Skip to main content
Search

University of Ulsan

2 related articles

Subscribe to updates
  1. Otoendoscopic images stop relying on text alone: CLNA turns unwritten visual variation into an adjustable latent, cutting FID from 52.91 to 10.11

    Otoendoscopic image synthesis has been limited because text prompts state a diagnosis but not visual details such as hue and texture, leaving appearance variation within a diagnostic class hard to control. CLNA adds a style encoder and dual cross-attention to a Stable Diffusion 2.1 backbone, compressing such non-prompt attributes into a continuous latent whose sampling range is set by a style parameter. Across normal tympanic membrane, otitis media with effusion and chronic otitis media, FID against the held-out internal test set fell from 52.91 for baseline Stable Diffusion to 10.11, and feature-space recall rose from 57.67% to 90.22%.

  2. Neurointervention

    Chronic Subdural Hematoma in the Super-Aged Society: From a Traumatic Curiosity to a Self-Perpetuating Vascular-Inflammatory Disease

    This review reframes chronic subdural hematoma (cSDH) from a simple mechanical consequence of head trauma into a chronic, self-perpetuating disease driven by inflammation, pathological angiogenesis, and hyperfibrinolysis within an outer neomembrane, and on that basis summarizes patient- and hematoma-related risk factors, conventional conservative and surgical treatment, and contemporary evidence for middle meningeal artery embolization (MMAE) as a mechanism-targeted adjunct or alternative to surgery, alongside recurrence burden, cost-effectiveness, country-specific reimbursement exemplified by Korean practice, and emerging biomarker-based and artificial-intelligence-guided stratification and early transvascular access to the subdural space.

You’re all caught up