Automatic retinal vessel segmentation is important for the diagnosis and prevention of ophthalmic diseases. The existing deep learning retinal vessel segmentation models always treat each pixel equally. However, the multi-scale vessel structure is a vital factor affecting the segmentation results, especially in thin vessels. To address this crucial gap, we propose a novel Fully Attention-based network (FANet) based on attention mechanisms to adaptively learn rich feature representation and aggregate the multi-scale information. Specifically, the framework consists of the image pre-processing procedure and the semantic segmentation networks. Green channel extraction (GE) and contrast limited adaptive histogram equalization (CLAHE) are employed as pre-processing to enhance the texture and contrast of retinal blood images. Besides, the network combines two types of attention modules with the U-Net. We propose a lightweight dual-direction attention block to model global dependencies and reduce intra-class inconsistencies, in which the weights of feature maps are updated based on the semantic correlation between pixels. The dual-direction attention block utilizes horizontal and vertical pooling operations to produce the attention map. In this way, the network aggregates global contextual information from semantic-closer regions or a series of pixels belonging to the same object category. Meanwhile, we adopt the selective kernel(SK) unit to replace the standard convolution for obtaining multi-scale features of different receptive field sizes generated by soft attention. Furthermore, we demonstrate that the proposed model can effectively identify irregular, noisy, and multi-scale retinal vessels. The abundant experiments on DRIVE, STARE, and CHASE_DB1 datasets show that our method achieves state-of-the-art performance.

Atrial fibrillation (AF), a common abnormal heartbeat rhythm, is a life-threatening recurrent disease that affects older adults. Automatic classification is one of the most valuable topics in medical sciences and bioinformatics, especially the detection of atrial fibrillation. However, it is difficult to accurately explain the local characteristics of electrocardiogram (ECG) signals by manual analysis, due to their small amplitude and short duration, coupled with the complexity and non-linearity. Hence, in this paper, we propose a novel deep arrhythmia-diagnosis method named deep CNN-BLSTM network model to automatically detect the AF heartbeats using ECG signals. The model mainly consists of four convolution layers, two BLSTM layers, and two fully connected layers. The datasets of RR intervals (called set A.) and heartbeat sequences (P-QRS-T waves, called set B.) are fed into above-mentioned model. Most importantly, our proposed approach achieved favorable performances with an accuracy of 99.94%, 98.63% in the training and validation set of set A, respectively. In the testing set (unseen data sets), we obtained an accuracy of 96.59%, a sensitivity of 99.93%, and a specificity of 97.03%. To the best of our knowledge, the algorithm we proposed has shown excellent results comparing to many state-of-art researches, which provides a new solution for AF automatic detection.

Generating vivid and diverse 3D co-speech gestures is crucial for various applications in animating virtual avatars. While most existing methods can generate gestures from audio directly, they usually overlook that emotion is one of the key factors of authentic co-speech gesture generation. In this work, we propose EmotionGesture , a novel framework for synthesizing vivid and diverse emotional co-speech 3D gestures from audio. Considering emotion is often entangled with the rhythmic beat in speech audio, we first develop an Emotion-Beat Mining module (EBM) to extract the emotion and audio beat features as well as model their correlation via a transcript-based visual-rhythm alignment. Then, we propose an initial pose based Spatial-Temporal Prompter (STP) to generate future gestures from the given initial poses. STP effectively models the spatial-temporal correlations between the initial poses and the future gestures, thus producing the spatial-temporal coherent pose prompt. Once we obtain pose prompts, emotion, and audio beat features, we will generate 3D co-speech gestures through a transformer architecture. However, considering the poses of existing datasets often contain jittering effects, this would lead to generating unstable gestures. To address this issue, we propose an effective objective function, dubbed Motion-Smooth Loss. Specifically, we model motion offset to compensate for jittering ground-truth by forcing gestures to be smooth. Last, we present an emotion-conditioned VAE to sample emotion features, enabling us to generate diverse emotional results. Extensive experiments demonstrate that our framework outperforms the state-of-the-art, achieving vivid and diverse emotional co-speech 3D gestures. Our code and dataset will be released on the project page: https://xingqunqi-lab.github.io/Emotion-Gesture-Web/

Automatic gastric cancer segmentation is a challenging problem in digital pathology image analysis. Accurate segmentation of gastric cancer regions can efficiently facilitate clinical diagnosis and pathological research. Technically, this problem suffers from various sizes, vague boundaries, and the nonrigid characters of cancerous regions. For addressing these challenges, we use a deep learning based method and integrate several customized modules. Structurally, we replace the basic form of convolution with deformable and Atrous convolutions in specific layers, for adapting to the non-rigid characters and larger receptive field. We take advantage of the Atrous Spatial Pyramid Pooling module and encoder-decoder based semantic-level embedding networks for multi-scale segmentation. Additionally, we propose a lightweight decoder to fuse the contexture information, and utilize the Dense Upsampling Convolution for boundary refinement at the end of the decoder. Experimentally, sufficient comparative experiments are enforced on our own gastric cancer segmentation dataset, which is delicately annotated to pixel-level by medical specialists. Quantitative comparisons against several prior methods demonstrate the superiority of our approach. We achieve 91.60% for pixel-level accuracy and 82.65% for mean Intersection over Union.

Support Vector Machine and Softmax are two widely used linear classifiers in computer vision. Especially in the field of deep learning algorithms, the application of these two classifiers is more frequent. In addition, in the field of statistics, speech recognition, character recognition and other aspects that Support Vector Machine and Softmax also have been used. However, there are still some controversies of these two classifiers in the specific implementations. And the understanding of them comes to a significance place in deep learning process. This paper will make a comparison and analysis of the two classifiers from a holistic perspective to help the reader have a more comprehensive understanding of the two classifiers.

Remote sensing image segmentation is a challenging task in remote sensing image analysis. Remote sensing image segmentation has great significance in urban planning, crop planting, and other fields that need plentiful information about the land. Technically, this task suffers from the ultra-high resolution, large shooting angle, and feature complexity of the remote sensing images. To address these issues, we propose a deep learning-based network called ATD-LinkNet with several customized modules. Specifically, we propose a replaceable module named AT block using multi-scale convolution and attention mechanism as the building block in ATD-LinkNet. AT block fuses different scale features and effectively utilizes the abundant spatial and semantic information in remote sensing images. To refine the nonlinear boundaries of internal objects in remote sensing images, we adopt the dense upsampling convolution in the decoder part of ATD-LinkNet. Experimentally, we enforce sufficient comparative experiments on two public remote sensing datasets (Potsdam and DeepGlobe Road Extraction). The results show our ATD-LinkNet achieves better performance against most state-of-the-art networks. We obtain 89.0% for pixel-level accuracy in the Potsdam dataset and 62.68% for mean Intersection over Union in the DeepGlobe Road Extraction dataset.