Deep Network-Based Comprehensive Parotid Gland Tumor Detection.

RATIONALE AND OBJECTIVES: Salivary gland tumors constitute 2%-6% of all head and neck tumors and are most common in the parotid gland. Magnetic resonance (MR) imaging is the most sensitive imaging modality for diagnosis. Tumor type, localization, and relationship with surrounding structures are important factors for treatment. Therefore, parotid gland tumor segmentation is important. Specialists widely use manual segmentation in diagnosis and treatment. However, considering the development of artificial intelligence-based models today, it is seen that artificial intelligence-based automatic segmentation models can be used instead of manual segmentation, which is a time-consuming technique. Therefore, we segmented parotid gland tumor (PGT) using deep learning-based architectures in the paper. MATERIALS AND METHODS: The dataset used in the study includes 102 T1-w, 102 contrast-enhanced T1-w (T1C-w), and 102 T2-w MR images. After cropping the raw and manually segmented images by experts, we obtained the masks of these images. After standardizing the image sizes, we split these images into approximately 80% training set and 20% test set. Hereabouts, we trained six models for these images using ResNet18 and Xception-based DeepLab v3+. We prepared a user-friendly Graphical User Interface application that includes each of these models. RESULTS: From the results, the accuracy and weighted Intersection over Union values of the ResNet18-based DeepLab v3+ architecture trained for T1C-w, which is the most successful model in the study, are equal to 0.96153 and 0.92601, respectively. Regarding the results and the literature, it can be seen that the proposed system is competitive in terms of both using MR images and training the models independently for T1-w, T1C-w, and T2-w. Expressing that PGT is usually segmented manually in the literature, we predict that our study can contribute significantly to the literature. CONCLUSION: In this study, we prepared and presented a software application that can be easily used by users for automatic PGT segmentation. In addition to predicting the reduction of costs and workload through the study, we developed models with meaningful performance metrics according to the literature.

What Are We Missing From Asymmetric Relationship Between the Retinal Nerve Fiber Layer Thickness Profiles and Sphenoid Sinus Volume?

PURPOSE/AIM OF THE STUDY: Detailed analysis of retinal structure such as the retinal nerve fiber layer can be performed by spectral-domain optical coherence tomography (OCT). There are no published studies concerning a relationship between retinal nerve fiber layer and human sphenoid sinus volumes. We investigated this relationship. MATERIAL AND METHODS: Spectral-domain OCT. The peripapillary retinal nerve fiber layer (RNFL) thickness and sphenoid sinus volume estimation of both sides of sex-matched patients were retrospectively analyzed. RESULTS: The mean RNFL thicknesses at the left side (91.8 µm) were significantly smaller than the right side (94.5 µm) (P = 0.040). However, the mean left sinus volume (44.5 cm) is larger than the right side, (34.5 mm) (P < 0.005). Left and right differences of both parameters are statistically significant (P < 0.05). CONCLUSION: There is a negative correlation between mean RNFL thicknesses and mean sinus volumes. To our knowledge, this article is the first report demonstrating the asymmetry relationship between RNFL and sphenoid sinus volumes.

Effects of gadolinium-based contrast agents on submandibular gland tissue in rats.

AIM: The aim of this prospective animal study is to investigate the influence of multiple administrations of macrocyclic ionic (gadoteric acid) and linear nonionic (gadodiamide) gadolinium-based contrast agents (GBCA) on submandibular gland tissue (SGT) of the rats. MATERIAL AND METHOD: Twenty-four Sprague Dawley female rats were included the study. Group 1 was determined as a control group (n = 6). Group 2 was determined as saline group (n = 6). Group 3 was determined as Omniscan group (n = 6) and received only intraperitoneal (IP) 0.1 mmol (0.2 mL/kg)/kg gadodiamide for 8 days. Group 4 was determined as Dotarem group (n = 6) and received only IP 0.1 mmol (0.2 mL/kg)/mg/kg gadoteric acid daily for 8 days. On the 9th day of the administration, the rats were sedated with ketamine and xylazine through IP injection. The right SGT was removed after sedation. Histopathological and immunohistochemical changes in SGT were evaluated. RESULTS: The SGT of the Omniscan and Dotarem groups decreased SGT acini surface area, and serous acinar cells number were observed. On the other hand, no pathology was observed. Mucous acinar cells' caspase-3 positivity for the same markers in Omniscan and Dotarem sections was similar to the control group. However, Omniscan and Dotarem groups serous acinar cells were caspase-3 (+) staining. The intensity of serous acinar cells' caspase-3 (+) for the same markers in Dotarem sections was similar to the Omniscan group. The results also revealed in the analysis of the mean area of the acinus area of the SGT; there were significantly decreased Dotarem group rats when compared to control rats (p < 0.05). CONCLUSION: We consider that numerical increased apoptosis results arise from repeated doses of GBCAs. Being aware of this effect of the contrast agent may have significance for the chronic sialo-adenitis patients group when used for recurrent contrasted MRI for diagnosis of diseases like MS which requires in follow-up. We should be aware about the frequently contrasted MRI in routine investigations.

The role of HRCT versus CXR in children with recurrent pulmonary infections.

The purpose of this study is to evaluate the role of high-resolution computed tomography (HRCT) versus chest radiography (CXR) in children with recurrent respiratory infections. Fifty-one cases, aged 2 months-13 years, who had a history of recurrent respiratory infections, were examined with CXR and HRCT. HRCT showed that 16/51 of the cases had bronchiectasis. CXR revealed findings of bronchiectasis only in 5 of the 16 cases. HRCT showed peribronchial thickening in 18 cases, whereas CXR showed the same finding in 5 patients. Overall, HRCT showed the underlying pathology and sequel of pulmonary lesions in 22 out of 51 cases, and linear densities in 12. Compared with the CXR, HRCT gives much more information.