Quantification of hepatic steatosis in histologic images by deep learning method

Article type: Research Article

Authors: Yang, Fan^{b; c} | Jia, Xianyuan^{b; c} | Lei, Pinggui^{a; 1; *} | He, Yan^{b; c} | Xiang, Yining^d | Jiao, Jun^{a; 1} | Zhou, Shi^a | Qian, Wei^e | Duan, Qinghong^a

Affiliations: [a] Department of Radiology, The Affiliated Hospital of Guizhou Medical University, Guiyang, Guizhou Province, China | [b] School of Biology & Engineering, Guizhou Medical University, Guiyang, Guizhou Province, China | [c] Key Laboratory of Biology and Medical Engineering, Guizhou Medical University, Guiyang, Guizhou Province, China | [d] Department of Pathology, The Affiliated Hospital of Guizhou Medical University, Guiyang, Guizhou Province, China | [e] Department of Electrical and Computer Engineering, College of Engineering, University of Texas, El Paso, TX, USA

Correspondence: [*] Corresponding author: Pinggui Lei, MD. PhD., Department of Radiology, the Affiliated Hospital of Guizhou Medical University. No.28, Guiyi Street, Yunyan District, Guiyang of Guizhou 550004, China. E-mail: [email protected].

Note: [1] Equal contributors.

Abstract: OBJECTIVE:To develop and test a novel method for automatic quantification of hepatic steatosis in histologic images based on the deep learning scheme designed to predict the fat ratio directly, which aims to improve accuracy in diagnosis of non-alcoholic fatty liver disease (NAFLD) with objective assessment of the severity of hepatic steatosis instead of subjective visual estimation. MATERIALS AND METHODS:Thirty-six 8-week old New Zealand white rabbits of both sexes were fed with high-cholesterol, high-fat diet and sacrificed under deep anesthesia at various time points to obtain the pathological specimen. All rabbits were performed by multislice computed tomography for surveillance to measure density changes of liver parenchyma. A deep learning scheme using a convolutional neural network was developed to directly predict the liver fat ratio based on the pathological images. The average error value, standard deviation, and accuracy (error <5%) were evaluated and compared between the deep learning scheme and manual segmentation results. The Pearson’s correlation coefficient was also calculated in this study. RESULTS:The deep learning scheme performs successfully on rabbit liver histologic data, showing a high degree of accuracy and stability. The average error value, standard deviation, and accuracy (error <5%) were 3.21%, 4.02%, and 79.10% for the cropped images, 2.22%, 1.92%, and 88.34% for the original images, respectively. The strong positive correlation was also observed for cropped images (R = 0.9227) and original images (R = 0.9255) in comparison to labeled fat ratio. CONCLUSIONS:This new deep learning scheme may aid in the quantification of steatosis in the liver and facilitate its treatment by providing an earlier clinical diagnosis.

Keywords: Quantitative assessment, hepatic steatosis, NAFLD, convolutional neural network, deep learning

DOI: 10.3233/XST-190570

Journal: Journal of X-Ray Science and Technology, vol. 27, no. 6, pp. 1033-1045, 2019