Dynamic multiatlas selection-based consensus segmentation of head and neck structures from CT images Journal Article


Authors: Haq, R.; Berry, S. L.; Deasy, J. O.; Hunt, M.; Veeraraghavan, H.
Article Title: Dynamic multiatlas selection-based consensus segmentation of head and neck structures from CT images
Abstract: Purpose: Manual delineation of head and neck (H&N) organ-at-risk (OAR) structures for radiation therapy planning is time consuming and highly variable. Therefore, we developed a dynamic multiatlas selection-based approach for fast and reproducible segmentation. Methods: Our approach dynamically selects and weights the appropriate number of atlases for weighted label fusion and generates segmentations and consensus maps indicating voxel-wise agreement between different atlases. Atlases were selected for a target as those exceeding an alignment weight called dynamic atlas attention index. Alignment weights were computed at the image level and called global weighted voting (GWV) or at the structure level and called structure weighted voting (SWV) by using a normalized metric computed as the sum of squared distances of computed tomography (CT)-radiodensity and modality-independent neighborhood descriptors (extracting edge information). Performance comparisons were performed using 77 H&N CT images from an internal Memorial Sloan-Kettering Cancer Center dataset (N = 45) and an external dataset (N = 32) using Dice similarity coefficient (DSC), Hausdorff distance (HD), 95th percentile of HD, median of maximum surface distance, and volume ratio error against expert delineation. Pairwise DSC accuracy comparisons of proposed (GWV, SWV) vs single best atlas (BA) or majority voting (MV) methods were performed using Wilcoxon rank-sum tests. Results: Both SWV and GWV methods produced significantly better segmentation accuracy than BA (P < 0.001) and MV (P < 0.001) for all OARs within both datasets. SWV generated the most accurate segmentations with DSC of: 0.88 for oral cavity, 0.85 for mandible, 0.84 for cord, 0.76 for brainstem and parotids, 0.71 for larynx, and 0.60 for submandibular glands. SWV’s accuracy exceeded GWV's for submandibular glands (DSC = 0.60 vs 0.52, P = 0.019). Conclusions: The contributed SWV and GWV methods generated more accurate automated segmentations than the other two multiatlas-based segmentation techniques. The consensus maps could be combined with segmentations to visualize voxel-wise consensus between atlases within OARs during manual review. © 2019 American Association of Physicists in Medicine
Keywords: clinical article; controlled study; consensus; computer assisted tomography; computed tomography images; neck; attention; larynx; brain stem; head and neck; parotid gland; rank sum test; mandible; mouth cavity; submandibular gland; article; neighborhood; atlas segmentation
Journal Title: Medical Physics
Volume: 46
Issue: 12
ISSN: 0094-2405
Publisher: American Association of Physicists in Medicine  
Date Published: 2019-12-01
Start Page: 5612
End Page: 5622
Language: English
DOI: 10.1002/mp.13854
PUBMED: 31587300
PROVIDER: scopus
PMCID: PMC7042892
DOI/URL:
Notes: Article -- Export Date: 2 January 2020 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Sean L Berry
    70 Berry
  2. Joseph Owen Deasy
    524 Deasy
  3. Margie A Hunt
    287 Hunt
  4. Rabia Haq
    12 Haq