98%
921
2 minutes
20
Automatic segmentation of retinal vessels from retinography images is crucial for timely clinical diagnosis. However, the high cost and specialized expertise required for annotating medical images often result in limited labeled datasets, which constrains the full potential of deep learning methods. Recent advances in self-supervised pretraining using unlabeled data have shown significant benefits for downstream tasks. Recognizing that multimodal feature fusion can substantially enhance retinal vessel segmentation accuracy, this paper introduces a novel self-supervised pretraining framework that leverages pairs of unlabeled multimodal fundus images to generate supervisory signals. The core idea is to exploit the complementary differences between the two modalities to construct a multimodal feature fusion map containing vessel information, achieved through Vision Transformer encoding and correlation filtering. Instance-level discriminative features are then learned under the guidance of INFOMAX loss, and the learned knowledge is transferred to a supervised vessel segmentation network. Extensive experiments show that our approach achieves state-of-the-art results among unsupervised methods and remains competitive with supervised baselines while greatly reducing annotation requirements.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.neunet.2025.108011 | DOI Listing |
AJR Am J Roentgenol
September 2025
Department of Radiology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China.
Patients with inflammation-associated coronary artery disease (CAD) may exhibit rapid progression and require regular coronary imaging. To evaluate the diagnostic performance of spectral photon-counting detector (PCD) coronary CTA with reduced radiation and contrast media doses for detecting coronary stenosis and in-stent restenosis in patients with inflammation-associated CAD. This prospective study enrolled patients with inflammation-associated CAD from January 2023 to March 2024.
View Article and Find Full Text PDFZhonghua Jie He He Hu Xi Za Zhi
September 2025
Department of Respiratory and Critical Care Medicine, the First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China.
Tracheobronchial Dieulafoy's disease (TBDD) is a rare bronchial artery vascular malformation, characterized clinically by sudden, recurrent, and life-threatening massive hemoptysis. This article reports the case of a 9-year-old female patient who presented with massive hemoptysis lasting two weeks. Following ineffective treatment at a local hospital, she was transferred to our institution.
View Article and Find Full Text PDFEur J Cancer
August 2025
Emory University, Atlanta, USA; Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA; Atlanta Veterans Administration Medical Center, Atlanta, USA. Electronic address:
Background: Early detection of hematological malignancies improves long-term survival but remains a critical challenge due to heterogeneity in clinical presentation. Chronic inflammation is a key driver in hematologic cancers and is known to induce compensatory microvascular changes. High-resolution, non-invasive retinal imaging can allow the quantification of microvascular changes for the early detection of hematological malignancies.
View Article and Find Full Text PDFSemin Vasc Surg
September 2025
Division of Vascular and Endovascular Surgery, Brigham and Women's Hospital, 75 Francis Street, Boston, MA 02115; Center for Surgery and Public Health, Boston, MA; Harvard Medical School, Boston, MA. Electronic address:
The rate of end-stage kidney disease (ESKD) is steadily rising in the United States, and older adults (ie, 65 years and older) represent the fastest-growing segment in need of hemodialysis. This demographic shift presents unique challenges due to age-related comorbidities, frailty, and increased procedural risks. Despite these challenges, there is limited guidance for risk stratification and management of renal replacement therapy in older patients with ESKD.
View Article and Find Full Text PDFBiomed Phys Eng Express
September 2025
College of Computer Science and Technology, China University of Petroleum East China - Qingdao Campus, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China, Qingdao, Shandong, 266580, CHINA.
Purpose: Cerebrovascular segmentation is crucial for the diagnosis and treatment of cerebrovascular diseases. However, accurately extracting cerebral vessels from Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) remains challenging due to the topological complexity and anatomical variability.
Methods: This paper presents a novel Y-shaped segmentation network with fast Fourier convolution and Mamba, termed F-Mamba-YNet.