Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as an important tool for diagnosing ophthalmic diseases. However, it is challenging to achieve accurate segmentation due to low contrast and blood flow noises presented in the images. In addition, the algorithm should be lightweight to be deployed for practical clinical applications. Therefore, it is desired to design a lightweight network with high performance for retinal layer segmentation. In this article, we propose LightReSeg for retinal layer segmentation which can be applied to OCT images. Specifically, our approach follows an encoder-decoder structure, where the encoder part uses multiscale feature extraction and a transformer block for fully exploiting the semantic information of feature maps at all scales and making the features have better global reasoning capabilities, while the decoder part, we design a multiscale asymmetric attention (MAA) module for preserving the semantic information at each encoder scale. The experiments show that our approach achieves a better segmentation performance compared with the current state-of-the-art method TransUnet with 105.7 M parameters on both our collected dataset and two other public datasets, with only 3.3 M parameters.

Fault diagnosis of hydraulic system is of great significance to reduce the risk of damage to road machinery and improve construction safety. The hydraulic system of highway machinery has the characteristics of uncertainty, nonlinearity, and time-varying, so it is difficult to carry out efficient fault diagnosis under complex working conditions. In this article, a new approach to classification based on a hybrid model of transformer and long short-term memory neural network (LS-TF) is proposed. At first, the feature information of 1-D time series is extracted by the convolution layer and long short-term memory (LSTM) network, which reduces the problems, such as gradient disappearance. Second, the location feature information is obtained by location encoding in transformer, and the multihead attention mechanism (MHAM) as well as the residual network realize the capture of associated features in time series to facilitate the transfer of feature information in the network. Finally, the anti-noise experiments are conducted on the model in the dataset of the hydraulic system of road machinery, and the results of fault diagnosis are visualized. The analysis has shown that the proposed model has high diagnostic accuracy and noise resolution compared with other diagnostic methods.

High-resolution retinal optical coherence tomography(OCT) images are crucial for the diagnosis of numerous retinal diseases, but images acquired by narrow bandwidth OCT devices suffer from axial resolution degradation and are difficult to support disease diagnosis. Deep learning-based methods can enhance the axial resolution of OCT images, but most methods focus on improving the model architecture, the potential of fully exploiting the fusion of spatial and frequency domain information for image reconstruction has not been fully explored. This paper proposes a Dual-branch Multidomain Feature Fusion Network (MDFNet). The core module of the model consists of a parallel Enhanced Multi-scale Spatial Feature module and an Auxiliary Frequcy Feature module to provide non-interfering dual-domain feature information to improve the reconstruction effect. MDFNet achieved the best performance in the tests of mouse retina and human retina datasets, outperforming the state-of-the-art (SOTA) algorithms by 0.11 dB and 0.18 dB respectively. In addition, the results of this method performed best in the retinal layer segmentation test.

Variations in the thickness of retinal layers serve as early diagnostic indicators for various fundus diseases, and precise segmentation of these layers is essential for accurately measuring their thickness. Optical Coherence Tomography (OCT) is an important non-invasive tool for diagnosing various eye diseases through the acquisition and layering of retinal images. However, noise and artifacts in images present significant challenges in accurately segmenting retinal layers. We propose a novel method for retinal layer segmentation that addresses these issues. This method utilizes ConvNeXt as the backbone network to enhance multi-scale feature extraction and incorporates a Transformer–CNN module to improve global processing capabilities. This method has achieved the highest segmentation accuracy on the Retina500 dataset, with a mean Intersection over Union (mIoU) of 81.26% and an accuracy (Acc) of 91.38%, and has shown excellent results on the public NR206 dataset.

Denoising is a commonly used technique in medical image preprocessing, particularly in the processing of optical coherence tomography (OCT) images. Due to the characteristics of OCT systems and their operational principles, the acquired images inevitably contain a superposition of various types of noise, including speckle noise, structural noise, and random noise, which consequently reduces the accuracy of subsequent segmentation tasks. Moreover, medical image processing places a high emphasis on image details, making it challenging to remove noise without causing excessive smoothing of the images. In addition, the difficulty in obtaining ground truth for medical images limits the application of many supervised learning methods. To address these issues, this article proposes an unsupervised masked region-based denoising diffusion probabilistic model algorithm. This algorithm employs pixel-level masking, which not only effectively enhances the removal of random noise but also enables the model to focus more on adjacent regions, thereby avoiding excessive alteration of the original image’s details and edges. Furthermore, the method leverages information complementarity among data within the same group, effectively preventing information loss caused by masking. Experimental results demonstrate that compared to the baseline, the proposed algorithm increases the CNR to 3.77 with minimal reduction in the structural similarity index measure (SSIM). In addition, further segmentation experiments confirm the effectiveness of the denoising algorithm, achieving a 5.5% improvement in segmentation accuracy. This study presents the MR-DDPM algorithm, which improves the denoising quality of OCT images and consequently enhances segmentation accuracy, without the need for labeled data. This contribution is valuable to the advancement of medical image processing algorithms.

Optical coherence tomography angiography (OCTA) suffers from more motion artifacts compared to optical coherence tomography, which are the primary source of image quality degradation in in vivo imaging. We propose an OCTA algorithm in this Letter that differs from motion compensation methods widely employed to reduce motion artifacts and effectively mitigates these artifacts. The algorithm integrates differential phase and intensity images based on the standard deviation of the flow signals. The performance of this algorithm is evaluated on mouse retina in vivo imaging. Compared to three conventional OCTA algorithms, the OCTA images obtained by the proposed algorithm exhibit fewer motion artifacts and less noise in tissue regions, with maximum improvements of 1.38 dB and 0.82 in signal-to-noise ratio and contrast-to-noise ratio (CNR), respectively, in the maximum projection of en face images.