Work

A CT Compartment Atlas for Head-and-Neck Lymphedema: Multi-Observer Contouring Agreement and Readiness for Automated Segmentation

Year: 2026

Type: article

Abstract: This research evaluates a CT-based compartment atlas for head-and-neck lymphedema following cancer treatment. Five post-radiotherapy neck CT scans were independently contoured by three observers across 12 anatomical compartments to assess inter-observer agreement and readiness for automated segmentation. Across 174 pairwise comparisons, the median Dice score was 0.789, with 9 of 12 compartments meeting the pre-specified 0.70 training threshold and none requiring recalibration. The findings support the feasibility of the atlas while identifying Midface, Submental, and Jowl as compartments requiring clearer anatomical border definitions. This work provides a foundation for developing automated, objective CT-based measurements of head-and-neck lymphedema.

Source: Figshare

DOI: 10.6084/m9.figshare.33434347

Authors: Morgan Pearson, Shanay Goyal, Aaron Shaykevich, Ulysses Hill, Cem Dede, Clifton D. Fuller

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: green

OpenAlex ID: W7208720342

FWCI:

Cites:

Cited by:

Related to: