Response modeling enters AstraZeneca PSMA research
Nucs AI will adapt and validate image-based AI models for metastatic castration-resistant prostate cancer research involving PSMA-targeted radioconjugates.
Nucs AI is collaborating with AstraZeneca to develop AI-driven response-prediction models for research involving a PSMA-targeted radioconjugate. The work focuses on metastatic prostate cancer and image-based predictive biomarkers.
The collaboration will adapt and validate a Nucs AI product for emerging radioconjugates in metastatic castration-resistant prostate cancer. Nucs AI said the work will tune response-prediction models to the characteristics of next-generation therapies.
The company framed the project around a shift from population-level eligibility criteria toward individual-specific response prediction. Its announcement said the goal is to predict which patients may respond to a therapy rather than only confirm whether the target is present.
SelectPSMA is the relevant Nucs AI product family for response prediction. The company says the software analyzes PSMA PET/CT scans to identify patients most likely to benefit from PSMA-targeted radioligand therapy.
Nucs AI’s SelectPSMA page states that the tool is investigational and has not been cleared or approved by the FDA or any other regulatory body. It is not intended for clinical diagnostic use.
The company’s broader PSMA platform also includes DeepPSMA for whole-body tumor-burden quantification and TrackPSMA for automated treatment-response evaluation. Nucs AI said these tools form the basis of its precision-medicine work for therapeutic radioconjugates.
AstraZeneca has been building its radioconjugate portfolio. In 2024, the company completed its acquisition of Fusion Pharmaceuticals, adding FPI-2265, an actinium-225-based PSMA-targeting radioconjugate in phase II development for metastatic castration-resistant prostate cancer.
The Nucs AI announcement did not disclose financial terms, trial timelines, or regulatory plans for the collaboration.
Companies:Nucs AI, AstraZeneca, Fusion Pharmaceuticals
About the author
RadiologySignal.com writersEditorial Team
Radiology Signal Staff covers developments across medical imaging, radiology AI, imaging informatics, clinical research, and radiology business. The team monitors primary sources, peer-reviewed studies, company announcements, society updates, and healthcare industry news to deliver concise reporting for imaging professionals.
More from this section
MIM KineticID awaits FDA review for dynamic PET
GE HealthCare said the kinetic-modeling software is designed for 4D visualization, Patlak analysis, curve fitting, and tracer-behavior assessment across PET systems.
GE 3T scanner anchors UC imaging R&D center
The University of Cincinnati opened the Imaging Research & Development Center with UC Health, Cincinnati Children’s, GE HealthCare, and JobsOhio.
NewVue folds reporting into Radiologist Cockpit
The update puts clinical context, EHR data retrieval, generative dictation, and critical-result routing inside one interpretation workspace.
Hermia dosimetry update enters Canadian market
Health Canada approval covers Hermia SIRT and Hermia Lung Lobe Quantification, extending clinical use of the molecular imaging platform in Canada.
Disney themes enter Philips pediatric MRI rooms
Philips said Disney content is being incorporated into Ambient Experience for MRI across 87 countries, with study data showing lower stress and fewer scan pauses in younger children.
SubtleHD-PET clearance targets low-count PET scans
Subtle Medical said the software can enhance PET images from accelerated acquisitions and supports PET/CT and PET/MR systems across FDA-approved radiotracers.
AI-savvy trainees show mixed signals on radiology careers
A Canadian survey found that trainees with stronger AI knowledge were more likely to consider radiology, but also more likely to report discouragement tied to AI uncertainty.
UTA grant work sharpens deep-tissue vascular imaging
NIH-funded research led by Baohong Yuan is developing super-resolution tomographic imaging for clearer visualization of biological structures several centimeters below the skin.
SimonMed highlights role in large global X-ray AI study
The study analyzed 258,373 X-rays from 100 medical centers across 26 countries and evaluated the Rayvolve AI Suite across trauma, chest, measurement, and bone age use cases.
Former RadNet CTO joins Neurophet as scientific advisor
The neuroradiologist and former RadNet CTO will advise the neuroimaging AI company as it seeks to strengthen clinical validation and U.S. market expansion.
CMR-CLIP AI model interprets cardiac MRI scans with high accuracy
The model was trained on more than 13,000 cardiac MRI studies and linked moving heart images with clinical radiology reports, according to the research team.
Flywheel-AWS link creates governed imaging layer for trials
The integration combines AWS HealthImaging’s cloud-based DICOM storage with Flywheel’s imaging data orchestration tools for clinical trials, research, and AI development.