Label-Free Hyperspectral Imaging and Deep-Learning Prediction of Retinal Amyloid β-Protein and Phosphorylated Tau

Abstract

AbstractAlzheimer’s disease (AD) is a major risk for the aging population. The pathological hallmarks of AD—an abnormal deposition of amyloid β-protein (Aβ) and phosphorylated tau (pTau)—have been demonstrated in the retinas of AD patients, including in prodromal patients with mild cognitive impairment (MCI). Aβ pathology, especially the accumulation of the amyloidogenic 42-residue long alloform (Aβ42), is considered an early and specific sign of AD, and together with tauopathy, confirms AD diagnosis. To visualize retinal Aβ and pTau, state-of-the-art methods use fluorescence. However, administering contrast agents complicates the imaging procedure. To address this problem, we developed a label-free hyperspectral imaging method to detect the spectral signatures of Aβ42 and pS396-Tau and predicted their abundance in retinal cross sections. For the first time, we reported the spectral signature of pTau and demonstrated an accurate prediction of Aβ and pTau distribution powered by deep learning. We expect our finding will lay the groundwork for label-free detection of AD at its very earliest roots.Significance StatementThe pathological hallmarks of Alzheimer’s disease (AD), amyloid β-protein (Aβ) and hyperphosphorylated (p)Tau protein have been characterized by a hyperspectral camera in terms of spectral signatures. The unique optical properties of the hallmark proteins on the broad visible light range enable label-free and high-resolution detection and virtual staining of abnormal deposition in the retina tissue, which will lay the groundwork for AD early diagnosis and AD development quantification.