Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

inter-pixel relationships

Inter-pixel relationships refer to the spatial, topological, and statistical connections or dependencies that exist between individual pixels within a digital image. In image processing and computer vision, these relationships characterize how adjacent or distant pixels associate with one another based on geometric proximity, directional alignment, connectivity paths, and shared visual attributes such as intensity, texture, or color. By accounting for the mutual influence among pixels rather than treating them as isolated data points, modeling inter-pixel relationships enables computational methods to preserve structural boundaries, maintain topological continuity, and recognize coherent regions during tasks such as image segmentation and object detection.

1 item

Directional Connectivity-based Segmentation of Medical Images

Ziyun Yang, Sina Farsiu

Anatomical consistency in biomarker segmentation is crucial for many medical image analysis tasks. A promising paradigm for achieving anatomically consistent segmentation via deep networks is incorporating pixel connectivity, a basic concept in digital topology, to model inter-pixel relationships. However, previous works on connectivity modeling have ignored the rich channel-wise directional information in the latent space. In this work, we demonstrate that effective disentanglement of directional sub-space from the shared latent space can significantly enhance the feature representation in the connectivity-based network. To this end, we propose a directional connectivity modeling scheme for segmentation that decouples, tracks, and utilizes the directional information across the network. Experiments on various public medical image segmentation benchmarks show the effectiveness of our model as compared to the state-of-the-art methods. Code is available at https://github.com/Zyun-Y/DconnNet.

Added

2026-09-26