Abstract
Simple SummaryRadiomics has become a prominent component of medical imaging research and many studies show its specific value as a support tool for clinical decision-making processes. Radiomic data are typically analyzed with statistical and machine learning methods, which change depending on the disease context and the imaging modality. We found a certain bias in the literature towards the use of such methods and believe that this limitation may influence the capacity of producing accurate and reliable decisions. Therefore, in view of the relevance of various types of learning methods, we report their significance and discuss their unrevealed potential.Processing and modeling medical images have traditionally represented complex tasks requiring multidisciplinary collaboration. The advent of radiomics has assigned a central role to quantitative data analytics targeting medical image features algorithmically extracted from large volumes of images. Apart from the ultimate goal of supporting diagnostic, prognostic, and therapeutic decisions, radiomics is computationally attractive due to specific strengths: scalability, efficiency, and precision. Optimization is achieved by highly sophisticated statistical and machine learning algorithms, but it is especially deep learning that stands out as the leading inference approach. Various types of hybrid learning can be considered when building complex integrative approaches aimed to deliver gains in accuracy for both classification and prediction tasks. This perspective reviews some selected learning methods by focusing on both their significance for radiomics and their unveiled potential.
Highlights
Driven by the recent advancement of precision medicine, both pathology and radiology have undergone substantial transformation
The learning techniques that were presented in this perspective include only part of the methods and approaches that are available but share the main challenges usually faced in applications
The current focus is on the need of reconciling radiomic features retrieved from multiple imaging modalities and on integrating a variety of feature types aimed at providing improved predictive learning for specific targets
Summary
Driven by the recent advancement of precision medicine, both pathology and radiology have undergone substantial transformation. Among the most noticeable factors inducing change, there is the centrality assigned to data-driven integrative modeling approaches designed to leverage quantitative imaging. These aspects have characterized the field of radiomics, a discipline strongly based on developing methods and algorithms able to reveal subtle disease marks by processing features extracted from medical images. This latter point is quite surprising and suggests that the spectrum of radiomic approaches (from handcrafted to machine learning (ML) driven) may require further consideration. Radiomics uses a variety of ML methods that support inference and that may work standalone or be cast within integrative approaches, depending on the complexity of the context under study (cancer, diabetes, etc.). The progresses that have been made are mostly referred to: (i) Extracting computerized features from radiologic imaging, (ii) associating image features with molecular phenotypes (radiogenomics), and (iii) determining the relevance of radiologic features associated with pathologic phenotypes (radiopathomics)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
