Diagnostic application in streptozotocin‐induced diabetic retinopathy rats: A study based on Raman spectroscopy and machine learning

• Published in: Journal of biophotonics Vol. 17; no. 8; pp. e202400115 - n/a
• Main Authors: Xiao, Kunhong, Li, Li, Chen, Yang, Lin, Rong, Wen, Boyuan, Wang, Zhiqiang, Huang, Yan
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY‐VCH Verlag GmbH & Co. KGaA 01.08.2024; Wiley Subscription Services, Inc
• Subjects: Algorithms; Animals; Band spectra; Chemical fingerprinting; Data acquisition; Data analysis; Data processing; Diabetes mellitus; Diabetes Mellitus, Experimental - chemically induced; Diabetes Mellitus, Experimental - pathology; Diabetic retinopathy; diabetic retinopathy (DR); Diabetic Retinopathy - pathology; Discriminant analysis; Disease transmission; Machine Learning; machine learning (ML); Male; Raman spectra; Raman spectroscopy; Raman spectroscopy (RS); Rats; Rats, Sprague-Dawley; Retina; Retina - diagnostic imaging; Retina - pathology; Retinopathy; Spectroscopic analysis; Spectroscopy; Spectrum Analysis, Raman; Streptozocin; Transmission electron microscopy; Raman spectroscopy (RS); machine learning (ML); diabetic retinopathy (DR)
• ISSN: 1864-063X; 1864-0648; 1864-0648
• DOI: 10.1002/jbio.202400115

Vision impairment caused by diabetic retinopathy (DR) is often irreversible, making early‐stage diagnosis imperative. Raman spectroscopy emerges as a powerful tool, capable of providing molecular fingerprints of tissues. This study employs RS to detect ex vivo retinal tissue from diabetic rats at various stages of the disease. Transmission electron microscopy was utilized to reveal the ultrastructural changes in retinal tissue. Following spectral preprocessing of the acquired data, the random forest and orthogonal partial least squares‐discriminant analysis algorithms were employed for spectral data analysis. The entirety of Raman spectra and all annotated bands accurately and distinctly differentiate all animal groups, and can identify significant molecules from the spectral data. Bands at 524, 1335, 543, and 435 cm−1 were found to be associated with the preproliferative phase of DR. Bands at 1045 and 1335 cm−1 were found to be associated with early stages of DR. Traditional imaging techniques exhibit certain limitations in the early diagnosis of diabetic retinopathy. This study confirms the potential of Raman spectroscopy for the early diagnosis of diabetic retinopathy at the animal level.