Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

A framework for quality control of corpus callosum segmentation in large-scale studies

Full text
Author(s):
Herrera, William Garcia [1] ; Pereira, Mariana [1] ; Bento, Mariana [2] ; Lapa, Aline Tamires [3] ; Appenzeller, Simone [3] ; Rittner, Leticia [1]
Total Authors: 6
Affiliation:
[1] Univ Estadual Campinas, Sch Elect & Comp Engn, Med Image Comp Lab MICLab, UNICAMP, Campinas - Brazil
[2] Univ Calgary, Hotchkiss Brain Inst, Radiol & Clin Neurosci, Calgary, AB - Canada
[3] Univ Estadual Campinas, Fac Med Sci, Rheumatol Dept, UNICAMP, Campinas - Brazil
Total Affiliations: 3
Document type: Journal article
Source: JOURNAL OF NEUROSCIENCE METHODS; v. 334, MAR 15 2020.
Web of Science Citations: 0
Abstract

Background: The corpus callosum (CC) is the largest white matter structure in the brain, responsible for the interconnection of the brain hemispheres. Its segmentation is a required preliminary step for any posterior analysis, such as parcellation, registration, and feature extraction. In this context, the quality control (QC) of CC segmentation allows studies on large datasets with no human interaction, and the proper usage of available automated and semi-automated algorithms. New method: We propose a framework for QC of CC segmentation based on the shape signature, computed at 49 distinct resolutions. At each resolution, a support vector machine (SVM) classifier was trained, generating 49 individual classifiers. Then, a disagreement metric was used to cluster these individual classifiers. The final ensemble was constructed by selecting one representation from each cluster. Results: The proposed framework achieved an area under the curve (AUC) metric of 98.25% on the test set (207 subjects) employing an ensemble composed of 12 components. This ensemble outperformed all individual classifiers. Comparison with existing methods: To the best of our knowledge, this is the first approach to assess quality of CC segmentations on large datasets without the need for a ground-truth. Conclusions: The shape descriptor is robust and versatile, describing the segmentation at different resolutions. The selection of classifiers and the disagreement measure lead to an ensemble composed of high-quality and heterogeneous classifiers, ensuring an optimal trade-off between the ensemble size and high AUC. (AU)

FAPESP's process: 13/07559-3 - BRAINN - The Brazilian Institute of Neuroscience and Neurotechnology
Grantee:Fernando Cendes
Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC