Differentiating Hepatic Epithelioid Angiomyolipoma From Hepatocellular Carcinoma and Focal Nodular Hyperplasia via Radiomics Models.

Wenjie Liang,Xiuming Zhang,Qiang Huang,Wuwei Tian,Shijian Ruan,Yong Ding,Dalong Wan,Jiayuan Shao,Weihai Liu,Wenbo Xiao

doi:10.3389/fonc.2020.564307

Abstract

Background: We conduct a study in developing and validating two radiomics-based models to preoperatively distinguish hepatic epithelioid angiomyolipoma (HEAML) from hepatic carcinoma (HCC) as well as focal nodular hyperplasia (FNH).Methods: Totally, preoperative contrast-enhanced computed tomography (CT) data of 170 patients and preoperative contrast-enhanced magnetic resonance imaging (MRI) data of 137 patients were enrolled in this study. Quantitative texture features and wavelet features were extracted from the regions of interest (ROIs) of each patient imaging data. Then two radiomics signatures were constructed based on CT and MRI radiomics features, respectively, using the random forest (RF) algorithm. By integrating radiomics signatures with clinical characteristics, two radiomics-based fusion models were established through multivariate linear regression and 10-fold cross-validation. Finally, two diagnostic nomograms were built to facilitate the clinical application of the fusion models.Results: The radiomics signatures based on the RF algorithm achieved the optimal predictive performance in both CT and MRI data. The area under the receiver operating characteristic curves (AUCs) reached 0.996, 0.879, 0.999, and 0.925 for the training as well as test cohort from CT and MRI data, respectively. Then, two fusion models simultaneously integrated clinical characteristics achieved average AUCs of 0.966 (CT data) and 0.971 (MRI data) with 10-fold cross-validation. Through decision curve analysis, the fusion models were proved to be excellent models to distinguish HEAML from HCC and FNH in comparison between the clinical models and radiomics signatures.Conclusions: Two radiomics-based models derived from CT and MRI images, respectively, performed well in distinguishing HEAML from HCC and FNH and might be potential diagnostic tools to formulate individualized treatment strategies.

Highlights

Preoperative evaluation of liver tumors sometimes remains a challenge for clinicians
The inclusion criteria for the patients were as follows: [1] Hepatic epithelioid angiomyolipoma (HEAML), hepatocellular carcinoma (HCC), and focal nodular hyperplasia (FNH) diagnosed pathologically by surgical resection or biopsy; [2] contrast-enhanced computed tomography (CT) or magnetic resonance imaging (MRI) scans performed within 1 month before operation; [3] complete imaging data for further analysis
The texture features included 5 features extracted from the neighborhood gray-tone difference matrix (NGTDM), 13 from the gray-level size zone matrix (GLSZM), 13 from the graylevel run-length matrix (GLRLM), and 9 from the gray-level cooccurrence matrix (GLCM)

Summary

Introduction

Preoperative evaluation of liver tumors sometimes remains a challenge for clinicians. Clinicians need to evaluate plenty of hepatic lesions to implement individualized diagnosis, treatments and follow-up strategies for the patients. As a special subtype of angiomyolipoma, HEAML without visible fat is confused with other blood-rich hepatic masses, including HCC and focal nodular hyperplasia (FNH) [3]. It is vital to precisely distinguish HEAML from non-HEAML hepatic lesions because diagnostic evaluation is an important prerequisite for implementing individualized treatment strategies. According to the diagnosis and treatment guidelines, patients with HCC can individually undergo radiation therapy, surgical resection or transarterial chemoembolization after overall clinical evaluation. We conduct a study in developing and validating two radiomics-based models to preoperatively distinguish hepatic epithelioid angiomyolipoma (HEAML) from hepatic carcinoma (HCC) as well as focal nodular hyperplasia (FNH)

Methods

Results

Conclusion