Development of a classification model for non‐alcoholic steatohepatitis (NASH) using confocal Raman micro‐spectroscopy. Issue 12 (21st June 2017)

• Record Type: Journal Article
• Authors: Yan, Jie; Yu, Yang; Kang, Jeon Woong; Tam, Zhi Yang; Xu, Shuoyu; Fong, Eliza Li Shan; Singh, Surya Pratap; Song, Ziwei; Tucker‐Kellogg, Lisa; So, Peter T. C.; Yu, Hanry
• Other Names: Luo Qingming guestEditor.
• Is Part Of: Journal of biophotonics. Volume 10:Issue 12(2017)
• Page Start: 1703
• Page End: 1713
• Publication Date: 2017-06-21
• Subjects: non-alcoholic fatty liver disease -- non-alcoholic steatohepatitis -- Raman micro-spectroscopic imaging -- biochemical component analysis -- model fitting; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.201600303
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract: Non‐alcoholic fatty liver disease (NAFLD) is the most common liver disorder in developed countries [1]. A subset of individuals with NAFLD progress to non‐alcoholic steatohepatitis (NASH), an advanced form of NAFLD which predisposes individuals to cirrhosis, liver failure and hepatocellular carcinoma. The current gold standard for NASH diagnosis and staging is based on histological evaluation, which is largely semi‐quantitative and subjective. To address the need for an automated and objective approach to NASH detection, we combined Raman micro‐spectroscopy and machine learning techniques to develop a classification model based on a well‐established NASH mouse model, using spectrum pre‐processing, biochemical component analysis (BCA) and logistic regression. By employing a selected pool of biochemical components, we identified biochemical changes specific to NASH and show that the classification model is capable of accurately detecting NASH (AUC=0.85–0.87) in mice. The unique biochemical fingerprint generated in this study may serve as a useful criterion to be leveraged for further validation in clinical samples. Abstract : Raman micro‐spectroscopy was used to detect and quantify NASH signatures on mice model tissue samples. Quantification of the signatures such as lipid content, using spectrum decomposition and machine learning techniques, revealed their spatiotemporal redistribution as the disease progresses. We identified biochemical changes specific to NASH and show that the classification model could accurately detect NASH (AUC=0.85–0.87). This model can be further validated in clinical samples.