Color prediction of layered dental resin composites with varying thickness.

OBJECTIVE: The aim of this study was to assess the accuracy of a Principal Components Analysis (PCA)-based method for reflectance reconstruction and color estimation of layered dental resin-based composites with different thicknesses. METHOD: Bi-layered samples of different clinically relevant thicknesses were created using shades of VITAPAN Excell (VE), VITAPAN Dentine (VD) and VITA Physiodens (VP), combined with their corresponding enamel shades. Spectral reflectance of all samples was measured over a black background using a non-contact spectroradiometer with CIE 45∘∕0∘ geometry. Two different PCA-based models, built from two different configurations of known samples, were proposed to reconstruct the spectral data and color of unknown layered samples. Root Mean Square Error (RMSE), Goodness of Fit (GFC), as well as ΔE00 with corresponding 50:50% acceptability and perceptibly thresholds (AT and PT) were used as performance assessment. RESULTS: The 5-samples training set approach provided an average RMSE < 0.015 and GFC > 0.999 when measured and predicted spectral reflectances were compared, while for the 9-samples training set, RMSE < 0.0098 and GFC > 0.9999 were obtained. The overall mean color differences obtained with the 5-samples training set approach were ΔE00 = 0.99 (AT% = 96.25% and PT% = 32.50%), while using the 9-samples training set resulted in lower overall mean color differences: ΔE00 = 0.50 (AT% = 99.22% and PT% = 83.87%). SIGNIFICANCE: Within the framework of this study, the two proposed PCA-based configurations allow the prediction of the spectral reflectance of layered dental resin-based composites of different shades and thicknesses, with a high degree of accuracy.

Combination of heterogeneous EEG feature extraction methods and stacked sequential learning for sleep stage classification.

This work proposes a methodology for sleep stage classification based on two main approaches: the combination of features extracted from electroencephalogram (EEG) signal by different extraction methods, and the use of stacked sequential learning to incorporate predicted information from nearby sleep stages in the final classifier. The feature extraction methods used in this work include three representative ways of extracting information from EEG signals: Hjorth features, wavelet transformation and symbolic representation. Feature selection was then used to evaluate the relevance of individual features from this set of methods. Stacked sequential learning uses a second-layer classifier to improve the classification by using previous and posterior first-layer predicted stages as additional features providing information to the model. Results show that both approaches enhance the sleep stage classification accuracy rate, thus leading to a closer approximation to the experts' opinion.

Primary embryonal rhabdomyosarcoma of the breast in an adolescent female: a case report.

Rhabdomyosarcoma is the most common soft tissue sarcoma in children. Primary breast location has been reported rarely in the literature. Most rhabdomyosarcomas encountered in the breast more commonly are metastatic disease from some primary foci in another part of the body. This report addresses the case of an adolescent girl who had primary embryonal rhabdomyosarcoma of the breast with no evidence of local invasion or metastatic disease within the spectrum of Li-Fraumeni syndrome.