Rupture of intracranial aneurysms is a major cause of subarachnoid hemorrhage, making accurate segmentation important for aneurysm assessment and treatment planning. However, automated segmentation in computed tomography angiography (CTA) remains challenging because of small lesion size, complex morphology, and ambiguous boundaries between aneurysms and adjacent vessels. To address these challenges, we propose HSF-Net, a Swin UNETR-based segmentation network that integrates a Hybrid-Scale Fusion (HSF) module and the Convolutional Block Attention Module (CBAM) into the decoder. Unlike conventional decoders that mainly rely on simple feature concatenation, HSF-Net follows a "fuse first, refine later" strategy, in which HSF performs input-dependent multi-scale feature fusion and CBAM subsequently refines the fused features through channel and spatial attention. On the internal independent test set, HSF-Net achieved a mean patient-level Dice score of 83.4%, outperforming the Swin UNETR baseline and obtaining the highest Dice score among the evaluated methods under the same evaluation protocol. Ablation studies confirmed the complementary contributions of HSF and CBAM. Evaluation on an independent external cohort provided preliminary evidence of its cross-center applicability. These results suggest that HSF-Net provides an effective approach for automated intracranial aneurysm segmentation in CTA images.

Bartonella infective endocarditis (IE) is a rare cause of initially blood culture-negative IE, classically associated with cat flea exposure in Bartonella henselae infection or body lice infestation among individuals experiencing homelessness or alcoholism in Bartonella quintana infection. We report the case of an 84-year-old man with severe calcific aortic stenosis who was undergoing evaluation for pre-transcatheter aortic valve implantation (TAVI). Cardiac computed tomography (CT) unexpectedly revealed a peri-annular cavity consistent with a drained or healed peri-annular abscess, despite the absence of fever or other clinical features of IE. Initial blood cultures were negative, and TAVI was planned following multidisciplinary discussion, pending serological results. However, a subsequently reported high-titer Bartonella serology prompted readmission, and TAVI was ultimately deferred after the diagnosis was confirmed. Prolonged incubation of blood cultures subsequently identified B. quintana, while brain magnetic resonance imaging (MRI) revealed a lesion suspicious for an intracranial infectious aneurysm. Definite IE was established according to the 2023 Duke-International Society for Cardiovascular Infectious Diseases (Duke-ISCVID) criteria based on two major criteria: high-titer Bartonella serology and imaging evidence of a peri-annular abscess. No classical epidemiological risk factors for Bartonella infection were identified. Despite targeted antimicrobial therapy, the patient experienced progressive clinical deterioration, and multiple comorbidities precluded surgical intervention. He ultimately died of multiorgan failure. This case highlights the diagnostic challenge of occult B. quintana IE incidentally identified during pre-TAVI evaluation, including in patients without classical epidemiological risk factors or overt manifestations of infection. It also emphasizes that unexpected peri-annular abnormalities detected during pre-TAVI evaluation should prompt a thorough investigation for IE, even in clinically unsuspected cases, with direct implications for procedural planning.

Flow diverter (FD) technology has provided a new concept for the treatment of intracranial aneurysms: reconstruction of the parent artery by covering the neck with a braided mesh stent. It has enabled us to treat not only saccular aneurysms but also complex aneurysms that were previously considered difficult or impossible to treat. Despite its clinical impact, FD remains associated with thromboembolic and hemorrhagic complications, both of which are closely related to perioperative antiplatelet therapy. Dual antiplatelet therapy (DAPT), consisting of aspirin combined with a P2Y12 inhibitor, has traditionally been adopted as the standard strategy to reduce thromboembolic risk. However, the optimal regimen remains poorly defined, and substantial variability exists in clinical practice. Recent evidence suggests that the risk of thromboembolism is highest in the early perioperative period, while prolonged antiplatelet therapy may expose patients to unnecessary bleeding risks without clear additional benefits. In parallel, advances in platelet function testing, the availability of potent P2Y12 inhibitors, and the development of surface-modified FD devices are prompting reconsideration of the conventional paradigm of prolonged DAPT. This review provides a comprehensive synthesis of current evidence on perioperative antiplatelet therapy in the context of flow diversion and proposes a contemporary framework that emphasizes temporal risk stratification and individualized treatment strategies.