DAILYPHARMA | 07.18.2022 – 12:53
The bone scan, ultrasound or magnetic resonance are some of the diagnostic techniques that allow obtaining internal images of an individual and thus detect the presence of diseases, their extension and degree of involvement, and thus be able to precisely establish the best therapeutic approach. However, despite advances in the resolution of medical images, there is still relevant information for clinical decision making that is not visible to the observer.
Radiomics is an omics science that extracts, by means of computational algorithms, quantitative parameters in medical images to detect and measure those characteristics that cannot be appreciated by direct observation, called “radiomic characteristics”, with the aim of associating them with specific physiological states.
In this sense, the Foundation Roche Institute has published the ‘Anticipating Report: Radiomics’, prepared by the Observatory of Trends in Medicine of the Future. In the words of the vice president of the Fundación Instituto RocheFederico Plaza, “Computational advances and the current extensive digital development make it possible to generate information through radiomics, thus contributing medical imaging to the development of Personalized Precision Medicine (PPM)”.
Thanks to its ability to analyze large amounts of data, radiomics is a highly relevant source of information with a view to deepening our knowledge of the biological and functional diversity of tissues, the heterogeneity of pathological phenomena and the foreseeable evolution of diseases. diseases. This is explained by the coordinator of the Report and director of the Medical Imaging Clinical Area of the Hospital Universitario y Politécnico La Fe, Luis Martí-Bonmatí: “When we study a pancreatic tumor with a CT scan, in addition to the radiologist reporting its size and resectability, radiomics studies on these images will tell us with greater precision whether or not the patient is susceptible to surgery if you are going to develop a short-term recurrence or metastasis in the next three months.”
This type of information is unattainable to the eye of the radiologist, which is why, as the expert points out, the combination of the classic radiological reading with this new “hidden” radiomics information, which gives us information to estimate events that are going to happen to the patient , contributes to a greater precision and personalization of the management of the patients and the design of the most appropriate therapeutic approach.
This omics science is presented as a support tool in research and clinical practice. According to the coordinator of the Report, it offers multiple applications in areas such as oncology, rheumatological or neurodegenerative diseases. “For example, through images of the liver and the tumor we can know if hepatic metastases are going to develop in the short term. Thus, it makes it possible to see very subtle changes in the image that are related to pre-metastatic niches, it can even detect alterations before the lesions are macroscopically evident to the radiologist, and this greatly changes the staging of patients”.
In addition, as Martí-Bonmatí points out, “it also allows us to analyze the heterogeneity of the lesions. When we look at lesions, radiologists are very good at knowing their size, shape, and structure, but we don’t recognize that within them there are clusters of cells that have very different aggressive characteristics.”
Radiomics offers the opportunity to obtain a greater amount of information from medical images, contributing to the development of applications for the diagnosis and prediction of risk of events, support in decision-making and monitoring of treatments, or even of complementary diagnosis (companion diagnostic) through the identification of different phenotypes in patients and their stratification once morest a treatment. “Before giving a drug, an image of the patient should be obtained to guarantee that the effect of the drug is as expected, that it will be effective. Radiomics acts as a complementary and necessary diagnostic tool”, she remarks.
Radiomics is useful in optimizing clinical research since it can be used, for example, in the re-analysis of images from clinical trials to detect methodological biases, such as incorrect patient selection; or used as a predictive tool for clinical events such as the appearance of metastases a posteriori. Likewise, the physician specifies that he can provide more reliable information than that obtained with other procedures such as biopsy, in which the study sample is very small and does not always represent the entire tissue or lesion. “The biopsy may not be enough when it comes to selecting the best candidates for the administration of a targeted or very specific drug because it only samples a part of the tumor or because there are metastatic tumors where the metastasis no longer has the same expression as the tumor. Primary,” he explains.
Despite having developed much of its potential, this omics science is in an exploratory and evidence-generating phase, in which it is necessary to address challenges of a different nature for its translation into clinical practice. These include the great variability in the normalization processes and analysis of radiomics characteristics, the lack of knowledge regarding the clinical potential of radiomics as a tool for healthcare practice, as well as the limited access to medical image banks and derived data. of radiomic analysis for reasons of security and data protection. However, Martí-Bonmatí points out that the main challenge is to harmonize the images. “We want them to be comparable, so that we can extract metrics that do not depend on which equipment we have acquired them with,” she says.
The managing director of the Roche Institute Foundation, Consuelo Martín de Dios, recalls that with the development of new computational technologies that allow radiomics information to be obtained, “a disruptive advance in medicine has been achieved. Radiomics aims to report the predisposition, presence or prognosis of diseases and can be used to select patients who are candidates for treatment and offer them better therapeutic options in a personalized way”.
Follow us on social networks
