z-logo
Premium
P2–157: Effects of APOE‐ε4 on regional cerebral amyloid deposition and gray matter atrophy in mild cognitive impairment with PiB‐PET‐confirmed amyloid pathology: Results from J‐ADNI
Author(s) -
Ishii Kazunari,
Takahashi Ryuichi,
Matsuda Hiroshi,
Senda Michio,
Ito Kengo,
Ishii Kenji,
Kato Takashi,
Kuwano Ryozo,
Sugishita Morihiro,
Iwatsubo Takeshi
Publication year - 2013
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.2013.05.802
Subject(s) - precuneus , apolipoprotein e , posterior cingulate , atrophy , pittsburgh compound b , voxel based morphometry , pathology , grey matter , psychology , medicine , white matter , magnetic resonance imaging , alzheimer's disease , nuclear medicine , neuroscience , cognition , radiology , disease
corrected based on the feedback, and to segment 4 additional images. Dice and Jaccard overlapping indices were computed versus the mean of the HPexperts’ segmentations. A slice by slice visual quality check (QC) was carried out to match overlapping values with levels of compliance with the HP criteria. Results: The 10 tracers who completed the training so far had very high Dice values (1.5T: median1⁄40.90 range1⁄40.82-0.91; 3T: median1⁄40.91 range1⁄40.89-0.92). Jaccard values (1.5T: median1⁄40.81 range1⁄40.74-0.84; 3T: median1⁄40.83, range1⁄40.80-0.85) better discriminated segmentations based on compliance versus the HP, with values below 0.71 denoting major segmentation mistakes, and values below 0.80 denoting incomplete compliance with the HP criteria. Conclusions: Preliminary results show that tracers can successfully be trained a remoto to segment the hippocampus based on the HP in three training rounds. Results paired with QC will allow to set criteria for qualification within a standard web-based platform.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here