Abstract
Over the last decade there has been an extensive evolution in the Artificial Intelligence (AI) field. Modern radiation oncology is based on the exploitation of advanced computational methods aiming to personalization and high diagnostic and therapeutic precision. The quantity of the available imaging data and the increased developments of Machine Learning (ML), particularly Deep Learning (DL), triggered the research on uncovering "hidden" biomarkers and quantitative features from anatomical and functional medical images. Deep Neural Networks (DNN) have achieved outstanding performance and broad implementation in image processing tasks. Lately, DNNs have been considered for radiomics and their potentials for explainable AI (XAI) may help classification and prediction in clinical practice. However, most of them are using limited datasets and lack generalized applicability. In this study we review the basics of radiomics feature extraction, DNNs in image analysis, and major interpretability methods that help enable explainable AI. Furthermore, we discuss the crucial requirement of multicenter recruitment of large datasets, increasing the biomarkers variability, so as to establish the potential clinical value of radiomics and the development of robust explainable AI models.
Highlights
Besides automation in different stages of image processing, machine learning (ML)/deep learning (DL) opened a new era in clinical oncology, providing a more exhaustive and fast extraction of features from the diagnostic data, including some that may not be directly captured by the naked eye, including the expertly trained one
In this review we present an overview of the state-of-the-art of Deep Neural Networks (DNNs) on oncological applications, using radiomics
The exploitation of imaging biomarkers and radiomics features provided a new metric for quantitative image analysis, aiming to support clinical decisions, in detection, characterization and treatment planning on several pathologies
Summary
Healthcare is expected to be highly impacted by machine learning (ML)-based artificial intelligence (AI). Besides automation in different stages of image processing, ML/DL opened a new era in clinical oncology, providing a more exhaustive and fast extraction of features from the diagnostic data, including some that may not be directly captured by the naked eye, including the expertly trained one. Quantification analysis of such features alongside with the combination of conventional anatomical and functional characteristics could further characterize tumors’ profiles such as aggressiveness or potential of response to therapy, thereby informing clinical decision [5,6]. There are still several limitations and challenges to be addressed in the clinical application of AI in oncology, including the explainability and interpretability of the models, the sensitivity of the features’ extraction, the reproducibility of the quan titative feature selection and the harmonization of the data
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.
