PurposeThe expression of human epidermal growth factor receptor 2 (HER2) in breast cancer is critical in the treatment with targeted therapy. A 3-block-DenseNet-based deep learning model was developed to predict the expression of HER2 in breast cancer by ultrasound images.MethodsThe data from 144 breast cancer patients with preoperative ultrasound images and clinical information were retrospectively collected from the Shandong Province Tumor Hospital. An end-to-end 3-block-DenseNet deep learning classifier was built to predict the expression of human epidermal growth factor receptor 2 by ultrasound images. The patients were randomly divided into a training (n = 108) and a validation set (n = 36).ResultsOur proposed deep learning model achieved an encouraging predictive performance in the training set (accuracy = 85.79%, AUC = 0.87) and the validation set (accuracy = 80.56%, AUC = 0.84). The effectiveness of our model significantly exceeded the clinical model and the radiomics model. The score of the proposed model showed significant differences between HER2-positive and -negative expression (p < 0.001).ConclusionsThese results demonstrate that ultrasound images are predictive of HER2 expression through a deep learning classifier. Our method provides a non-invasive, simple, and feasible method for the prediction of HER2 expression without the manual delineation of the regions of interest (ROI). The performance of our deep learning model significantly exceeded the traditional texture analysis based on the radiomics model.

Image enhancement is an important pre-processing step for various image processing applications. In this paper, we proposed a physiologically-based adaptive three-Gaussian model for image enhancement. Comparing to the standard three-Gaussian model inspired by the spatial structure of the receptive field (RF) of the retinal ganglion cells, the proposed model can dynamically adjust its parameters according to the local image luminance and contrast based on the physiological findings. Experimental results on several images show that the proposed adaptive three-Gaussian model achieves better performance than the classical method of histogram equalization and the standard three-Gaussian model.

No abstract

Minimal test cost attribute reduction is an important problem in cost-sensitive learning. Recently, heuristic algorithms including the information gain-based algorithm and the genetic algorithm have been designed for this problem. However, in many cases these algorithms cannot find the optimal solution. In this paper, we develop an ant colony optimization algorithm to tackle this problem. The attribute set is represented as a graph with each vertex corresponding to an attribute and weight of each edge to pheromone. Our algorithm contains three stages, namely, the addition stage, the deletion stage, and the filtration stage. In the addition stage, each ant starts from the initial position and traverses edges probabilistically until the stopping criterion is satisfied. The pheromone of the traveled path is also updated in this process. In the deletion stage, each ant deletes redundant attributes. Two strategies, called the centralized deletion strategy and the distributed deletion strategy, are proposed. Finally, the ant with minimal test cost is selected to construct the reduct in the filtration stage. Experimental results on UCI datasets indicate that the algorithm is significantly better than the information gain-based one. It also outperforms the genetic algorithm on medium-sized dataset Mushroom.

No abstract