Reduced Deep Convolutional Activation Features (R-DeCAF) in Histopathology Images to Improve the Classification Performance for Breast Cancer Diagnosis.

Breast cancer is the second most common cancer among women worldwide, and the diagnosis by pathologists is a time-consuming procedure and subjective. Computer-aided diagnosis frameworks are utilized to relieve pathologist workload by classifying the data automatically, in which deep convolutional neural networks (CNNs) are effective solutions. The features extracted from the activation layer of pre-trained CNNs are called deep convolutional activation features (DeCAF). In this paper, we have analyzed that all DeCAF features are not necessarily led to higher accuracy in the classification task and dimension reduction plays an important role. We have proposed reduced DeCAF (R-DeCAF) for this purpose, and different dimension reduction methods are applied to achieve an effective combination of features by capturing the essence of DeCAF features. This framework uses pre-trained CNNs such as AlexNet, VGG-16, and VGG-19 as feature extractors in transfer learning mode. The DeCAF features are extracted from the first fully connected layer of the mentioned CNNs, and a support vector machine is used for classification. Among linear and nonlinear dimensionality reduction algorithms, linear approaches such as principal component analysis (PCA) represent a better combination among deep features and lead to higher accuracy in the classification task using a small number of features considering a specific amount of cumulative explained variance (CEV) of features. The proposed method is validated using experimental BreakHis and ICIAR datasets. Comprehensive results show improvement in the classification accuracy up to 4.3% with a feature vector size (FVS) of 23 and CEV equal to 0.15.

A fast model of voltage-dependent NMDA receptors.

NMDA receptors are among the crucial elements of central nervous system models. Recent studies show that both conductance and kinetics of these receptors are changing voltage-dependently in some parts of the brain. Therefore, several models have been introduced to simulate their current. However, on the one hand, kinetic models-which are able to simulate these voltage-dependent phenomena-are computationally expensive for modeling of large neural networks. On the other hand, classic exponential models, which are computationally less expensive, are not able to simulate the voltage-dependency of these receptors, accurately. In this study, we have modified these classic models to endow them with the voltage-dependent conductance and time constants. Temperature sensitivity and desensitization of these receptors are also taken into account. We show that, it is possible to simulate the most important physiological aspects of NMDA receptor's behavior using only three to four differential equations, which is significantly smaller than the previous kinetic models. Consequently, it seems that our model is both fast and physiologically plausible and therefore is a suitable candidate for the modeling of large neural networks.