Abstract #4637
MANUAL SEGMENTATION QUALIFICATION PLATFORM FOR THE EADC-ADNI HARMONIZED PROTOCOL FOR HIPPOCAMPAL SEGMENTATION PROJECT
Simon Duchesne 1 , Fernando Valdivia 2 , Nicolas Robitaille 2 , Abderazzak Mouiha 2 , Abiel F. Valdivia 2 , Martina Bocchetta 3 , Liana G. Apostolova 4 , Rossana Ganzola 2 , Greg Preboske 5 , Dominik Wolf 6 , Marina Boccardi 3 , Clifford R. Jack Jr. 5 , and Giovanni B. Frisoni 3
1
Universite Laval, Quebec, Quebec, Canada,
2
Universite
Laval, Quebec, Canada,
3
IRCCS
Fatebenefratelli, Brescia, Italy,
4
UCLA,
Los Angeles, CA, United States,
5
Mayo
Clinic, Rochester, Minnesota, United States,
6
Johannes
Gutenberg-Universitt, Mainz, Germany
We present early user cases for a platform for manual
segmentation of the hippocampus on magnetic resonance
images, set within the context of the EADC-ADNI
Harmonized Protocol project (HarP). The interactive web
system allows for protocol learning, segmentation
training and qualification of the ability of new tracers
to segment the hippocampus according to the HarP. Our
objective was to demonstrate that the training process
embedded in the platform led to increased compliance
with the HarP. Statistical testing of training over
three phases showed a significant effect of Jaccard
overlap, demonstrating that training positively
increased compliance with the HarP.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here