Min Wang1,2, Michael Schutte3, Timo Grimmer4, Aldana Lizarraga5, Thomas Schultz6, Dennis M Hedderich5, Janine Diehl-Schmid4, Axel Rominger7, Sybille Ziegler8, Nassir Navab2, Zhuangzhi Yan1, Jiehui Jiang9, Igor Yakushev10, Kuangyu Shi2,7. 1. Institute of Biomedical Engineering, School of Life Science, Shanghai University, Shanghai, China. 2. Computer-Aided Medical Procedures and Augmented Reality, Technical University of Munich, Munich, Germany. 3. The Bonn-Aachen International Center for Information Technology (b-it) and Institute of Computer Science II, University of Bonn, Bonn, Germany. 4. Department of Psychiatry and Psychotherapy, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany. 5. Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany. 6. Department for Visual Computing, University of Bonn, Bonn, Germany. 7. Department of Nuclear Medicine, University of Bern, Bern, Switzerland. 8. Department of Nuclear Medicine, Ludwig Maximilian University of Munich, Munich, Germany. 9. Institute of Biomedical Engineering, School of Life Science, Shanghai University, Shanghai, China. jiangjiehui@shu.edu.cn. 10. Department of Nuclear Medicine, Klinikum rechts der Isar, Technical University of Munich, Ismaninger Str. 22, 81675, Munich, Germany. igor.yakushev@tum.de.
Abstract
PURPOSE: Sparse inverse covariance estimation (SICE) is increasingly utilized to estimate inter-subject covariance of FDG uptake (FDGcov) as proxy of metabolic brain connectivity. However, this statistical method suffers from the lack of robustness in the connectivity estimation. Patterns of FDGcov were observed to be spatially similar with patterns of structural connectivity as obtained from DTI imaging. Based on this similarity, we propose to regularize the sparse estimation of FDGcov using the structural connectivity. METHODS: We retrospectively analyzed the FDG-PET and DTI data of 26 healthy controls, 41 patients with Alzheimer's disease (AD), and 30 patients with frontotemporal lobar degeneration (FTLD). Structural connectivity matrix derived from DTI data was introduced as a regularization parameter to assign individual penalties to each potential metabolic connectivity. Leave-one-out cross validation experiments were performed to assess the differential diagnosis ability of structure weighted SICE approach. A few approaches of structure weighted were compared with the standard SICE. RESULTS: Compared to the standard SICE, structural weighting has shown more stable performance in the supervised classification, especially in the differentiation AD vs. FTLD (accuracy of 89-90%, while unweighted SICE only 85%). There was a significant positive relationship between the minimum number of metabolic connection and the robustness of the classification accuracy (r = 0.57, P < 0.001). Shuffling experiments showed significant differences between classification score derived with true structural weighting and those obtained by randomized structure (P < 0.05). CONCLUSION: The structure-weighted sparse estimation can enhance the robustness of metabolic connectivity, which may consequently improve the differentiation of pathological phenotypes.
PURPOSE: Sparse inverse covariance estimation (SICE) is increasingly utilized to estimate inter-subject covariance of FDG uptake (FDGcov) as proxy of metabolic brain connectivity. However, this statistical method suffers from the lack of robustness in the connectivity estimation. Patterns of FDGcov were observed to be spatially similar with patterns of structural connectivity as obtained from DTI imaging. Based on this similarity, we propose to regularize the sparse estimation of FDGcov using the structural connectivity. METHODS: We retrospectively analyzed the FDG-PET and DTI data of 26 healthy controls, 41 patients with Alzheimer's disease (AD), and 30 patients with frontotemporal lobar degeneration (FTLD). Structural connectivity matrix derived from DTI data was introduced as a regularization parameter to assign individual penalties to each potential metabolic connectivity. Leave-one-out cross validation experiments were performed to assess the differential diagnosis ability of structure weighted SICE approach. A few approaches of structure weighted were compared with the standard SICE. RESULTS: Compared to the standard SICE, structural weighting has shown more stable performance in the supervised classification, especially in the differentiation AD vs. FTLD (accuracy of 89-90%, while unweighted SICE only 85%). There was a significant positive relationship between the minimum number of metabolic connection and the robustness of the classification accuracy (r = 0.57, P < 0.001). Shuffling experiments showed significant differences between classification score derived with true structural weighting and those obtained by randomized structure (P < 0.05). CONCLUSION: The structure-weighted sparse estimation can enhance the robustness of metabolic connectivity, which may consequently improve the differentiation of pathological phenotypes.
Authors: Igor Yakushev; Gael Chételat; Florian U Fischer; Brigitte Landeau; Christine Bastin; Armin Scheurich; Audrey Perrotin; Mohamed Ali Bahri; Alexander Drzezga; Francis Eustache; Mathias Schreckenberger; Andreas Fellgiebel; Eric Salmon Journal: Neuroimage Date: 2013-04-28 Impact factor: 6.556
Authors: Yong Jeong; Sang Soo Cho; Jung Mi Park; Sue J Kang; Jae Sung Lee; Eunjoo Kang; Duk L Na; Sang Eun Kim Journal: J Nucl Med Date: 2005-02 Impact factor: 10.057
Authors: Silvia Morbelli; Robert Perneczky; Alexander Drzezga; Giovanni B Frisoni; Anna Caroli; Bart N M van Berckel; Rik Ossenkoppele; Eric Guedj; Mira Didic; Andrea Brugnolo; Mehrdad Naseri; Gianmario Sambuceti; Marco Pagani; Flavio Nobili Journal: J Nucl Med Date: 2013-04-16 Impact factor: 10.057