Domain Generalization-based Medical Image Segmentation (DGMIS) aims to enhance the robustness of segmentation models on unseen target domains by learning from fully annotated data across multiple source domains. Despite the progress made by traditional DGMIS methods, they still face several challenges. First, most DGMIS approaches rely on static models to perform inference on unseen target domains, lacking the ability to dynamically adapt to samples from different target domains. Second, current DGMIS methods often use Fourier transforms to simulate target domain styles from a global perspective, but relying solely on global transformations for data augmentation fails to fully capture the complexity and local details of the target domains. To address these issues, we propose a Dynamic Domain Generalization (DDG) method for medical image segmentation, which improves the generalization capability of models on unseen target domains by dynamically adjusting model parameters and effectively simulating target domain styles. Specifically, we design a Dynamic Position Transfer (DPT) module that decouples model parameters into static and dynamic components while incorporating positional encoding information to enable efficient feature representation and dynamic adaptation to target domain characteristics. Additionally, we introduce a Global-Local Fourier Random Transformation (GLFRT) module, which jointly considers both global and local style information of the samples. By using a random style selection strategy, this module enhances sample diversity while controlling training costs. Experimental results demonstrate that our method outperforms state-of-the-art approaches on several public medical image datasets, achieving average Dice score improvements of 0.58%, 0.76%, and 0.76% on the Fundus dataset (1060 retinal images), Prostate dataset (1744 T2-weighted MRI scans), and SCGM dataset (551 MRI image slices), respectively. The code is available online (https://github.com/ZMC-IIIM/DDG-Med).
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.neunet.2024.107073 | DOI Listing |
JAMA Psychiatry
January 2025
Department of Psychiatry, University of Pittsburgh, Pittsburgh, Pennsylvania.
Importance: Mania/hypomania is the pathognomonic feature of bipolar disorder (BD). As BD is often misdiagnosed as major depressive disorder (MDD), replicable neural markers of mania/hypomania risk are needed for earlier BD diagnosis and pathophysiological treatment development.
Objective: To replicate the previously reported positive association between left ventrolateral prefrontal cortex (vlPFC) activity during reward expectancy (RE) and mania/hypomania risk, to explore the effect of MDD history on this association, and to compare RE-related left vlPFC activity in individuals with and at risk of BD.
J Virol
December 2024
Department of Animal Science, Institute for Systems Genomics, University of Connecticut, Storrs, Connecticut, USA.
Unlabelled: Porcine reproductive and respiratory syndrome (PRRS) remains a major threat to animal health and causes substantial economic losses worldwide. The nonstructural protein 11 (NSP11) of the causative agent, PRRS virus (PRRSV), contains a highly conserved nidoviral uridylate-specific endoribonuclease (NendoU) domain essential for viral replication and immune evasion. Targeting NSP11 offers a novel approach to antiviral intervention.
View Article and Find Full Text PDFJ Virol
December 2024
Key Laboratory of Animal Disease Diagnostics and Immunology, Ministry of Agriculture, MOE International Joint Collaborative Research Laboratory for Animal Health & Food Safety, College of Veterinary Medicine, Nanjing Agricultural University, Nanjing, Jiangsu, China.
Porcine circovirus type 2 (PCV2) is the primary causative agent of porcine circovirus-associated disease, clinically resulting in immunosuppression and co-infections with other pathogens in infected pigs. The mechanism of PCV2 infection remains unclear. In this study, we firstly found that the tetraspanin CD81 in PK-15 cells interacts with PCV2 Cap protein by using virus overlay protein-binding assay combined with mass spectrometry.
View Article and Find Full Text PDFJ Virol
December 2024
State Key Laboratory of Pathogen and Biosecurity, Academy of Military Medical Sciences, Beijing, China.
Emerging tick-borne orthonairovirus infections pose a growing global concern, with limited understanding of the viral ovarian tumor-like cysteine proteases (vOTUs) encoded by novel orthonairoviruses. These vOTUs, a group of deubiquinylases (DUBs), disrupt the innate immune response. Yezo virus (YEZV), a recently discovered pathogenic orthonairovirus, was first reported in Japan in 2021.
View Article and Find Full Text PDFInfect Immun
December 2024
Department of Internal Medicine, Division of Pulmonary and Critical Care Medicine, the Thoracic Diseases Research Unit, Mayo Clinic College of Medicine, Rochester, Minnesota, USA.
pneumonia (PJP) remains a significant cause of morbidity and mortality during AIDS. In AIDS, the absence of CD4 immunity results in exuberant and often fatal PJP. In addition, organism clearance requires a balanced macrophage response since excessive inflammation promotes lung injury and respiratory failure.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!