@InProceedings{BentoSouzFray:2018:AuApEv,
author = "Bento, Mariana and Souza, Roberto and Frayne, Richard",
affiliation = "{University of Calgary} and {University of Calgary} and
{University of Calgary}",
title = "Multicenter Imaging Studies: Automated Approach to Evaluating Data
Variability and the Role of Outliers",
booktitle = "Proceedings...",
year = "2018",
editor = "Ross, Arun and Gastal, Eduardo S. L. and Jorge, Joaquim A. and
Queiroz, Ricardo L. de and Minetto, Rodrigo and Sarkar, Sudeep and
Papa, Jo{\~a}o Paulo and Oliveira, Manuel M. and Arbel{\'a}ez,
Pablo and Mery, Domingo and Oliveira, Maria Cristina Ferreira de
and Spina, Thiago Vallin and Mendes, Caroline Mazetto and Costa,
Henrique S{\'e}rgio Gutierrez and Mejail, Marta Estela and Geus,
Klaus de and Scheer, Sergio",
organization = "Conference on Graphics, Patterns and Images, 31. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "multicenter MR data, outlier detection, data variability.",
abstract = "Magnetic resonance (MR) as well as other imaging modalities have
been used in a large number of clinical and research studies for
the analysis and quantification of important structures and the
detection of abnormalities. In this context, machine learning is
playing an increasingly important role in the development of
automated tools for aiding in image quantification, patient
diagnosis and follow-up. Normally, these techniques require large,
heterogeneous datasets to provide accurate and generalizable
results. Large, multi-center studies, for example, can provide
such data. Images acquired at different centers, however, can
present varying characteristics due to differences in acquisition
parameters, site procedures and scanners configuration. While
variability in the dataset is required to develop robust,
generalizable studies (i.e., independent of the acquisition
parameters or center), like all studies there is also a need to
ensure overall data quality by prospectively identifying and
removing poor-quality data samples that should not be included,
e.g., outliers. We wish to keep image samples that are
representative of the underlying population (so called inliers),
yet removing those samples that are not. We propose a framework to
analyze data variability and identify samples that should be
removed in order to have more representative, reliable and robust
datasets. Our example case study is based on a public dataset
containing T1-weighted volumetric head images data acquired at six
different centers, using three different scanner vendors and at
two commonly used magnetic fields strengths. We propose an
algorithm for assessing data robustness and finding the optimal
data for study occlusion (i.e., the data size that presents with
lowest variability while maintaining generalizability (i.e., using
samples from all sites)).",
conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
conference-year = "29 Oct.-1 Nov. 2018",
doi = "10.1109/SIBGRAPI.2018.00030",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2018.00030",
language = "en",
ibi = "8JMKD3MGPAW/3RMKN22",
url = "http://urlib.net/ibi/8JMKD3MGPAW/3RMKN22",
targetfile = "57_manuscript.pdf",
urlaccessdate = "2024, Apr. 28"
}