Leveraging radiomics and AI for precision diagnosis and prognostication of liver malignancies

Abstract

Liver tumors, whether primary or metastatic, have emerged as a growing concern with substantial global health implications. Timely identification and characterization of liver tumors are pivotal factors in order to provide optimum treatment. Imaging is a crucial part of the detection of liver tumors; however, conventional imaging has shortcomings in the proper characterization of these tumors which leads to the need for tissue biopsy. Artificial intelligence (AI) and radiomics have recently emerged as investigational opportunities with the potential to enhance the detection and characterization of liver lesions. These advancements offer opportunities for better diagnostic accuracy, prognostication, and thereby improving patient care. In particular, these techniques have the potential to predict the histopathology, genotype, and immunophenotype of tumors based on imaging data, hence providing guidance for personalized treatment of such tumors. In this review, we outline the progression and potential of AI in the field of liver oncology imaging, specifically emphasizing manual radiomic techniques and deep learning-based representations. We discuss how these tools can aid in clinical decision-making challenges. These challenges encompass a broad range of tasks, from prognosticating patient outcomes, differentiating benign treatment-related factors and actual disease progression, recognizing uncommon response patterns, and even predicting the genetic and molecular characteristics of the tumors. Lastly, we discuss the pitfalls, technical limitations and future direction of these AI-based techniques.

MRI Radiomics in Imaging of Focal Hepatic Lesions: A Narrative Review

“…Radiomics is a novel radiological technique that permits decrypting medical imaging into minable numerical data and extracting high-throughput quantitative imaging features beyond human assessment [ 2 ]. Large datasets with radiomic features allow for the improvement of liver imaging assessment through sophisticated statistical models such as artificial intelligence (AI) and machine learning [ 1 ]. These models help explain the features of tumors, guide therapy choices, and enable prompt modifications to treatment plans [ 1 ].…”

“…Focal hepatic lesions represent a heterogeneous set of benign and malignant tumors with different pathogeneses, clinical manifestations, and prognoses. It is common practice to employ magnetic resonance imaging (MRI) to identify, describe, and evaluate treatment responses for these lesions [ 1 ]. However, due to aberrant presentations, uncommon tumor development over time, and overlap in imaging characteristics, characterizing such lesions can be difficult [ 1 ].…”

“…It is common practice to employ magnetic resonance imaging (MRI) to identify, describe, and evaluate treatment responses for these lesions [ 1 ]. However, due to aberrant presentations, uncommon tumor development over time, and overlap in imaging characteristics, characterizing such lesions can be difficult [ 1 ]. Subjective interpretation, inconsistent definitions, and reader experience all have an impact on the qualitative assessment of imaging features, which might result in less-than-ideal inter-reader agreement [ 1 ].…”

“…However, due to aberrant presentations, uncommon tumor development over time, and overlap in imaging characteristics, characterizing such lesions can be difficult [ 1 ]. Subjective interpretation, inconsistent definitions, and reader experience all have an impact on the qualitative assessment of imaging features, which might result in less-than-ideal inter-reader agreement [ 1 ]. Differential diagnosis, predicting tumor aggressiveness, and assessing therapy response present difficulties for radiologists [ 1 ].…”

“…Subjective interpretation, inconsistent definitions, and reader experience all have an impact on the qualitative assessment of imaging features, which might result in less-than-ideal inter-reader agreement [ 1 ]. Differential diagnosis, predicting tumor aggressiveness, and assessing therapy response present difficulties for radiologists [ 1 ]. In recent years, various quantitative imaging methods have been proposed to overcome these difficulties.…”