. Conclusion: The SNOT-22 scores after 6 months of ATAD showed the greatest predictive value for long-term quality-of-life outcomes and, therefore, poor 6-month SNOT-22 scores could serve as a basis for consideration of alternative therapies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.