Volume measurements of maxillary sinus may be useful to identify diseases affecting paranasal sinuses. However, literature shows a lack of consensus in studies measuring the volume. This may be attributable to different computed tomography data acquisition techniques, segmentation methods, focuses of investigation, among other reasons. Furthermore, methods for volumetrically quantifying the maxillary sinus are commonly manual or semiautomated, which require substantial user expertise and are time-consuming. The purpose of the present study was to develop an automated tool for quantifying the total and air-free volume of the maxillary sinus based on computed tomography images. The quantification tool seeks to standardize maxillary sinus volume measurements, thus allowing better comparisons and determinations of factors that influence maxillary sinus size. The automated tool utilized image processing techniques (watershed, threshold, and morphological operators). The maxillary sinus volume was quantified in 30 patients. To evaluate the accuracy of the automated tool, the results were compared with manual segmentation that was performed by an experienced radiologist using a standard procedure. The mean percent differences between the automated and manual methods were 7.19% ± 5.83% and 6.93% ± 4.29% for total and air-free maxillary sinus volume, respectively. Linear regression and Bland-Altman statistics showed good agreement and low dispersion between both methods. The present automated tool for maxillary sinus volume assessment was rapid, reliable, robust, accurate, and reproducible and may be applied in clinical practice. The tool may be used to standardize measurements of maxillary volume. Such standardization is extremely important for allowing comparisons between studies, providing a better understanding of the role of the maxillary sinus, and determining the factors that influence maxillary sinus size under normal and pathological conditions.

Background: Neuroimaging strategies are essential to locate, to elucidate the etiology, and to the follow up of brain disease patients. Magnetic resonance imaging (MRI) provides good cerebral soft-tissue contrast detection and diagnostic sensitivity. Inflammatory lesions and tumors are common brain diseases that may present a similar pattern of a cerebral ring enhancing lesion on MRI, and non-enhancing core (which may reflect cystic components or necrosis) leading to misdiagnosis. Texture analysis (TA) and machine learning approaches are computer-aided diagnostic tools that can be used to assist radiologists in such decisions. Methods: In this study, we combined texture features with machine learning (ML) methods aiming to differentiate brain tumors from inflammatory lesions in magnetic resonance imaging. Retrospective examination of 67 patients, with a pattern of a cerebral ring enhancing lesion, 30 with inflammatory, and 37 with tumoral lesions were selected. Three different MRI sequences and textural features were extracted using gray level co-occurrence matrix and gray level run length. All diagnoses were confirmed by histopathology, laboratorial analysis or MRI. Results: The features extracted were processed for the application of ML methods that performed the classification. T1-weighted images proved to be the best sequence for classification, in which the differentiation between inflammatory and tumoral lesions presented high accuracy (0.827), area under ROC curve (0.906), precision (0.837), and recall (0.912). Conclusion: The algorithm obtained textures capable of differentiating brain tumors from inflammatory lesions, on T1-weghted images without contrast medium using the Random Forest machine learning classifier.