What can artificial intelligence teach us about the molecular mechanisms underlying disease?

Abstract

While molecular imaging with positron emission tomography or single-photon emission computed tomography already reports on tumour molecular mechanisms on a macroscopic scale, there is increasing evidence that there are multiple additional features within medical images that can further improve tumour characterization, treatment prediction and prognostication. Early reports have already revealed the power of radiomics to personalize and improve patient management and outcomes. What remains unclear is how these additional metrics relate to underlying molecular mechanisms of disease. Furthermore, the ability to deal with increasingly large amounts of data from medical images and beyond in a rapid, reproducible and transparent manner is essential for future clinical practice. Here, artificial intelligence (AI) may have an impact. AI encompasses a broad range of 'intelligent' functions performed by computers, including language processing, knowledge representation, problem solving and planning. While rule-based algorithms, e.g. computer-aided diagnosis, have been in use for medical imaging since the 1990s, the resurgent interest in AI is related to improvements in computing power and advances in machine learning (ML). In this review we consider why molecular and cellular processes are of interest and which processes have already been exposed to AI and ML methods as reported in the literature. Non-small-cell lung cancer is used as an exemplar and the focus of this review as the most common tumour type in which AI and ML approaches have been tested and to illustrate some of the concepts.

Introduction to Radiomics

“…Radiomic features have also been suggested to predict clinical endpoints such as survival and treatment response, and, to be directly linked to genomic, transcriptomic, or proteomic characteristics (1,2,9). While even individual radiomic features may correlate with genomic data or clinical outcomes, the impact of radiomics is increased when the wealth of information that it provides -typically hundreds of features, a fraction of which will contribute to a disease-specific "radiomic signature"-is processed using machine learning techniques (10,11).…”

A bird’s-eye view of deep learning in bioimage analysis

“…Modern small-animal based anatomical, functional, and molecular imaging research involves a wide range of well-established as well as more experimental imaging modalities, including micro versions of clinical scanners (µCT, µMRI, µPET, µSPECT, µUS), optical coherence tomography (OCT), fluorescence molecular tomography (FMT), bioluminescence imaging (BLI), photoacoustic (PA) and thermoacoustic (TA) imaging, multispectral imaging (MSI), and others [93] , [158] , [159] . The use of deep learning for automated analysis of such imaging data is relatively uncharted territory, but recent studies have reported first applications in translational molecular imaging experiments [160] , [161] , [162] , [163] , [164] .…”

Longitudinal CT Imaging to Explore the Predictive Power of 3D Radiomic Tumour Heterogeneity in Precise Imaging of Mantle Cell Lymphoma (MCL)

“…Radiomics has shown promising results to analyze tumour heterogeneity using different imaging techniques, including artificial intelligence-based machine-learning algorithms [ 22 , 26 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ]. Taking into consideration the “whole tumour volume” assessment across the entire body instead of just a tiny sample from a single site, radiomic analysis might represent a non-invasive prediction approach to identify patients at high risk of relapse; early identification of these patients could allow modification of their therapeutic management to reduce unnecessary toxicity and improve prognosis according to follow-up studies [ 18 , 20 , 37 , 38 ]. There have been other studies on the diagnostic value of radiomics regarding different types of lymphoma and the reproducibility of CT texture parameters [ 31 , 33 , 35 , 39 , 40 ].…”