TY - JOUR
T1 - A novel approach to multiple anatomical shape analysis
T2 - Application to fetal ventriculomegaly
AU - Benkarim, Oualid
AU - Piella, Gemma
AU - Rekik, Islem
AU - Hahner, Nadine
AU - Eixarch, Elisenda
AU - Shen, Dinggang
AU - Li, Gang
AU - González Ballester, Miguel Angel
AU - Sanroma, Gerard
N1 - This research was partially funded by the “Fundació La Marató de TV3” (n∘20154031) and supported in part by National Institutes of Health grants (MH116225 to G.L, and MH117943 to G.L). The work is partly financed by the Spanish Ministry of Economy and Competitiveness under the Mara de Maeztu Units of Excellence Programs (MDM-2015-0502 and MDM-2014-0370). E.E has received funding from the Departament de Salut under grant SLT008/18/00156. The research leading to these results has received funding form “la Caixa” Foundation under grant agreement LCF/PR/GN14/10270005, the 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”, Cerebra Foundation for the Brain Injured Child (Carmarthen, Wales, UK), AGAUR 2017 SGR grant no 1531 and CERCA Programme from Generalitat de Catalunya. Additionally, this project has been funded with support of the Erasmus + Programme of the European Union (Framework Agreement number: 2013-0040).
PY - 2020/8
Y1 - 2020/8
N2 - Fetal ventriculomegaly (VM) is a condition in which one or both lateral ventricles are enlarged, and is diagnosed as an atrial diameter larger than 10 mm. Evidence of altered cortical folding associated with VM has been shown in the literature. However, existing works use a single scalar value such as diagnosis or lateral ventricular volume to characterize VM and study its relationship with alterations in cortical folding, thus failing to reveal the spatially-heterogeneous associations. In this work, we propose a novel approach to identify fine-grained associations between cortical folding and ventricular enlargement by leveraging the vertex-wise correlations between their growth patterns in terms of area expansion and curvature. Our approach comprises three steps. In the first step, we define a joint graph Laplacian matrix using cortex-to-ventricle correlations. The joint Laplacian is built based on multiple cortical features. Next, we propose a spectral embedding of the cortex-to-ventricle graph into a common underlying space where its nodes are projected according to the joint ventricle-cortex growth patterns. In this low-dimensional joint ventricle-cortex space, associated growth patterns lie close to each other. In the final step, we perform hierarchical clustering in the joint embedded space to identify associated sub-regions between cortex and ventricle. Using a dataset of 25 healthy fetuses and 23 fetuses with isolated non-severe VM within the age range of 26–29 gestational weeks, our approach reveals clinically relevant and heterogeneous regional associations. Cortical regions forming these associations are further validated using statistical analysis, revealing regions with altered folding that are significantly associated with ventricular dilation.
AB - Fetal ventriculomegaly (VM) is a condition in which one or both lateral ventricles are enlarged, and is diagnosed as an atrial diameter larger than 10 mm. Evidence of altered cortical folding associated with VM has been shown in the literature. However, existing works use a single scalar value such as diagnosis or lateral ventricular volume to characterize VM and study its relationship with alterations in cortical folding, thus failing to reveal the spatially-heterogeneous associations. In this work, we propose a novel approach to identify fine-grained associations between cortical folding and ventricular enlargement by leveraging the vertex-wise correlations between their growth patterns in terms of area expansion and curvature. Our approach comprises three steps. In the first step, we define a joint graph Laplacian matrix using cortex-to-ventricle correlations. The joint Laplacian is built based on multiple cortical features. Next, we propose a spectral embedding of the cortex-to-ventricle graph into a common underlying space where its nodes are projected according to the joint ventricle-cortex growth patterns. In this low-dimensional joint ventricle-cortex space, associated growth patterns lie close to each other. In the final step, we perform hierarchical clustering in the joint embedded space to identify associated sub-regions between cortex and ventricle. Using a dataset of 25 healthy fetuses and 23 fetuses with isolated non-severe VM within the age range of 26–29 gestational weeks, our approach reveals clinically relevant and heterogeneous regional associations. Cortical regions forming these associations are further validated using statistical analysis, revealing regions with altered folding that are significantly associated with ventricular dilation.
KW - Cortical folding
KW - Fetal ventriculomegaly
KW - Joint spectral embedding
KW - Similarity fusion
UR - http://www.scopus.com/inward/record.url?scp=85086503419&partnerID=8YFLogxK
U2 - 10.1016/j.media.2020.101750
DO - 10.1016/j.media.2020.101750
M3 - Article
C2 - 32559594
AN - SCOPUS:85086503419
SN - 1361-8415
VL - 64
JO - Medical Image Analysis
JF - Medical Image Analysis
M1 - 101750
ER -