Peripapillary atrophy (PPA) is a critical imaging biomarker for the diagnosis and grading of pathological myopia (PM), and its accurate segmentation plays an essential role in clinical evaluation and longitudinal monitoring. However, automatic PPA segmentation from color fundus images remains challenging due to blurred and discontinuous boundaries, low tissue contrast, and noise interference, which limit the performance of existing methods. In this study, we propose a novel segmentation framework, termed FSD-PPA (Frequency-Semantic Dual-Driven Segmentation Network), to address these limitations. The proposed FSD-PPA integrates a high-frequency edge extraction module to enhance anatomical boundary perception, a low-frequency compensation module to restore tissue structural integrity, and a multi-scale semantic enhancement module to improve cross-level contextual understanding. Experimental results on an expert-annotated PPA dataset and the public PALM dataset demonstrate that our method achieves Dice scores of 83.48 % and 84.30 %, respectively, outperforming existing approaches. These results confirm two major advantages of FSD-PPA: (1) high segmentation accuracy, enabling precise identification of complex PPA morphology; and (2) strong generalization ability, with stable performance across different datasets. This study provides a robust and reliable solution for automatic PPA segmentation. Clinically, it holds potential as an assistive tool for early PM screening and offers an objective imaging basis for quantitative assessment and monitoring of myopic progression, thereby facilitating intelligent diagnosis of myopia-associated fundus lesions.lligent diagnosis systems for myopia-related fundus lesions.

Domain shifts between samples acquired with different instruments are one of the major challenges in accurate segmentation of Optical Coherence Tomography (OCT) images. Given that OCT images may be acquired with different devices in different clinical centers, this study presents astyle and structure data augmentation (SSDA) method to improve the adaptability of segmentation models. Inspired by our initial analysis of OCT domain differences, we propose an innovative hypothesis that domain shifts are primarily due to differences in image style and anatomical structure, which further guides the design of our method. By designing a modality-specific NURBS curve for style enhancement and implementing global and local elastic deformation fields, SSDA addresses both stylistic and structural variations in OCT data. Global deformations simulate changes in retinal curvature, while local deformations model layer-specific changes observed in OCT images. We validate our hypothesis through a comprehensive evaluation conducted on five OCT data domains, each differing in device type and imaging conditions. We train models on each of these domains for single-domain generalisation experiments and evaluate performance on the remaining unseen domains. The results show that SSDA outperforms existing methods when segmenting OCT images from different sources with different requirements for retinal layer segmentation. Specifically, across five different source domain generalisation experiments, SSDA achieves approximately 1.6% higher Dice and 2.6% improved MIOU, underscoring its superior segmentation accuracy and robust generalisation across all evaluated unseen domains.

Optical coherence tomography angiography (OCTA) plays a crucial role in quantifying and analyzing retinal vascular diseases. However, the limited field of view (FOV) inherent in most commercial OCTA imaging systems poses a significant challenge for clinicians, restricting the possibility to analyze larger retinal regions of high resolution. Automatic stitching of OCTA scans in adjacent regions may provide a promising solution to extend the region of interest. However, commonly-used stitching algorithms face difficulties in achieving effective alignment due to noise, artifacts and dense vasculature present in OCTA images. To address these challenges, we propose a novel retinal OCTA image stitching network, named -Net, which integrates multi-scale representation learning and dynamic location guidance. In the first stage, an image registration network with a progressive multi-resolution feature fusion is proposed to derive deep semantic information effectively. Additionally, we introduce a dynamic guidance strategy to locate the foveal avascular zone (FAZ) and constrain registration errors in overlapping vascular regions. In the second stage, an image fusion network based on multiple mask constraints and adjacent image aggregation (AIA) strategies is developed to further eliminate the artifacts in the overlapping areas of stitched images, thereby achieving precise vessel alignment. To validate the effectiveness of our method, we conduct a series of experiments on two delicately constructed datasets, i.e., OPTOVUE-OCTA and SVision-OCTA. Experimental results demonstrate that our method outperforms other image stitching methods and effectively generates high-quality wide-field OCTA images, achieving a structural similarity index (SSIM) score of 0.8264 and 0.8014 on the two datasets, respectively.

Optical Coherence Tomography (OCT) imaging is extensively utilized for non-invasive observation of pathological conditions, such as retinal fluid-associated diseases. Accurate fluid segmentation in OCT images is therefore critical for quantifying disease severity and aiding clinical decision-making. However, achieving precise segmentation remains challenging due to pathological variations in shape and size, uncertain boundaries, and low contrast of fluid. Most importantly, variability in OCT image styles across different vendors and centers significantly affects fluid segmentation, leading to poor generalization to unseen domains. To address this, we propose a novel method, RSAPower, to enhance the generalization ability of fluid perception networks via style augmentation for retinal fluid segmentation. Specifically, RSAPower comprises a plug-and-play random style transform augmentation (RSTAug) module and a novel fluid perception network (FLPNet) for end-to-end training. The RSTAug module generates new random-style data from the source domain, preserving realistic pathological and structural features. The FLPNet benefits from a novel hybrid structure attention (HSA) module to perceive fluid's spatial features and long-range dependence. Furthermore, FLPNet adapts to the diverse augmented data through a saliency-guided multi-scale attention (SGMA) block, boosting its segmentation performance. We validate RSAPower against various state-of-the-art methods using two publicly available datasets, Retouch and Kermany. Experimental results demonstrate the proposed method's superior generalization ability and effectiveness in fluid segmentation.

Time-of-flight magnetic resonance angiography (TOF-MRA) is the least invasive and ionizing radiation-free approach for cerebrovascular imaging, but variations in imaging artifacts across different clinical centers and imaging vendors result in inter-site and inter-vendor heterogeneity, making its accurate and robust cerebrovascular segmentation challenging. Moreover, the limited availability and quality of annotated data pose further challenges for segmentation methods to generalize well to unseen datasets. In this paper, we construct the largest and most diverse TOF-MRA dataset (COSTA) from 8 individual imaging centers, with all the volumes manually annotated. Then we propose a novel network for cerebrovascular segmentation, namely CESAR, with the ability to tackle feature granularity and image style heterogeneity issues. Specifically, a coarse-to-fine architecture is implemented to refine cerebrovascular segmentation in an iterative manner. An automatic feature selection module is proposed to selectively fuse global long-range dependencies and local contextual information of cerebrovascular structures. A style self-consistency loss is then introduced to explicitly align diverse styles of TOF-MRA images to a standardized one. Extensive experimental results on the COSTA dataset demonstrate the effectiveness of our CESAR network against state-of-the-art methods. We have made 6 subsets of COSTA with the source code online available, in order to promote relevant research in the community.

This study focuses on networked H ∞ fuzzy filtering for Markovian jump Takagi–Sugeno (T–S) fuzzy systems. Since the traditional PDC method is ineffective under network environments, a flexible filter design method is provided with imperfect premise matching. First, a unified T–S fuzzy error model is provided by considering the mismatched grades of membership. Second, by use of the constructed model and the Markovian switched Lyapunov–Krasovskii functional, a stability and a stabilisation criteria of the fuzzy filtering error system are derived, in which it is no required that the fuzzy filter shares the same membership functions with the fuzzy systems. Therefore, the designed filter is available under network environments since the mismatched premises induced by networks are well considered. Finally, the effectiveness of the proposed new design method is illustrated by two examples.

This paper addresses the problem of an event-triggered non-parallel distribution compensation (PDC) control for networked Takagi-Sugeno (T-S) fuzzy systems, under consideration of the limited data transmission bandwidth and the imperfect premise matching membership functions. First, a unified event-triggered T-S fuzzy model is provided, in which: 1) a fuzzy observer with the imperfect premise matching is constructed to estimate the unmeasurable states of the studied system; 2) a fuzzy controller is designed following the same premise as the observer; and 3) an output-based event-triggering transmission scheme is designed to economize the restricted network resources. Different from the traditional PDC method, the synchronous premise between the fuzzy observer and the T-S fuzzy system are no longer needed in this paper. Second, by use of Lyapunov theory, a stability criterion and a stabilization condition are obtained for ensuring asymptotically stable of the studied system. On account of the imperfect premise matching conditions are well considered in the derivation of the above criteria, less conservation can be expected to enhance the design flexibility. Compared with some existing emulation-based methods, the controller gains are no longer required to be known a priori. Finally, the availability of proposed non-PDC design scheme is illustrated by the backing-up control of a truck-trailer system.

This paper introduces a discrete Wirtinger-based inequality to investigate the problem of delay-dependent stability analysis of networked control systems. Firstly, a discrete-time system with an interval time-varying delay is used to describe networked control systems with quality-of-service constraints. Then, by constructing a novel augmented Lyapunov-Krasovskii functional and applying the discrete Wirtinger-based inequality and reciprocally convex approach to deal with the sum items in the derivation of the results, two delay-dependent stability criteria are obtained in terms of linear matrix inequalities (LMIs). Numerical examples are provided to show that the derived stability criteria can provide a larger allowable upper delay bound than some existing results while depending on less scalar decision variables.