Vessel segmentation is critical for disease diagnosis and surgical planning. Recently, the vessel segmentation method based on deep learning has achieved outstanding performance. However, vessel segmentation remains challenging due to thin vessels with low contrast that easily lose spatial information in the traditional U-shaped segmentation network. To alleviate this problem, we propose a novel and straightforward full-resolution network (FR-UNet) that expands horizontally and vertically through a multiresolution convolution interactive mechanism while retaining full image resolution. In FR-UNet, the feature aggregation module integrates multiscale feature maps from adjacent stages to supplement high-level contextual information. The modified residual blocks continuously learn multiresolution representations to obtain a pixel-level accuracy prediction map. Moreover, we propose the dual-threshold iterative algorithm (DTI) to extract weak vessel pixels for improving vessel connectivity. The proposed method was evaluated on retinal vessel datasets (DRIVE, CHASE_DB1, and STARE) and coronary angiography datasets (DCA1 and CHUAC). The results demonstrate that FR-UNet outperforms state-of-the-art methods by achieving the highest Sen, AUC, F1, and IOU on most of the above-mentioned datasets with fewer parameters, and that DTI enhances vessel connectivity while greatly improving sensitivity. The code is available at: https://github.com/lseventeen/FR-UNet .

Multispectral pedestrian detection, which consists of a color stream and thermal stream, is essential under conditions of insufficient illumination because the fusion of the two streams can provide complementary information for detecting pedestrians based on deep convolutional neural networks (CNNs). In this paper, we introduced and adapted a simple and efficient one-stage YOLOv4 to replace the current state-of-the-art two-stage fast-RCNN for multispectral pedestrian detection and to directly predict bounding boxes with confidence scores. To further improve the detection performance, we analyzed the existing multispectral fusion methods and proposed a novel multispectral channel feature fusion (MCFF) module for integrating the features from the color and thermal streams according to the illumination conditions. Moreover, several fusion architectures, such as Early Fusion, Halfway Fusion, Late Fusion, and Direct Fusion, were carefully designed based on the MCFF to transfer the feature information from the bottom to the top at different stages. Finally, the experimental results on the KAIST and Utokyo pedestrian benchmarks showed that Halfway Fusion was used to obtain the best performance of all architectures and the MCFF could adapt fused features in the two modalities. The log-average miss rate (MR) for the two modalities with reasonable settings were 4.91% and 23.14%, respectively.

Cell (nuclei) segmentation is the basic and key step of pathological image analysis. However, robust and accurate cell (nuclei) segmentation is a difficult problem due to the enormous variability of staining, cell sizes, morphologies and cell adhesion or overlapping. In this paper, we extend U-Net with atrous depthwise separable convolution (AS-UNet) for cell (nuclei) segmentation. AS-UNet consists of three parts: encoder module, decoder module and atrous convolution module. The encoder module obtains the high-level semantic information of the cell image layer by layer, while the decoder module gradually recovers the spatial information. The atrous convolution module is composed of cascade and parallel atrous convolution operations. It can extract and combine multi-scale features so that the model can get strong perception ability for both small and large cells. At the same time, the atrous convolution can significantly increase the receptive field of the network model without hurting the segmentation performance or increasing the computational cost. During the training period, Log-Dice loss and Focal loss are combined, while Adam optimization method is employed to optimize the network. In order to increase the penalty for the smaller prediction result of the Dice coefficient, which is carried out by logarithmic operation and the negative value is taken as the Log-Dice loss. The above optimization is beneficial for the convergence speed. Additionally, some data augmentation techniques are applied to increase online data, which contribute to improving the robustness of the model. Compared with several state-of-the-art semantic segmentation algorithms, our method achieves the promising performance on two latest released pathological image datasets.