Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats

Abstract

Although cancer often is referred to as “a disease of the genes,” it is indisputable that the (epi)genetic properties of individual cancer cells are highly variable, even within the same tumor. Hence, preexisting resistant clones will emerge and proliferate after therapeutic selection that targets sensitive clones. Herein, the authors propose that quantitative image analytics, known as “radiomics,” can be used to quantify and characterize this heterogeneity. Virtually every patient with cancer is imaged radiologically. Radiomics is predicated on the beliefs that these images reflect underlying pathophysiologies, and that they can be converted into mineable data for improved diagnosis, prognosis, prediction, and therapy monitoring. In the last decade, the radiomics of cancer has grown from a few laboratories to a worldwide enterprise. During this growth, radiomics has established a convention, wherein a large set of annotated image features (1‐2000 features) are extracted from segmented regions of interest and used to build classifier models to separate individual patients into their appropriate class (eg, indolent vs aggressive disease). An extension of this conventional radiomics is the application of “deep learning,” wherein convolutional neural networks can be used to detect the most informative regions and features without human intervention. A further extension of radiomics involves automatically segmenting informative subregions (“habitats”) within tumors, which can be linked to underlying tumor pathophysiology. The goal of the radiomics enterprise is to provide informed decision support for the practice of precision oncology.

Machine and deep learning methods for radiomics

“…The number of publications issued in the last years has grown almost exponentially. Although there are many review articles already about radiomics, its definition, technical details, and applications in different areas of medicine, the view of radiomics as an image mining tool lends itself naturally to application of machine/deep learning algorithms as computational instruments for advanced model building of radiomics‐based signatures . This will be the main subject of this article, addressing issues related to common applications in medical physics, standardization, feature extraction, model building, and validation.…”

Texture analysis of early cerebral tissue damage in magnetic resonance imaging of patients with lung cancer

“…In light of recent advances in the acquisition and analysis of MR images for the high-throughput extraction of imaging feature information, medical imaging can now be used to quantify the distinguishing features of tumor tissues (30)(31)(32). This approach is distinct from prior subjective or qualitative methods (14).…”

Open access image repositories: high-quality data to enable machine learning research

“…14,21 Image-derived features are considered more useful for cross-scale analyses, e.g., radiogenomics. 20,45,46 Machine learning is also being used to remove image artefacts and enhance image quality. 44 Machine learning algorithms, in particular deep learning methods, have shown promising results in analysis of digitised tissue specimens and better performance than most traditional image analysis techniques.…”

“…17e19 Deep learning based pipelines are also gaining increased acceptance and use in radiology. 14,20,21 Identifying quantitative imaging phenotypes across scale through the use of machine learning is a rapidly evolving approach to improve our understanding of cancer biology. 1,2 In 2010, the US National Cancer Institute realised that open access to radiological images and other supporting data such as demographics, outcomes, and clinical trial data were required to promote cancer research.…”