5 papers
HiMatch-AD: DINOv3-driven Hierarchical Matching for Training-free Medical Anomaly Detection
Jiayu Huo, Jingyuan Hong, Meng Zhou +2
Anomaly detection is essential for medical image analysis, where pathological regions often appear as rare deviations from normal anatomical structures. While training-based method…
A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography
Ziqing Yu, Yuhui Tao, Jiayu Huo +19
Electrocardiography (ECG) is central to cardiovascular care, but conventional AI models are often restricted to common arrhythmias and may generalize poorly across populations or c…
DINO-AD: Unsupervised Anomaly Detection with Frozen DINO-V3 Features
Jiayu Huo, Jingyuan Hong, Liyun Chen
Unsupervised anomaly detection (AD) in medical images aims to identify abnormal regions without relying on pixel-level annotations, which is crucial for scalable and label-efficien…
Motion-Boundary-Driven Unsupervised Surgical Instrument Segmentation in Low-Quality Optical Flow
Yang Liu, Peiran Wu, Jiayu Huo +7
Unsupervised video-based surgical instrument segmentation has the potential to accelerate the adoption of robot-assisted procedures by reducing the reliance on manual annotations.…
SAM-I2I: Unleash the Power of Segment Anything Model for Medical Image Translation
Jiayu Huo, Sebastien Ourselin, Rachel Sparks
Medical image translation is crucial for reducing the need for redundant and expensive multi-modal imaging in clinical field. However, current approaches based on Convolutional Neu…