Prediction of Radiation-Related Dental Caries Through PyRadiomics Features and Artificial Neural Network on Panoramic Radiography.

The prediction and detection of radiation-related caries (RRC) are crucial to manage the side effects of the head and the neck cancer (HNC) radiotherapy (RT). Despite the demands for the prediction of RRC, no study proposes and evaluates a prediction method. This study introduces a method based on artificial intelligence neural network to predict and detect either regular caries or RRC in HNC patients under RT using features extracted from panoramic radiograph. We selected fifteen HNC patients (13 men and 2 women) to analyze, retrospectively, their panoramic dental images, including 420 teeth. Two dentists manually labeled the teeth to separate healthy and teeth with either type caries. They also labeled the teeth by resistant and vulnerable, as predictive labels telling about RT aftermath caries. We extracted 105 statistical/morphological image features of the teeth using PyRadiomics. Then, we used an artificial neural network classifier (ANN), firstly, to select the best features (using maximum weights) and then label the teeth: in caries and non-caries while detecting RRC, and resistant and vulnerable while predicting RRC. To evaluate the method, we calculated the confusion matrix, receiver operating characteristic (ROC), and area under curve (AUC), as well as a comparison with recent methods. The proposed method showed a sensibility to detect RRC of 98.8% (AUC = 0.9869) and to predict RRC achieved 99.2% (AUC = 0.9886). The proposed method to predict and detect RRC using neural network and PyRadiomics features showed a reliable accuracy able to perform before starting RT to decrease the side effects on susceptible teeth.

Constancy checks of HDR well-type ionization chambers in the linac era: Potential use of a 90Sr source.

A methodology using a90Sr source, originally designed for constancy checks of parallel-plate ionization chambers, was proposed for constancy checks of HDR brachytherapy well-type ionization chamber (WTIC). The 90Sr source was positioned on the top of the WTIC, a reference reading value was established, and the constancy variation was calculated by the difference between each subsequent measurement and the reference value. This methodology was validated by calibrated 192Ir sources measurements and an acceptable tolerance limit for constancy variation of 1.5% was suggested.

Análise do esvaziamento do compartimento central profilático em pacientes submetidos à tireoidectomia total por carcinoma papillífero de tireoide / Prophylatic central compartment lymph node ressection analysis in patients submitted to total thyroidectomy for papillary thyroid carcinoma

Introdução: O câncer da tireoide é o mais comum da regiãoda cabeça e pescoço e destes o carcinoma papilífero é o maisprevalente. Objetivo: Analisar as complicações em pacientessubmetidos à tireoidectomia total e esvaziamento cervical donível VI por carcinoma papilífero de tireoide N0 e comparálascom pacientes que foram submetidos somente à tireoidectomiatotal. Método: Análise retrospectiva de pacientes operadosno período de Janeiro de 2001 à Setembro de 2011. Ospacientes foram divididos em dois grupos, um grupo que foisubmetido a tireoidectomia total com esvaziamento do nívelVI e o outro submetido somente a tireoidectomia total. Osgrupos foram comparados em relação à presença de disfonia,hipoparatireoidismo e recidiva, pelo teste exato de Fischer.Resultados: Apresentaram disfonia 9 pacientes, sendo destes,66,7% com esvaziamento e 33,3% sem esvaziamento (p = 0,333).O hipoparatiroidismo ocorreu em 19 pacientes, dos quais 84,2%fizeram esvaziamento e 15,8% não (p = 0,316). A recidiva ocorreuem 10 pacientes, dos quais 70% fizeram esvaziamento e 30%não (p = 0,406). Pela análise univariada não houve significânciaestatística entre os grupos para recidiva. Conclusão: Oesvaziamento cervical do nível VI é um procedimento seguro quenão aumenta as complicações.