Sequential federated learning (SFL) trains models collaboratively across clients in a chain manner. This order shows communication efficiency compared to traditional FL in a parallel manner with a star topology. However, SFL can fail to produce stable training results when clients have significant statistical heterogeneity among their local data distributions. To address these challenges, we propose a novel element-wise model decoupling framework namedSeqFedEDTthat accelerates SFL training by separating model parameters of each client into a shared subset for global knowledge collaboration and a personalized subset for migrating data heterogeneity. We explore three types of parameter contribution scoring metrics based on gradient, Fisher information, and parameter importance (PI) for personalized parameter selection. In addition, we propose a quantile-based thresholding mechanism to separate shared and personalized subsets and explore the best performance quantile selection in numerical studies. Extensive experiments demonstrate thatSeqFedEDToutperforms eight state-of-the-art methods across diverse datasets and heterogeneity scenarios. All code and results are available athttps://github.com/tian0920/SeqFedEDT.

The detection of optic disc and macula is an essential step for ROP (Retinopathy of prematurity) zone segmentation and disease diagnosis. This paper aims to enhance deep learning-based object detection with domain-specific morphological rules. Based on the fundus morphology, we define five morphological rules, i.e., number restriction (maximum number of optic disc and macula is one), size restriction (e.g., optic disc width: 1.05 +/- 0.13 mm), distance restriction (distance between the optic disc and macula/fovea: 4.4 +/- 0.4 mm), angle/slope restriction (optic disc and macula should roughly be positioned in the same horizontal line), position restriction (In OD, the macula is on the left side of the optic disc; vice versa for OS). A case study on 2953 infant fundus images (with 2935 optic disc instances and 2892 macula instances) proves the effectiveness of the proposed method. Without the morphological rules, naïve object detection accuracies of optic disc and macula are 0.955 and 0.719, respectively. With the proposed method, false-positive ROIs (region of interest) are further ruled out, and the accuracy of the macula is raised to 0.811. The IoU (intersection over union) and RCE (relative center error) metrics are also improved .

Diagnosing retinopathy of prematurity (ROP) is a time-consuming and complex task, even for experienced clinicians, as it is challenging to determine its specific stages accurately. In this study, we propose an advanced dual-branch feature interaction network for predicting the stages of ROP using color fundus photographs. Specifically, the proposed network includes a Vision Transformer (ViT) branch and a convolutional neural network (CNN) branch, which are used to capture global contextual information and express local detail features, respectively. To improve the efficiency of ViT, we introduce a cascaded group attention (CGA) module feeding attention heads with different splits of the full feature, which not only saves computation cost but also improves attention diversity. The semantic features extracted from both the Transformer and CNN branches are fused through the branch feature interaction (BFI) module, allowing us to leverage the unique characteristics of both branches to optimize ROP feature representations comprehensively. Afterwards, we further design a Transformer block with structure information learning (SIL) to gather ROP-related semantic information from high-level features, gradually constructing ROP feature information structure to highlight important regions and improve the model’s discriminative ability for different lesion feature structures. Our extensive experiments on both clinical and public datasets produce promising results, showcasing the outstanding performance of our method.

North piedmont of Yinshan Mountain is a typical fragile ecology zone and important eco-shelter in north China, therefore, to monitor and analyze its dynamics of vegetation cover is an important entrance to study response of global change in this area even the ecotone. Based on annual SPOT4/VEGETATION images of this area from 1998 to 2003, we did time series analysis on dynamics of annual maximum NDVI, which reflected dynamics of vegetation cover condition, and then drew three conclusions: Firstly, the whole area annual maximum NDVI was degenerated continuously from year 1999 to 2001, while was improved continuously in the next two years. Secondly, when it comes to woodland, grassland and cropland, the order of the annual maximum NDVI and their change in a year both were: cropland>woodland>grassland, while the order of change in 1998-2003 was: woodland>cropland>grassland; Besides, cropland and woodland annual maximum NDVI in year 2003 had middling and slight improvement respectively, compared with those of year 1998, while grassland had middling degeneration. Thirdly, annual maximum NDVI of the whole area in year 2001 had serious degeneration, compared with that of year 1998, except for middle Damao Banner, east Duolun County and southeast Shangdu County, while that of 2003 had middling or high improvement, compared with that of year 2001, except for northwest Damao Banner and sporadic spots of east Duolun County. On the whole, annual maximum NDVI of year 2003 had middling degeneration in the northwest of this area, while degeneration and improvement coexisted in other places, compared with that of year 1998.