AI-based image analysis detects early organ damage

In the future, these findings could help adapt treatments earlier to prevent organ damage.

Lead author Dr Lisa Steinhelfer from the University of Munich said: “In an earlier study, we found that patients whose kidney function worsened after lutetium-177 PSMA therapy showed changes in kidney structure.

“Since it’s not feasible to routinely take tissue samples, we wanted to explore whether these changes could be detected using less invasive methods.”

In their latest study, researchers from the departments of radiology and nuclear medicine at TUM University Hospital evaluated data from 121 patients undergoing treatment for prostate cancer with lutetium-177 PSMA.

This radioligand therapy—a targeted form of nuclear medicine—is relatively new and shows promise for treating specific tumor types. However, one potential side effect is a decline in kidney function over the course of treatment.

Dr Steinhelfer and her colleagues opted for an approach that does not place any additional burden on patients. CT scans and blood tests are part of standard cancer care in order to monitor treatment progress.

The Munich researchers examined various indicators in these routinely collected data to find early signs of kidney damage.

While factors such as kidney length or patient age did not yield reliable predictions, changes in kidney volume proved to be a strong signal: when kidney volume decreased by 10 per cent or more within six months of starting treatment, there was a high likelihood that kidney function would decline significantly within an additional six months.

Prof Matthias Eiber is one of the study’s senior authors, alongside Prof. Rickmer Braren.

Eiber said: “These changes in kidney volume are very subtle.

“They can easily be missed during routine image assessments because clinicians are mainly focused on tracking tumors and other critical findings.

“In contrast, image analysis algorithms—if properly trained—can reliably detect even these minor changes,” added Dr Friederike Jungmann, who shares first authorship with Dr Steinhelfer.

Steinhelfer said: “If it becomes clear that a patient is at increased risk of kidney impairment after six months of treatment, both the number of therapy cycles and the dosage can be individually adjusted.

“This would allow for a more personalised treatment approach.”