Premium
IC‐P‐153: THE 90+ STUDY T1W TEMPLATE: IMPROVED REGISTRATION OF OLDEST‐OLD MRI TO A STANDARD SPACE
Author(s) -
Woodworth Davis C.,
Corrada Maria M.,
Greenia Dana,
Kawas Claudia H.,
Sajjadi S. Ahmad
Publication year - 2019
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1016/j.jalz.2019.06.4268
Subject(s) - initialization , template , concordance , dementia , atrophy , computer science , korean population , cognition , population , medicine , artificial intelligence , pattern recognition (psychology) , nuclear medicine , psychology , pathology , neuroscience , disease , environmental health , programming language
approach to cluster WMH lesions into distinctive groups based on their shape and then texture features. We then developed an approach to calculate the potential growth index (PGI) of WMH lesions based on the image intensity distributions at the edge of the WMH lesions (penumbra) using a region-growing algorithm. Results: Fig. 2 shows the WHM lesion classification based on shape. Fig. 3 shows theWMH lesion classification based on texture. Fig. 4 shows the voxels potentially grow based on our edge characterization algorithm. Our one-way Analyses of Variance (ANOVAs) showed significant differences in PGI among WMH group clusters in terms of either the shape (P 1⁄4 3310) or the texture (P < 1310) features. Conclusions: We have developed an innovative and proof-of-concept method to characterize and quantify the shape and texture of WMH lesions. Shape and texture features of WMH lesions characterized based on our methods can potentially be used as novel biomarkers to predict lesion growth.