TY - GEN
T1 - Supervised learning of anatomical structures using demographic and anthropometric information
AU - Otake, Yoshito
AU - Carneal, Catherine M.
AU - Lucas, Blake C.
AU - Thawait, Gaurav
AU - Carrino, John A.
AU - Corner, Brian D.
AU - Carboni, Marina G.
AU - Decristofano, Barry S.
AU - Maffeo, Michael A.
AU - Merkle, Andrew C.
AU - Armand, Mehran
N1 - Funding Information:
This research was supported in part by the United States Army Natick Soldier Research Development and Engineering Center. The opinions expressed are those of the authors alone and do not reflect the views of the U.S. Army. Approved for unlimited public release, US Army Natick Soldier RDEC, PAO #U12-424.
Publisher Copyright:
© Springer International Publishing Switzerland 2015.
PY - 2015
Y1 - 2015
N2 - A supervised learning approach to predict anatomical structures derived from computed tomography (CT) images using demographic and anthropometric information is proposed. The approach applies a dimensionality reduction technique to a training dataset to learn a low-dimensional manifold representing variation of organ geometry or variation of the CT intensities itself, which computes a mapping between a low-dimensional feature vector and the organ geometry or CT volume. Regression analysis is then applied to determine a regression function between the low-dimensional feature coordinates and external measurements of the subjects such as demographic or anthropometric data. Then for an unseen subject, the low-dimensional feature coordinates are predicted from external measurements using the computed regression function. Subsequently, the organ geometry or the CT volume is estimated from the mapping computed in the dimensionality reduction. As an example case, lung shapes and thoracic CT scans were analyzed based on available demographic parameters (age, gender, race) and anthropometric measurements (height, weight, and chest dimensions). The training dataset consisted of lung shapes represented as a topologically consistent point distribution model (PDM) and CT volumes (2563 voxels, 1.53 mm/voxel) of 124 subjects. The prediction error of lung shape of an unknown subject based on 11 independent demographic and anthropometric variables was 10.71 ± 5.48 mm. Isomap analysis of CT volumes revealed that 95% of the total variance was explained with 4 dimensions, and the computed mapping clearly captured trends in anatomical variation. This suggested a potential for a direct CT-volume based statistical analysis using dimensionality reduction, which we call a voxel-based statistical atlas. Potential application areas of the proposed approach includes subject-specific ergonomic design in personal protective equipment or population-specific finite-element modeling in biomechanical analysis. Examples also include the use of a predicted patient-specific CT volume as it a prior information for image quality improvement in low dose CT, and optimization of CT scanning protocols.
AB - A supervised learning approach to predict anatomical structures derived from computed tomography (CT) images using demographic and anthropometric information is proposed. The approach applies a dimensionality reduction technique to a training dataset to learn a low-dimensional manifold representing variation of organ geometry or variation of the CT intensities itself, which computes a mapping between a low-dimensional feature vector and the organ geometry or CT volume. Regression analysis is then applied to determine a regression function between the low-dimensional feature coordinates and external measurements of the subjects such as demographic or anthropometric data. Then for an unseen subject, the low-dimensional feature coordinates are predicted from external measurements using the computed regression function. Subsequently, the organ geometry or the CT volume is estimated from the mapping computed in the dimensionality reduction. As an example case, lung shapes and thoracic CT scans were analyzed based on available demographic parameters (age, gender, race) and anthropometric measurements (height, weight, and chest dimensions). The training dataset consisted of lung shapes represented as a topologically consistent point distribution model (PDM) and CT volumes (2563 voxels, 1.53 mm/voxel) of 124 subjects. The prediction error of lung shape of an unknown subject based on 11 independent demographic and anthropometric variables was 10.71 ± 5.48 mm. Isomap analysis of CT volumes revealed that 95% of the total variance was explained with 4 dimensions, and the computed mapping clearly captured trends in anatomical variation. This suggested a potential for a direct CT-volume based statistical analysis using dimensionality reduction, which we call a voxel-based statistical atlas. Potential application areas of the proposed approach includes subject-specific ergonomic design in personal protective equipment or population-specific finite-element modeling in biomechanical analysis. Examples also include the use of a predicted patient-specific CT volume as it a prior information for image quality improvement in low dose CT, and optimization of CT scanning protocols.
KW - Allometry
KW - Demographic and anthropometric data
KW - Dimensionality reduction
KW - Organ geometry
KW - Regression analysis
KW - Statistical shape atlas
KW - Supervised learning
UR - http://www.scopus.com/inward/record.url?scp=84914145565&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84914145565&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-12610-4_14
DO - 10.1007/978-3-319-12610-4_14
M3 - Conference contribution
AN - SCOPUS:84914145565
T3 - Advances in Intelligent Systems and Computing
SP - 225
EP - 240
BT - Pattern Recognition Applications and Methods - International Conference, ICPRAM 2013, Revised Selected Papers
A2 - De Marsico, Maria
A2 - Fred, Ana
PB - Springer Verlag
T2 - 2nd International Conference on Pattern Recognition, ICPRAM 2013
Y2 - 15 February 2013 through 18 February 2013
ER -