Títol:
|
Learning to combine complementary segmentation methods for fetal and 6-month infant brain MRI segmentation
|
Autor/a:
|
Piella Fenoy, Gemma; Sanromà, Gerard; Benkarim, Oualid M.; Piella Fenoy, Gemma; Lekadir, Karim; Hahner, Nadine; Eixarch, Elisenda; González Ballester, Miguel Ángel, 1973-
|
Altres autors:
|
Gerard Sanroma, Oualid M.Benkarim, Gemma Piella, Karim Lekadir, Nadine Hahner, Elisenda Eixarch, Miguel A.González Ballester |
Abstract:
|
Segmentation of brain structures during the pre-natal and early post-natal periods
is the first step for subsequent analysis of brain development. Segmentation
techniques can be roughly divided into two families. The first, which we denote
as registration-based techniques, rely on initial estimates derived by registration
to one (or several) templates. The second family, denoted as learning-based techniques,
relate imaging (and spatial) features to their corresponding anatomical
labels. Each approach has its own qualities and both are complementary to each
other. In this paper, we explore two ensembling strategies, namely, stacking and
cascading to combine the strengths of both families. We present experiments
on segmentation of 6-month infant brains and a cohort of fetuses with isolated
non-severe ventriculomegaly (INSVM). INSVM is diagnosed when ventricles
are midly enlarged and no other anomalies are apparent. Prognosis is diffcult
based solely on the degree of ventricular enlargement. In order to find markers
for a more reliable prognosis, we use the resulting segmentations to find abnormalities in the cortical folding of INSVM fetuses. Segmentation results show that either combination strategy outperform all of the individual methods, thus demonstrating the capability of learning systematic combinations that lead to
an overall improvement. In particular, the cascading strategy outperforms the
ensembling one, the former one obtaining top 5, 7 and 13 results (out of 21
teams) in the segmentation of white matter, gray matter and cerebro-spinal
fuid in the iSeg2017 MICCAI Segmentation Challenge. The resulting segmentations
reveal that INSVM fetuses have a less convoluted cortex. This points to
cortical folding abnormalities as potential markers of later neurodevelopmental
outcomes. |
Abstract:
|
The first author is co-financed by the Marie Curie FP7-PEOPLE-2012-
COFUND Action, Grant agreement no: 600387. This study was partly sup345
ported by Instituto de Salud Carlos III (PI16/00861) integrados en el Plan
Nacional de I+D+I y cofinanciados por el ISCIII-Subdirección General de Evaluación y el Fondo Europeo de Desarrollo Regional (FEDER) "Una manera de
hacer Europa"; additionally the research leading to these results has received
funding from "la Caixa" Foundation. This work is partly supported by the
350 Spanish Ministry of Economy and Competitiveness under the Maria de Maeztu
Units of Excellence Programme (MDM-2015-0502). |
Matèries:
|
-Fetal brain MRI segmentation -Multi-atlas label fusion -Stacking -Cascading -Isolated non-severe ventriculomegaly |
Drets:
|
© Elsevier https://doi.org/10.1016/j.compmedimag.2018.08.007
info:eu-repo/semantics/embargoedAccess |
Tipus de document:
|
Article Article - Versió acceptada |
Publicat per:
|
Elsevier
|
Compartir:
|
|