Abstract:Deep learning techniques have successfully been employed in numerous computer vision tasks including image segmentation. The techniques have also been applied to medical image segmentation, one of the most critical tasks in computer-aided diagnosis. Compared with natural images, the medical image is a gray-scale image with low-contrast (even with some invisible parts). Because some organs have similar intensity and texture with neighboring organs, there is usually a need to refine automatic segmentation results. In this paper, we propose an interactive deep refinement framework to improve the traditional semantic segmentation networks such as U-Net and fully convolutional network. In the proposed framework, we added a refinement network to traditional segmentation network to refine the segmentation results.Experimental results with public dataset revealed that the proposed method could achieve higher accuracy than other state-of-the-art methods.
Abstract:In recent years, intravital skin imaging has been used in mammalian skin research for the investigation of cell behaviors. The mitotic cell (cell division) detection is a fundamental step of the investigation. Due to the complex backgrounds (normal cells), most of the existing methods bring a lot of false positives. In this paper, we proposed a 2.5 dimensional (2.5D) cascaded end-to-end network (CasDetNet_LSTM) for accurate automatic mitotic cell detection in 4D microscopic images with fewer training data. The CasDetNet_LSTM consists of two 2.5D networks. The first one is a 2.5D fast region-based convolutional neural network (2.5D Fast R-CNN), which is used for the detection of candidate cells with only volume information and the second one is a long short-term memory (LSTM) network embedded with temporal information, which is used for reduction of false positive and retrieving back those mitotic cells that missed in the first step. The experimental results shown that our CasDetNet_LSTM can achieve higher precision and recall comparing to other state-of-the-art methods.