Work

H-Seg-JEPA: Hierarchical Joint-Embedding Predictive Architecture for Multi-Scale Medical Image Segmentation

Year: 2026

Type: conference-paper

Abstract: In the field of medical imaging, the accurate segmentation of multiscale pathological structures in brain MRI scans is a pivotal yet formidable challenge. Traditional methodologies predominantly rely on large-scale, expert-annotated datasets, which are both prohibitively expensive and labor-intensive to acquire [14]. Precision in identifying minute lesion boundaries necessitates advanced high-resolution data processing to facilitate effective clinical treatment planning.

Source: International Conference on Intelligent Information Technology (ICIIT)

DOI: 10.1145/3805862.3805932

Authors: Khoa Dang Dang Le, Nguyen Nhu Son, Giang Long Nguyen, Hiep Xuan Huynh

Institutions: Graduate University of Science and Technology, Vietnam Academy of Science and Technology, Viện Công nghệ Thông tin, Viện Công nghệ thông tin, Can Tho University

Language: English

Topic: Medical Image Segmentation Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: hybrid

OpenAlex ID: W7203718334

FWCI:

Cites: 8

Cited by:

Related to: 10