Radiomics based on artificial intelligence in liver diseases: where are we?

Abstract

Radiomics uses computers to extract a large amount of information from different types of images, form various quantifiable features, and select relevant features using artificial-intelligence algorithms to build models, in order to predict the outcomes of clinical problems (such as diagnosis, treatment, prognosis, etc.). The study of liver diseases by radiomics will contribute to early diagnosis and treatment of liver diseases and improve survival and cure rates of liver diseases. This field is currently in the ascendant and may have great development in the future. Therefore, we summarize the progress of current research in this article and then point out the related deficiencies and the direction of future research.

State of the Art in Artificial Intelligence and Radiomics in Hepatocellular Carcinoma

“…In clinical practice, the main feature to characterize HCC is its pattern of arterial phase hyperenhancement and venous or delayed phase washout on contrast-enhanced CT and/or MRI [ 1 ]. Even though this behavior is the hallmark of HCC, other hypervascular benign and malignant lesions can pose differential diagnosis problems [ 9 ]. Guidelines establish using US in the surveillance of healthy and cirrhotic patients with nodules smaller than one centimeter, while CT and MRI can be used to characterize suspicious lesions.…”

“…In this setting, several artificial intelligence (AI) technologies are emerging in recent years as very promising in genetic and histological characterization of HCC from medical imaging. AI and machine learning (ML) are able to build quantitative models from radiological exams, aiming to predict the outcomes to different clinical problems [ 8 , 9 ]. In this review, we will provide an overview of ML principles and of recent studies which have applied AI algorithms to HCC imaging for lesion segmentation, diagnosis, grading, prognosis and treatment response prediction.…”

A novel radiomics signature based on T2-weighted imaging accurately predicts hepatic inflammation in individuals with biopsy-proven nonalcoholic fatty liver disease: a derivation and independent validation study

“…In 2012, Lambin et al (20) proposed the approach of radiomics, which allows the extraction of numerous quantitative features from radiographic medical imaging. Although radiomics is mostly used to analyze tumors or tumor-like lesions, it can also be applied to non-neoplastic diseases (21). Recent radiomics techniques have shown excellent capability to non-invasively assess liver fibrosis (22,23).…”

Radiogenomics of gastroenterological cancer: The dawn of personalized medicine with artificial intelligence‐based image analysis

“…Radiomics is one of the current goals of method (3). Radiomics is a research field that extracts several tens of thousands of image features from images using mathematical methods, such as morphology/histogram/texture analysis, and compares them with other clinical information.…”