000162310 001__ 162310 000162310 005__ 20251009133841.0 000162310 0247_ $$2doi$$a10.1364/BOE.559663 000162310 0248_ $$2sideral$$a144923 000162310 037__ $$aART-2025-144923 000162310 041__ $$aeng 000162310 100__ $$0(orcid)0009-0009-6868-8327$$aCasado-Moreno, Juan$$uUniversidad de Zaragoza 000162310 245__ $$aDeep learning-based keratoconus detection from Scheimpflug images 000162310 260__ $$c2025 000162310 5060_ $$aAccess copy available to the general public$$fUnrestricted 000162310 5203_ $$aThis study evaluates the effectiveness of deep learning techniques applied to raw Scheimpflug corneal images for keratoconus detection, with a particular focus on forme fruste (FF) keratoconus, which refers to preclinical cases. Using an original dataset of 22,750 images from 910 eyes, a deep learning model based on transfer learning with a pre-trained VGG16 architecture was trained, incorporating specific preprocessing steps and data augmentation strategies. The proposed approach achieved an overall accuracy of 90.70%, with a sensitivity of 80.57%, and a specificity of 80.56% for FF keratoconus classification, and an AUC of 0.89. For clinical keratoconus, the model demonstrated a sensitivity of 93.28%, a specificity of 99.40%, and an AUC of 1.00. These findings highlight the potential of leveraging raw Scheimpflug images in deep learning-based keratoconus detection, particularly for identifying early-stage structural changes that may not be apparent in conventional topographic assessments. 000162310 536__ $$9info:eu-repo/grantAgreement/EC/HORIZON EUROPE/101162733/EU/Visual Impairment Screening using Images from Ophthalmology and Novel pathways for Structural Analysis and Fast Evaluation/VISIONSAFE 000162310 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es 000162310 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000162310 700__ $$0(orcid)0000-0003-0060-7278$$aMasia, Belén$$uUniversidad de Zaragoza 000162310 700__ $$aLu, Nanji 000162310 700__ $$aCui, Lele 000162310 700__ $$0(orcid)0000-0001-5186-1837$$aConsejo, Alejandra$$uUniversidad de Zaragoza 000162310 7102_ $$12002$$2385$$aUniversidad de Zaragoza$$bDpto. Física Aplicada$$cÁrea Física Aplicada 000162310 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf. 000162310 773__ $$g16, 8 (2025), 3047-3060$$pBIOMEDICAL OPTICS EXPRESS$$tBiomedical Optics Express$$x2156-7085 000162310 8564_ $$s4240097$$uhttps://zaguan.unizar.es/record/162310/files/texto_completo.pdf$$yVersión publicada 000162310 8564_ $$s2523568$$uhttps://zaguan.unizar.es/record/162310/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000162310 909CO $$ooai:zaguan.unizar.es:162310$$particulos$$pdriver 000162310 951__ $$a2025-10-09-13:25:56 000162310 980__ $$aARTICLE