Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks.

The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model.

Automatic anesthesia depth staging using entropy measures and relative power of electroencephalogram frequency bands.

Many of the surgeries performed under general anesthesia are aided by electroencephalogram (EEG) monitoring. With increased focus on detecting the anesthesia states of patients in the course of surgery, more attention has been paid to analyzing the power spectra and entropy measures of EEG signal during anesthesia. In this paper, by using the relative power of EEG frequency bands and the EEG entropy measures, a new method for detecting the depth of anesthesia states has been presented based on the least squares support vector machine (LS-SVM) classifiers. EEG signals were recorded from 20 patients before, during and after general anesthesia in the operating room at a sampling rate of 200 Hz. Then, 12 features were extracted from each EEG segment, 10 s in length, which are used for anesthesia state monitoring. No significant difference was observed (p > 0.05) between these features and the bispectral index (BIS), which is the commonly used measure of anesthetic effect. The used LS-SVM classifier based method is able to identify the anesthesia states with an accuracy of 80% with reference to the BIS index. Since the underlying equation of the utilized LS-SVM is linear, the computational time of the algorithm is not significant and therefore it can be used for online application in operation rooms.

A novel approach for quantification and analysis of the color Doppler twinkling artifact with application in noninvasive surface roughness characterization: an in vitro phantom study.

OBJECTIVES: The twinkling artifact is an undesired phenomenon within color Doppler sonograms that usually appears at the site of internal calcifications. Since the appearance of the twinkling artifact is correlated with the roughness of the calculi, noninvasive roughness estimation of the internal stones may be considered as a potential twinkling artifact application. This article proposes a novel quantitative approach for measurement and analysis of twinkling artifact data for roughness estimation. METHODS: A phantom was developed with 7 quantified levels of roughness. The Doppler system was initially calibrated by the proposed procedure to facilitate the analysis. A total of 1050 twinkling artifact images were acquired from the phantom, and 32 novel numerical measures were introduced and computed for each image. The measures were then ranked on the basis of roughness quantification ability using different methods. The performance of the proposed twinkling artifact-based surface roughness quantification method was finally investigated for different combinations of features and classifiers. RESULTS: Eleven features were shown to be the most efficient numerical twinkling artifact measures in roughness characterization. The linear classifier outperformed other methods for twinkling artifact classification. The pixel count measures produced better results among the other categories. The sequential selection method showed higher accuracy than other individual rankings. The best roughness recognition average accuracy of 98.33% was obtained by the first 5 principle components and the linear classifier. CONCLUSIONS: The proposed twinkling artifact analysis method could recognize the phantom surface roughness with average accuracy of 98.33%. This method may also be applicable for noninvasive calculi characterization in treatment management.