Dosiomics in the analysis of medical images and prospects for its use in clinical practice

Abstract

BACKGROUND: In recent years, there has been a notable increase in the number of articles using the term “dosiomics”. However, there are no literature reviews on this topic in the Russian language. AIM: This study aims to describe the basic principles of dosiomics as a derivative of radiomics and to analyze studies devoted to assessing the possibilities of its application in clinical practice. MATERIALS AND METHODS: A systematic literature search was performed in the PubMed database using the search query “dosiomics OR dosiomic”, and in the eLibrary database using the search query “dosiomics”. By April 2023, 43 foreign articles and 1 Russian article had been published. RESULTS: The analysis encompassed 43 foreign studies investigating the use of dosiomics in clinical practice, alongside one Russian article that provided a definition of the term “dosiomics”. The analyzed papers were divided into three groups according to their subject matter, and two tables describing the results of 27 studies on the prediction of clinical outcomes were created. CONCLUSION: Currently, dosiomics is a new and promising derivative of radiomics used in the textural analysis of medical images associated with radiation treatment of cancer patients. Dosiomics can contribute to the development of a more personalized approach to the planning of radiotherapy, the prediction of radiation damage of normal tissues, and the diagnosis of recurrence.

Keywords

• dosiomics
• radiomics
• radiation therapy
• machine learning
• artificial intelligence
• texture analysis
• radiation pneumonitis