Beyond Geometry: How Biomarkers and AI Are Redefining Personalization in Radiation Oncology

For decades, radiation therapy was defined by a question of millimeters—using ever more sophisticated imaging and planning to hit tumors accurately while sparing nearby organs at risk. Now, the discipline is on the cusp of a fundamental shift in which biological insight is beginning to complement, and in some cases challenge, its traditional focus on geometric precision.

The transition was the central theme of a GE HealthCare查看公司主页-sponsored symposium at the European Society for Radiotherapy and Oncology (搜索)搜索该词条 (ESTRO) Congress in Stockholm, where three academic radiation oncology researchers explained how imaging biomarkers, hidden biological variables, and artificial intelligence could help make radiotherapy more adaptive and more individualized.

Moderated by Ilya Gipp, MD, PhD, GE HealthCare查看公司主页's Chief Medical Officer for Oncology, the session underscored one consistent message: progress will depend on understanding tumor biology, response variability, and clinically useful biomarkers, rather than simply refining dose delivery alone.

Imaging biomarkers: untapped potential and cautious optimism

Claudio Fiorino, a senior medical physicist at San Raffaele Scientific Institute in Milan, highlighted the potential of Quantitative Imaging Biomarkers (QIBs)—numerical features extracted from routine imaging that correlate with biology or outcomes. Since radiotherapy already depends on CT, MRI, and PET scans throughout planning and treatment, these data represent readily available sources of biomarkers that could potentially predict toxicity, response, and outcomes without the need for new tests.

"Medical images are available without additional cost for all patients," said Fiorino, "and they can capture a lot of characteristics."

Fiorino described how San Raffaele clinicians analyzed CT densitometry measurements from planning CT scans of more than 1,500 patients for evidence that cardiac calcification scores predict cardiac events. They also examined lung density measures and fat percentages from CT scans to predict patient outcomes.

However, Fiorino sounded a note of caution about the clinical readiness of QIBs, warning that the "so-called variability" of radiomic features presents a significant challenge. Uncertainty is introduced at every stage of the imaging workflow, from acquisition to feature computation. He cited an influential radiomics survival model that later inspired another study driven largely by tumor volume, establishing a set of safeguards designed to improve current radiomic methodologies. Despite these challenges, Fiorino ended on an optimistic note: "We have examples of robust biomarkers we can trust."

Hidden biology and the risk of inequity

While Fiorino drew attention to imaging's untapped potential, Laure Marignol, Professor in Radiation Biology at Trinity College Dublin, focused on what standard workflows still fail to capture. She argued that some of the most important drivers of response remain biologically hidden, including hypoxia, DNA damage response, immune activity, inflammation, host factors, and chromosomal instability.

"Patients may receive the same dose, but they are not biologically equivalent," Marignol said.

The discipline has "largely mastered" geometry, imaging guidance, and anatomical targeting, she noted. "We really know very well where to treat. The next challenge is understanding who we are truly treating biologically."

Marignol warned that ignoring biology results in standardized treatment decisions that mask important differences between patients and populations. Citing sex as an underused variable, she noted that around 30% of male tumors have lost the Y chromosome, a phenomenon that might affect repair, survival, and immune response. Yet in a review of 321 radiation oncology papers, fewer than half included sex in the analysis, while only two separated outcomes by sex.

"These hidden variables matter," she said. "Precision radiotherapy without biology risks inequity."

Tumor heterogeneity and the next frontier

Robert Jeraj, Professor of Medical Physics, Human Oncology, Radiology and Biomedical Engineering at the University of Wisconsin-Madison, leaned further into the problem of tumor heterogeneity. He shared examples of spatial heterogeneity within single tumors—intra-lesion heterogeneity—and variable responses among multiple lesions—inter-lesion heterogeneity—in metastatic disease. These phenomena undermine one-size-fits-all assumptions about tumor response and raise the possibility of adapting treatment not just between patients, but within the tumor itself, such as through biologically-targeted radiotherapy or "dose painting," and between lesions over time.

Jeraj emphasized that QIBs have a role to play in addressing this challenge, since the modality is inherently spatio-temporal, allowing clinicians to understand how a tumor behaves in space and how its behavior changes during treatment. "Quantitative imaging allows us to uncover this heterogeneity," he said.

Yet identifying heterogeneity is only one part of the problem. "Combining systemic and local therapy, such as radiation therapy, is key," Jeraj concluded, pointing toward a future where integrated treatment strategies address the biological complexity that imaging reveals.

A connected, AI-enabled future

The symposium's insights align with broader trends reshaping radiation oncology. As molecular imaging, targeted therapies, and adaptive radiotherapy evolve, the field is becoming a central, data-driven component of multidisciplinary oncology. AI-powered tools, radiomics, and genomics are enabling treatment plans to evolve based on tumor biology and patient response—marking a shift from static planning to dynamic, adaptive radiotherapy.

Sampath Kandala, General Manager of Therapy Guidance at GE HealthCare查看公司主页, captured the moment: "We are entering a defining moment where advances in science, imaging, and data are converging—not just to improve precision, but to fundamentally expand the role of radiation oncology within an integrated cancer care ecosystem."

The challenge ahead lies not in individual breakthroughs, but in how effectively organizations connect imaging, treatment planning, therapy delivery, and longitudinal patient data into unified, interoperable care pathways that deliver on the promise of truly personalized radiation oncology.