Automated methods for sella turcica segmentation on cephalometric radiographic data using deep learning (CNN) techniques.

OBJECTIVE: The objective of this work is to present a novel technique using convolutional neural network (CNN) architectures for automatic segmentation of sella turcica (ST) on cephalometric radiographic image dataset. The proposed work suggests possible deep learning approaches to distinguish ST on complex cephalometric radiographs using deep learning techniques. MATERIALS AND METHODS: The dataset of 525 lateral cephalometric images was employed and randomly split into different training and testing subset ratios. The ground truth (annotated images) represents pixel-wise annotation of the ST using an online annotation platform by dental specialists. This study compared convolutional neural network architectures based on fine-tuned versions of the VGG19, ResNet34, InceptionV3, and ResNext50 architectures to select an appropriate model for autonomous segmentation of the nonlinear structure of ST. RESULTS: The study compared training and prediction results of the selected models: VGG19, ResNet34, InceptionV3, and ResNext50. The mean IoU scores for VGG19, ResNet34, InceptionV3 and ResNext50 are 0.7651, 0.7241, 0.4717, 0.4287, dice coefficients are 0.7794, 0.7487, 0.4714, 0.4363 and loss scores are 0.0973, 0.1299, 0.2049 and 0.2251, respectively. CONCLUSION: The obtained findings suggest that the VGG19 and Resnet34 architectures (mean IoU and dice coefficient > 75%) comparatively outperformed the InceptionV3 and ResNext50 architectures (mean IoU and dice coefficients is around 45%) for considered cephalometric radiographic dataset. The study findings can be used as a reference model for future investigation of non-linear ST morphological characteristics and related biological anomalies.

Successful perioperative management of three patients with hereditary angioedema without C1 esterase inhibitor therapy: A developing country perspective.

BACKGROUND: Hereditary angioedema (HAE) is a rare inherited disorder characterized by sudden and unpredictable appearance of swelling. Surgical procedures, even minor ones, are known to precipitate an attack in these patients. C1 esterase inhibitor (C1-INH) therapy may be effective for short term prophylaxis in such situations. However, there is limited experience with short term prophylaxis in countries where C1-INH therapy is not available. METHODS: To report our experience of using short term prophylaxis for a dental procedure, a Cesarean section and a major hip surgery in one patient each with HAE in resource constrained settings. RESULTS: All 3 patients were given FFP before and during the procedure. While the first (a 6-year-old girl) and third patient (a 60-year-old male) were already taking stanozolol and the dose was doubled 5 days before the surgery, the second patient (28-year-old woman) was not taking any prophylaxis and she was initiated on stanozolol on the day of Cesarean section. The first patient was also given additional FFP one day after the dental procedure. After the procedure, the dose of stanozolol was decreased to baseline in patient 1 and 3 while it was discontinued in patient 3. All 3 patients tolerated the procedures well and had no related episodes of angioedema. CONCLUSIONS: Dental and other major surgical procedures in patients with HAE are known to precipitate an episode of angioedema. In countries where C1-INH therapy is not available, attenuated androgens and FFP may be used to prevent these episodes.

Awareness among pediatricians regarding oral health care in children including those with special health care needs: A cross- sectional survey.

BACKGROUND: Pediatricians are the custodians of the overall health of children and are the ideal healthcare personnel to impart information and instruction about oral health care. The aim of this survey was to evaluate awareness of pediatricians regarding oral health care and prevention of oral diseases in children. METHODOLOGY: The study participants consist of 102 young pediatricians working as Junior and Senior Residents. A questionnaire was formulated to evaluate their knowledge about oral diseases and their prevention. The questionnaire also tested the attitude and practices of pediatricians towards oral health of children with special health care needs. RESULTS: Majority of the pediatricians had correct knowledge about dental caries (60%), bottle feeding (88.2%), tongue cleaning (83.3%) and medication causing gum enlargement (92.2%). Few had correct knowledge about recommended age to start tooth brushing (35.3%) and maximum recommended sugar exposures per day (35.3%). Although, majority (62.7%) had correct knowledge about fluoride and its role caries prevention, very few (2.9%) knew about recommended fluoride concentration in toothpaste for children. CONCLUSION: There was a lack of knowledge amongst pediatrician about oral health care, prevention, and appropriate referral. The study result necessitates the emphasis of improving oral health related knowledge among pediatrician.

Congenital granular cell tumor of the newborn - Spontaneous regression or early surgical intervention.

Congenital granular cell tumor of the newborn is a benign, relatively innocuous hamartomatous lesion arising from the alveolar ridge. Large lesions often warrant prompt surgical removal owing to the associated difficulty in breastfeeding and respiration of the infant. However, for medium-sized lesions, another approach could be observed for spontaneous regression. The present case report highlights the use of a combination approach for management of tumor in a 2-day-old female child presenting with a large protruding mass from the mouth associated with difficulty in breastfeeding. A combination of observation for regression in size followed by electrosurgical removal of the tumor was done. The infant was followed up regularly over a long period of 3 years to assess any adverse effects of surgical intervention on the maxillary primary anterior dentition of which none were recorded.