Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases.

Nils Forkert; Alexander Schmidt-Richberg; Brigitte Holst; Alexander Münchau; Heinz Handels; Kai Boelmans

Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases.

Standard

Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases. / Forkert, Nils; Schmidt-Richberg, Alexander; Holst, Brigitte; Münchau, Alexander; Handels, Heinz; Boelmans, Kai.

in: Stud Health Technol Inform, Jahrgang 169, 2011, S. 465-469.

Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung

Harvard

Forkert, N, Schmidt-Richberg, A, Holst, B, Münchau, A, Handels, H & Boelmans, K 2011, 'Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases.', Stud Health Technol Inform, Jg. 169, S. 465-469. <http://www.ncbi.nlm.nih.gov/pubmed/21893793?dopt=Citation>

APA

Forkert, N., Schmidt-Richberg, A., Holst, B., Münchau, A., Handels, H., & Boelmans, K. (2011). Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases. Stud Health Technol Inform, 169, 465-469. http://www.ncbi.nlm.nih.gov/pubmed/21893793?dopt=Citation

Vancouver

Forkert N, Schmidt-Richberg A, Holst B, Münchau A, Handels H, Boelmans K. Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases. Stud Health Technol Inform. 2011;169:465-469.

Bibtex

@article{d5a9e874ee2347bab722142f35da1b33,

title = "Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases.",

abstract = "Parkinsonian syndromes (PS) are genetically and pathologically heterogeneous neurodegenerative disorders. Clinical distinction between different PS can be difficult, particularly in early disease stages. This paper describes an automatic method for the distinction between classical Parkinson's disease (PD) and progressive supranuclear palsy (PSP) using T2' atlases. This procedure is based on the assumption that regional brain iron content differs between PD and PSP, which can be selectively measured using T2' MR imaging. The proposed method was developed and validated based on 33 PD patients, 10 PSP patients, and 24 healthy controls. The first step of the proposed procedure comprises T2' atlas generation for each group using affine and following non-linear registration. For classification, a T2' dataset is registered to the atlases and compared to each one of them using the mean sum of squared differences metric. The dataset is assigned to the group for which the corresponding atlas yields the lowest value. The evaluation using leave-one-out validation revealed that the proposed method achieves a classification accuracy of 91%. The presented method might serve as the basis for an improved automatic classification of PS in the future.",

keywords = "Adult, Diagnosis, Differential, Humans, Aged, Middle Aged, Regression Analysis, Reproducibility of Results, Image Processing, Computer-Assisted, Syndrome, Databases, Factual, Magnetic Resonance Imaging/*methods, Brain/pathology, Diagnosis, Computer-Assisted/methods, Parkinson Disease/classification/*diagnosis/*pathology, Adult, Diagnosis, Differential, Humans, Aged, Middle Aged, Regression Analysis, Reproducibility of Results, Image Processing, Computer-Assisted, Syndrome, Databases, Factual, Magnetic Resonance Imaging/*methods, Brain/pathology, Diagnosis, Computer-Assisted/methods, Parkinson Disease/classification/*diagnosis/*pathology",

author = "Nils Forkert and Alexander Schmidt-Richberg and Brigitte Holst and Alexander M{\"u}nchau and Heinz Handels and Kai Boelmans",

year = "2011",

language = "English",

volume = "169",

pages = "465--469",

}

RIS

TY - JOUR

T1 - Image-based Classification of Parkinsonian Syndromes Using T2'-Atlases.

AU - Forkert, Nils

AU - Schmidt-Richberg, Alexander

AU - Holst, Brigitte

AU - Münchau, Alexander

AU - Handels, Heinz

AU - Boelmans, Kai

PY - 2011

Y1 - 2011

N2 - Parkinsonian syndromes (PS) are genetically and pathologically heterogeneous neurodegenerative disorders. Clinical distinction between different PS can be difficult, particularly in early disease stages. This paper describes an automatic method for the distinction between classical Parkinson's disease (PD) and progressive supranuclear palsy (PSP) using T2' atlases. This procedure is based on the assumption that regional brain iron content differs between PD and PSP, which can be selectively measured using T2' MR imaging. The proposed method was developed and validated based on 33 PD patients, 10 PSP patients, and 24 healthy controls. The first step of the proposed procedure comprises T2' atlas generation for each group using affine and following non-linear registration. For classification, a T2' dataset is registered to the atlases and compared to each one of them using the mean sum of squared differences metric. The dataset is assigned to the group for which the corresponding atlas yields the lowest value. The evaluation using leave-one-out validation revealed that the proposed method achieves a classification accuracy of 91%. The presented method might serve as the basis for an improved automatic classification of PS in the future.

AB - Parkinsonian syndromes (PS) are genetically and pathologically heterogeneous neurodegenerative disorders. Clinical distinction between different PS can be difficult, particularly in early disease stages. This paper describes an automatic method for the distinction between classical Parkinson's disease (PD) and progressive supranuclear palsy (PSP) using T2' atlases. This procedure is based on the assumption that regional brain iron content differs between PD and PSP, which can be selectively measured using T2' MR imaging. The proposed method was developed and validated based on 33 PD patients, 10 PSP patients, and 24 healthy controls. The first step of the proposed procedure comprises T2' atlas generation for each group using affine and following non-linear registration. For classification, a T2' dataset is registered to the atlases and compared to each one of them using the mean sum of squared differences metric. The dataset is assigned to the group for which the corresponding atlas yields the lowest value. The evaluation using leave-one-out validation revealed that the proposed method achieves a classification accuracy of 91%. The presented method might serve as the basis for an improved automatic classification of PS in the future.

KW - Adult

KW - Diagnosis, Differential

KW - Humans

KW - Aged

KW - Middle Aged

KW - Regression Analysis

KW - Reproducibility of Results

KW - Image Processing, Computer-Assisted

KW - Syndrome

KW - Databases, Factual

KW - Magnetic Resonance Imaging/methods

KW - Brain/pathology

KW - Diagnosis, Computer-Assisted/methods

KW - Parkinson Disease/classification/diagnosis/pathology