activity
20212026
most citedLIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation

1 citations · 2 across the 7 of their papers we have counts for

collaborators
Showing eess.IVShow all

8 papers · 1 filter

eess.IV2024

SynStitch: a Self-Supervised Learning Network for Ultrasound Image Stitching Using Synthetic Training Pairs and Indirect Supervision

Xing Yao, Runxuan Yu, Dewei Hu +10

Ultrasound (US) image stitching can expand the field-of-view (FOV) by combining multiple US images from varied probe positions. However, registering US images with only partially o…

eess.IV2024

Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging

Jiacheng Wang, Hao Li, Dewei Hu +4

We propose a novel framework for retinal feature point alignment, designed for learning cross-modality features to enhance matching and registration across multi-modality retinal i…

eess.IV20231 cited

Promise:Prompt-driven 3D Medical Image Segmentation Using Pretrained Image Foundation Models

Hao Li, Han Liu, Dewei Hu +2

To address prevalent issues in medical imaging, such as data acquisition challenges and label availability, transfer learning from natural to medical image domains serves as a viab…

eess.IV2023

Novel OCT mosaicking pipeline with Feature- and Pixel-based registration

Jiacheng Wang, Hao Li, Dewei Hu +2

High-resolution Optical Coherence Tomography (OCT) images are crucial for ophthalmology studies but are limited by their relatively narrow field of view (FoV). Image mosaicking is…

eess.IV2023

CATS v2: Hybrid encoders for robust medical segmentation

Hao Li, Han Liu, Dewei Hu +3

Convolutional Neural Networks (CNNs) have exhibited strong performance in medical image segmentation tasks by capturing high-level (local) information, such as edges and textures.…

eess.IV2023

Deep Angiogram: Trivializing Retinal Vessel Segmentation

Dewei Hu, Xing Yao, Jiacheng Wang +2

Among the research efforts to segment the retinal vasculature from fundus images, deep learning models consistently achieve superior performance. However, this data-driven approach…