Combining Hepatic and Splenic CT Radiomic Features Improves Radiomic Analysis Performance for Liver Fibrosis Staging

Abstract

Background: The exact focus of computed tomography (CT)-based artificial intelligence techniques when staging liver fibrosis is still not exactly known. This study aimed to determine both the added value of splenic information to hepatic information, and the correlation between important radiomic features and information exploited by deep learning models for liver fibrosis staging by CT-based radiomics. Methods: The study design is retrospective. Radiomic features were extracted from both liver and spleen on portal venous phase CT images of 252 consecutive patients with histologically proven liver fibrosis stages between 2006 and 2018. The radiomics analyses for liver fibrosis staging were done by hepatic and hepatic–splenic features, respectively. The most predictive radiomic features were automatically selected by machine learning models. Results: When using splenic–hepatic features in the CT-based radiomics analysis, the average accuracy rates for significant fibrosis, advanced fibrosis, and cirrhosis were 88%, 82%, and 86%, and area under the receiver operating characteristic curves (AUCs) were 0.92, 0.81, and 0.85. The AUC of hepatic–splenic-based radiomics analysis with the ensemble classifier was 7% larger than that of hepatic-based analysis (p < 0.05). The most important features selected by machine learning models included both hepatic and splenic features, and they were consistent with the location maps indicating the focus of deep learning when predicting liver fibrosis stage. Conclusions: Adding CT-based splenic radiomic features to hepatic radiomic features increases radiomics analysis performance for liver fibrosis staging. The most important features of the radiomics analysis were consistent with the information exploited by deep learning.

Diagnosis of Liver Fibrosis Using Artificial Intelligence: A Systematic Review

“…The model can show which types of symptoms on images are more essential to the model, and the results paralleled previous research. This means that the current radiomic analysis results might supplement the Grad-cam location maps by demonstrating the emphasis of DLS for predicting liver fibrosis stages [ 24 ].…”

“…This integration of clinical features (e.g., BMI, laboratory markers, gender, and comorbidities) along with the non-invasive procedures as input to the AI classifier with great diagnostic results has been successfully achieved in other studies [ 33 , 39 ]. Radiomics feature selection in combination with ML algorithms has been used, with ROI or VOI selection from 2D-SWE and DWI-MRI images made by experienced radiologists [ 24 , 41 , 43 ].…”

Multi-organ Radiomics-Based Prediction of Future Remnant Liver Hypertrophy Following Portal Vein Embolization

“…Second, imaging data of the spleen was added to the presented radiomics approach, since it is known that molecular factors regulated by the spleen affect liver cirrhosis and the potential of liver regeneration, 43 , 44 and that splenic imaging parameters can support the prediction of liver-associated disease such as portal hypertension. 45 , 46 Third, bone marrow imaging data were included in the radiomics model, since it is known that stem cells/bone marrow-derived liver sinusoidal endothelial cells (LSEC) contribute to liver regeneration, 47 , 48 although the exact ways of mechanisms remain unknown, 49 and bone marrow suppression hinders adequate liver regeneration after partial hepatectomy. 50 Interestingly, our analysis identified each independent radiomic feature per organ (liver, spleen, bone marrow) to be predictive for FRL hypertrophy, potentially reflecting the addressed underlying mechanisms of liver hypertrophy and liver–spleen–bone marrow crosstalk.…”

Radiobioinformatics: A novel bridge between basic research and clinical practice for clinical decision support in diffuse liver diseases

“…Machine learning algorithms are powerful tools for processing and modeling large amounts of omics data. Indeed, the application of machine learning to radiomics has produced gratifying results for diffuse liver diseases, such as diagnosis of liver fibrosis staging [149],…”

“…Machine learning algorithms are powerful tools for processing and modeling large amounts of omics data. Indeed, the application of machine learning to radiomics has produced gratifying results for diffuse liver diseases, such as diagnosis of liver fibrosis staging [149], inflammatory activity grading [150], and differentiation of a healthy liver from hepatic steatosis, cirrhosis, amiodarone deposition, and iron overload [87]. Recent studies have proposed targeted metabolomics with machine learning to identify metabolites that distinguish the progression of NAFLD [151, 152].…”