5 papers
When Swin Transformer Meets KANs: An Improved Transformer Architecture for Medical Image Segmentation
Nishchal Sapkota, Haoyan Shi, Yejia Zhang +5
Medical image segmentation is critical for accurate diagnostics and treatment planning, but remains challenging due to complex anatomical structures and limited annotated training…
Self Pre-training with Topology- and Spatiality-aware Masked Autoencoders for 3D Medical Image Segmentation
Pengfei Gu, Huimin Li, Yejia Zhang +2
Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pix…
Cell Instance Segmentation: The Devil Is in the Boundaries
Peixian Liang, Yifan Ding, Yizhe Zhang +9
State-of-the-art (SOTA) methods for cell instance segmentation are based on deep learning (DL) semantic segmentation approaches, focusing on distinguishing foreground pixels from b…
TopoImages: Incorporating Local Topology Encoding into Deep Learning Models for Medical Image Classification
Pengfei Gu, Hongxiao Wang, Yejia Zhang +3
Topological structures in image data, such as connected components and loops, play a crucial role in understanding image content (e.g., biomedical objects). % Despite remarkable su…
UniCoN: Universal Conditional Networks for Multi-Age Embryonic Cartilage Segmentation with Sparsely Annotated Data
Nishchal Sapkota, Yejia Zhang, Zihao Zhao +10
Osteochondrodysplasia, affecting 2-3% of newborns globally, is a group of bone and cartilage disorders that often result in head malformations, contributing to childhood morbidity…