Image segmentation is a basic technology in the field of image processing and computer vision. Medical image segmentation is an important application field of image segmentation and plays an increasingly important role in clinical diagnosis and treatment. Deep learning has made great progress in medical image segmentation. In this paper, we proposed Residual-Attention UNet++, which is an extension of the UNet++ model with a residual unit and attention mechanism. Firstly, the residual unit improves the degradation problem. Secondly, the attention mechanism can increase the weight of the target area and suppress the background area irrelevant to the segmentation task. Three medical image datasets such as skin cancer, cell nuclei, and coronary artery in angiography were used to validate the proposed model. The results showed that the Residual-Attention UNet++ achieved superior evaluation scores with an Intersection over Union (IoU) of 82.32%, and a dice coefficient of 88.59% with the skin cancer dataset, a dice coefficient of 85.91%, and an IoU of 87.74% with the cell nuclei dataset and a dice coefficient of 72.48%, and an IoU of 66.57% with the angiography dataset.

Retinal vascular segmentation is very important for diagnosing fundus diseases. However, the existing methods of retinal vascular segmentation have some problems, such as low microvascular segmentation and wrong segmentation of pathological information. To solve these problems, we developed a fundus retinal vessels segmentation based on the improved deep learning U-Net model. First, enhance the retinal images. Second, add the residual module in the process of designing the network structure, which solved the problem of the traditional deep learning U-Net model is not deep enough. By using the improved deep learning U-Net model, it can connect the output of the convolutional layer with the output of the deconvolution layer to avoid low-level information sharing, and solved the problem of performance degradation of deep convolutional neural networks in residual networks under extreme depth conditions. By verifying on the DRIVE (digital retinal images for vessel extraction) dataset, the segmentation accuracy, sensitivity, and specificity of the proposed method are 96.50%, 93.1%, and 98.63% respectively.

Object detection in the process of driving is a convenient and efficient task. However, due to the complex transformation of the road environment and vehicle speed, the scale of the target will not only change significantly but also be accompanied by the phenomenon of motion blur, which will have a significant impact on the detection accuracy. In practical application scenarios, it is difficult for traditional methods to simultaneously take into account the need for real-time detection and high accuracy. To address the above problems, this study proposes an improved network based on YOLOv5, taking traffic signs and road cracks as detection objects and conducting separate research. This paper proposes a GS-FPN structure to replace the original feature fusion structure for road cracks. This structure integrates the convolutional block attention model (CBAM) based on bidirectional feature pyramid networks (Bi-FPN) and introduces a new lightweight convolution module (GSConv) to reduce the information loss of the feature map, enhance the expressive ability of the network, and ultimately achieve improved recognition performance. For traffic signs, a four-scale feature detection structure is used to increase the detection scale of shallow layers and improve the recognition accuracy for small targets. In addition, this study has combined various data augmentation methods to improve the robustness of the network. Through experiments using 2164 road crack datasets and 8146 traffic sign datasets made by LabelImg, compared to the baseline model (YOLOv5s), the modified YOLOv5 network improves the mean average precision (mAP) result of the road crack dataset and small targets in the traffic sign dataset by 3% and 12.2%, respectively.

Diffusion models have been increasingly utilized in various image-processing tasks, such as segmentation, denoising, and enhancement. These models also show exceptional performance in enhancing underwater images. However, conventional models for underwater image enhancement often face the challenge of simultaneously improving color restoration and super-resolution. This paper introduces a dual-layer attention mechanism that integrates spatial and channel attention to enhance color restoration, while preserving critical image features. Additionally, specific scale factors and interpolation methods are employed during the upsampling process to increase resolution. The proposed DL-UW method achieves significant enhancements in color, illumination, and resolution for low-quality underwater images, resulting in high PSNR, SSIM, and UIQM values. The model demonstrates a robust performance on different datasets, confirming its broad applicability and effectiveness.

Medical image classification plays an essential role in disease diagnosis and clinical treatment. More and more research efforts have been dedicated to the design of effective methods for medical image classification. As an effective framework, the capsule network (CapsNet) can realize translation equivariance. Lots of current research applies capsule networks in medical image analysis. In this paper, we propose an attentive octave convolutional capsule network (AOC-Caps) for medical image classification. In AOC-Caps, an AOC module is used to replace the traditional convolution operation. The purpose of the AOC module is to process and fuse the high- and low-frequency information in the input image simultaneously, and weigh the important parts automatically. Following the AOC module, a matrix capsule is used and the expectation maximization (EM) algorithm is applied to update the routing weights. The proposed AOC-Caps and comparative methods are tested on seven datasets, including PathMNIST, DermaMNIST, OCTMNIST, PneumoniaMNIST, OrganMNIST_Axial, OrganMNIST_Coronal, and OrganMNIST_Sagittal, which are from MedMNIST. In the experiments, baselines include the traditional CNN models, automated machine learning (AutoML) methods, and related capsule network methods. The experimental results demonstrate that the proposed AOC-Caps achieves better performance on most of the seven medical image datasets.

The precise segmentation of retinal vasculature is crucial for the early screening of various eye diseases, such as diabetic retinopathy and hypertensive retinopathy. Given the complex and variable overall structure of retinal vessels and their delicate, minute local features, the accurate extraction of fine vessels and edge pixels remains a technical challenge in the current research. To enhance the ability to extract thin vessels, this paper incorporates a pyramid channel attention module into a U-shaped network. This allows for more effective capture of information at different levels and increased attention to vessel-related channels, thereby improving model performance. Simultaneously, to prevent overfitting, this paper optimizes the standard convolutional block in the U-Net with the pre-activated residual discard convolution block, thus improving the model’s generalization ability. The model is evaluated on three benchmark retinal datasets: DRIVE, CHASE_DB1, and STARE. Experimental results demonstrate that, compared to the baseline model, the proposed model achieves improvements in sensitivity (Sen) scores of 7.12%, 9.65%, and 5.36% on these three datasets, respectively, proving its strong ability to extract fine vessels.