3 papers
cs.CV2026
When Retrieval Hurts: Measuring and Explaining Retrieval-Induced Hallucination in Chest X-ray Report Generation
Emmanuel Idoko, Abdusshakur Olabisi, Shiloh Oni +1
Retrieval-augmented generation is an attractive way to improve chest X-ray reporting, because reports from similar prior studies supply clinical context a general vision-language m…
cs.CV2026
VAMAE: Vessel-Aware Masked Autoencoders for OCT Angiography
Ilerioluwakiiye Abolade, Prince Mireku, Kelechi Chibundu +4
Optical coherence tomography angiography (OCTA) provides non-invasive visualization of retinal microvasculature, but learning robust representations remains challenging due to spar…
eess.IV2025
SharpXR: Structure-Aware Denoising for Pediatric Chest X-Rays
Ilerioluwakiiye Abolade, Emmanuel Idoko, Solomon Odelola +6
Pediatric chest X-ray imaging is essential for early diagnosis, particularly in low-resource settings where advanced imaging modalities are often inaccessible. Low-dose protocols r…