131293 20240208144956.0 doi 10.1109/ISBI45749.2020.9098445 sideral 118591 ART-2020-118591 eng Ramón-Júlvez, Ubaldo Universidad de Zaragoza Analysis of the influence of diffeomorphic normalization in the prediction of stable VS progressive MCI conversion with convolutional neural networks 2020 Access copy available to the general public Unrestricted We study the effect of the selection of diffeomorphic normalization in the performance of Spasov''s deep-learning system for the problem of progressive MCI vs stable MCI discrimination. We considered different degrees of normalization (no, affine and non-rigid normalization) and two diffeomorphic registration methods (ANTS and BL PDE-LDDMM) with different image similarity metrics (SSD, NCC, and lNCC) yielding qualitatively different deformation models and quantitatively different degrees of registration accuracy. BL PDE-LDDMM NCC achieved the best performing accuracy with median values of 89%. Surprisingly, the accuracy of no and affine normalization was also among the highest, indicating that the deep-learning system is powerful enough to learn accurate models for pMCI vs sMCI discrimination without the need for normalization. However, the best sensitivity values were obtained by BL PDE-LDDMM SSD and NCC with median values of 97% and 94% while the sensitivity of the remaining methods stayed under 88%. info:eu-repo/grantAgreement/ES/MICINN/TIN2016-80347-R info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 0.6 2020 Radiology, Nuclear Medicine and Imaging 2020 Biomedical Engineering 2020 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Hernández, Mónica Universidad de Zaragoza (orcid)0000-0003-1270-5852 Mayordomo, Elvira Universidad de Zaragoza (orcid)0000-0002-9109-5337 ADNI 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 2020-April (2020), 1120-1124 Proc. (IEEE Int. Symp. Biomed. Imaging) Proceedings - International Symposium on Biomedical Imaging 1945-7928 528920 http://zaguan.unizar.es/record/131293/files/texto_completo.pdf Postprint 2951764 http://zaguan.unizar.es/record/131293/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:131293 articulos driver 2024-02-08-14:47:20 ARTICLE