Diagnosis of Liver Neoplasms by Computational and Statistical Image Analysis

Abstract

BackgroundDistinguishing well-differentiated hepatocellular carcinoma (WD-HCC), hepatocellular adenoma (HA) and non-neoplastic liver tissue (NNLT) solely on morphology is often challenging. The purpose of this study was to evaluate the use of computational image analysis to distinguish WD-HCC, HA and NNLT.MethodsSeventy-seven cases comprising of WD-HCC (n = 26), HA (n = 23) and NNLT (n = 28) were retrieved and reviewed. A total of 485 hematoxylin and eosin (H&E) photomicrographs (× 400, 0.09 µm2) of WD-HCC (n = 183), HA (n = 173), NNLT (n = 129) and nine whole-slide scans (three of each diagnosis) were obtained, color deconvoluted and digitally transformed. Quantitative data including nuclear density, nuclear sphericity, nuclear perimeter, and nuclear eccentricity from each image were acquired. The data were analyzed by one-way analysis of variance (ANOVA) with Tukey post hoc test, followed by unsupervised and supervised (Chi-square automatic interaction detection (CHAID)) cluster analysis.ResultsUnsupervised cluster analysis identified three well defined clusters of WD-HCC, HA and NNLT. Employing the four most discriminating nuclear features, supervised analysis was performed on a training set of 383 images, and validated on the remaining 102 test images. The analysis identified WD-HCC (sensitivity 100%, specificity 98%), HA (sensitivity 71%, specificity 85%) and NNLT (sensitivity 70%, specificity 86%). An analysis of whole-slide images identified WD-HCC with sensitivity and specificity of 100%.ConclusionsWe have successfully demonstrated that computational image analysis of nuclear features can differentiate WD-HCC from non-malignant liver with high accuracy, and can be used to assist in the histopathological diagnosis of hepatocellular carcinoma.

Nuclear morphometry and chromatin texture changes in hepatocellular carcinoma samples may predict outcomes of liver transplanted patients

“…Changes in chromatin texture are frequent in tumor cells and may be associated with disease progression [ 8 ]. The investigation of these nuclear modifications has already been initiated in different types of neoplasms, including HCC [ 9 – 11 ], melanoma [ 12 ], lung squamous cell carcinoma [ 13 ], and basal cell carcinoma [ 14 ], all of which compare neoplastic and healthy nuclei. However, we are not aware of the use of digital analysis in the investigation of nuclear alterations in a cohort such as the one in this study, HCC samples from liver transplantation patients.…”

Evolution of the liver biopsy and its future

“…Aside from the measurement of fibrosis, the application of DIA and AI techniques to liver biopsies has been limited. ML has been used to evaluate characteristics of nuclei to differentiate benign from malignant lesions in the liver (133). From a diagnostic standpoint, there could be a role for ML in the differentiation of medical liver diseases which may appear similar upon routine histopathologic examination, such as drug-induced liver injury and autoimmune hepatitis, among others (Figure 5).…”

Nuclear Morphometry and Chromatin Texture Changes in Hepatocellular Carcinoma Samples May Predict Liver Transplant Patients’ Outcomes

“…Changes in chromatin texture are frequent in tumor cells and may be associated with disease progression [8]. The investigation of these nuclear modi cations has already been initiated in different types of neoplasms, including HCC [9][10][11], melanoma [12], lung squamous cell carcinoma [13], and basal cell carcinoma [14], all of which compare neoplastic and healthy nuclei. However, we are not aware of the use of digital analysis in the investigation of nuclear alterations in a cohort such as the one in this study, HCC samples from liver transplantation patients.…”