000147934 001__ 147934
000147934 005__ 20250109162738.0
000147934 0247_ $$2doi$$a10.1016/j.artmed.2024.103006
000147934 0248_ $$2sideral$$a141482
000147934 037__ $$aART-2024-141482
000147934 041__ $$aeng
000147934 100__ $$aÁlvarez-Rodríguez, Lorena
000147934 245__ $$aFully automatic deep convolutional approaches for the screening of neurodegeneratives diseases using multi-view OCT images
000147934 260__ $$c2024
000147934 5060_ $$aAccess copy available to the general public$$fUnrestricted
000147934 5203_ $$aThe prevalence of neurodegenerative diseases (NDDs) such as Alzheimer’s (AD), Parkinson’s (PD), Essential tremor (ET), and Multiple Sclerosis (MS) is increasing alongside the aging population. Recent studies suggest that these disorders can be identified through retinal imaging, allowing for early detection and monitoring via Optical Coherence Tomography (OCT) scans. This study is at the forefront of research, pioneering the application of multi-view OCT and 3D information to the neurological diseases domain. Our methodology consists of two main steps. In the first one, we focus on the segmentation of the retinal nerve fiber layer (RNFL) and a class layer grouping between the ganglion cell layer and Bruch’s membrane (GCL-BM) in both macular and optic disc OCT scans. These are the areas where changes in thickness serve as a potential indicator of NDDs. The second phase is to select patients based on information about the retinal layers. We explore how the integration of both views (macula and optic disc) improves each screening scenario: Healthy Controls (HC) vs. NDD, AD vs. NDD, ET vs. NDD, MS vs. NDD, PD vs. NDD, and a final multi-class approach considering all four NDDs. For the segmentation task, we obtained satisfactory results for both 2D and 3D approaches in macular segmentation, in which 3D performed better due to the inclusion of depth and cross-sectional information. As for the optic disc view, transfer learning did not improve the metrics over training from scratch, but it did provide a faster training. As for screening, 3D computational biomarkers provided better results than 2D ones, and multi-view methods were usually better than the single-view ones. Regarding separability among diseases, MS and PD were the ones that provided better results in their screening approaches, being also the most represented classes. In conclusion, our methodology has been successfully validated with an extensive experimentation of configurations, techniques and OCT views, becoming the first multi-view analysis that merges data from both macula-centered and optic disc-centered perspectives. Besides, it is also the first effort to examine key retinal layers across four major NDDs within the framework of pathological screening.
000147934 536__ $$9info:eu-repo/grantAgreement/ES/AEI/TED2021-131201B-I00$$9info:eu-repo/grantAgreement/ES/ISCIII/FORT23-00010$$9info:eu-repo/grantAgreement/ES/ISCIII/PI17-01726$$9info:eu-repo/grantAgreement/ES/ISCIII/PI20-00437$$9info:eu-repo/grantAgreement/ES/ISCIII-RICORDS/RD21-0002-0050$$9info:eu-repo/grantAgreement/ES/MICINN/PDC2022-133132-I00$$9info:eu-repo/grantAgreement/ES/MICINN/PID2023-148913OB-I00
000147934 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
000147934 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000147934 700__ $$aPueyo, Ana
000147934 700__ $$ade Moura, Joaquim
000147934 700__ $$0(orcid)0000-0001-9411-5834$$aVilades, Elisa$$uUniversidad de Zaragoza
000147934 700__ $$0(orcid)0000-0001-6258-2489$$aGarcia-Martin, Elena$$uUniversidad de Zaragoza
000147934 700__ $$aSánchez, Clara I.
000147934 700__ $$aNovo, Jorge
000147934 700__ $$aOrtega, Marcos
000147934 7102_ $$11013$$2646$$aUniversidad de Zaragoza$$bDpto. Cirugía$$cÁrea Oftalmología
000147934 773__ $$g158 (2024), 103006 [20 pp.]$$pArtif. intell. med.$$tARTIFICIAL INTELLIGENCE IN MEDICINE$$x0933-3657
000147934 8564_ $$s5091840$$uhttps://zaguan.unizar.es/record/147934/files/texto_completo.pdf$$yVersión publicada
000147934 8564_ $$s2581899$$uhttps://zaguan.unizar.es/record/147934/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000147934 909CO $$ooai:zaguan.unizar.es:147934$$particulos$$pdriver
000147934 951__ $$a2025-01-09-14:42:09
000147934 980__ $$aARTICLE