The Potential Role of Radiomics and Radiogenomics in Patient Stratification by Tumor Hypoxia Status
Date
2019
Authors
Marcu, L.G.
Forster, J.C.
Bezak, E.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Journal of the American College of Radiology, 2019; 16(9):1329-1337
Statement of Responsibility
Conference Name
Abstract
BACKGROUND:Despite the clinical knowledge accumulated over a century about tumor hypoxia, this biologic parameter remains a major challenge in cancer treatment. Patients presenting with hypoxic tumors are more resistant to radiotherapy and often poor responders to chemotherapy. Treatment failure because of hypoxia is, therefore, very common. Several methods have been trialed to measure and quantify tumor hypoxia, with varied success. Over the last couple of decades, hypoxia-specific functional imaging has started to play an important role in personalized treatment planning and delivery. Yet, there are no gold standards in place, owing to inter- and intrapatient phenotypic variations that further complicate the overall picture. The aim of the current article is to analyze, through the review of the literature, the potential role of radiomics and radiogenomics in patient stratification by tumor hypoxia status. METHODS:Search of literature published in English since 2000 was conducted using Medline. Additional articles were retrieved via pearling of identified literature. Publications were reviewed and summarized in text and in a tabulated format. RESULTS:Although still an immature area of science, radiomics has shown its potential in the quantification of hypoxia within the heterogeneous tumor, quantification of changes regarding the degree of hypoxia after radiotherapy and drug delivery, monitoring tumor response to anti-angiogenic therapy, and assisting with patient stratification and outcome prediction based on the hypoxic status. CONCLUSIONS:The lack of technique standardization to measure and quantify tumor hypoxia presents an opportunity for data mining and machine learning in radiogenomics.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2019 American College of Radiology