Premium
Atlas‐based estimation of lung and lobar anatomy in proton MRI
Author(s) -
Tustison Nicholas J.,
Qing Kun,
Wang Chengbo,
Altes Talissa A.,
Mugler John P.
Publication year - 2016
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.25824
Subject(s) - atlas (anatomy) , segmentation , computer science , lung , medicine , nuclear medicine , artificial intelligence , radiology , anatomy
Purpose To propose an accurate methodological framework for automatically segmenting pulmonary proton MRI based on an optimal consensus of a spatially normalized library of annotated lung atlases. Methods A library of 62 manually annotated lung atlases comprising 48 mixed healthy, chronic obstructive pulmonary disease, and asthmatic subjects of a large age range with multiple ventilation levels is used to produce an optimal segmentation in proton MRI, based on a consensus of the spatially normalized library. An extension of this methodology is used to provide best‐guess estimates of lobar subdivisions in proton MRI from annotated computed tomography data. Results A leave‐one‐out evaluation strategy was used for evaluation. Jaccard overlap measures for the left and right lungs were used for performance comparisons relative to the current state‐of‐the‐art (0.966 ± 0.018 and 0.970 ± 0.016, respectively). Best‐guess estimates for the lobes exhibited comparable performance levels (left upper: 0.882 ± 0.059, left lower: 0.868 ± 0.06, right upper: 0.852 ± 0.067, right middle: 0.657 ± 0.130, right lower: 0.873 ± 0.063). Conclusion An annotated atlas library approach can be used to provide good lung and lobe estimation in proton MRI. The proposed framework is useful for subsequent anatomically based analysis of structural and/or functional pulmonary image data. Magn Reson Med 76:315–320, 2016. © 2015 Wiley Periodicals, Inc.