Nucs AI has partnered with healthcare data specialist Segmed to accelerate the development and validation of artificial intelligence-powered imaging biomarkers for oncology using one of the world’s largest collections of real-world clinical and imaging data.

The collaboration will give Nucs AI access to Segmed’s network of de-identified imaging and clinical data from more than 2,800 healthcare partner sites, supporting the development of predictive biomarkers, real-world evidence studies and clinical intelligence tools for cancer care.

Segmed will also become Nucs AI’s preferred oncology data partner and has made a strategic investment in the company to support the development of disease registries, validation frameworks and research initiatives.

The partnership aims to address one of the biggest challenges facing AI in healthcare: ensuring predictive models perform reliably across diverse patient populations rather than within a single healthcare system or institution.

Real-world data is becoming increasingly important in oncology research, allowing developers to validate biomarkers and artificial intelligence models using patients treated in routine clinical practice rather than only within controlled clinical trials. Combining imaging with clinical outcomes can improve understanding of which patients are most likely to benefit from specific therapies, particularly as precision medicine and radiopharmaceutical treatments continue to expand.

Segmed’s data library includes more than 150 million imaging studies covering multiple cancer types, imaging modalities, treatment settings and geographic regions. According to the companies, the scale and diversity of the dataset will support the development of predictive imaging biomarkers designed to improve patient selection and treatment planning.

Nucs AI has already used data from more than 72,000 lesions to train and develop its existing AI models. Access to Segmed’s broader real-world datasets is expected to support expansion into additional cancer types, imaging technologies and clinical applications.

Nijat Ahmadov, chief executive officer of Nucs AI, said: “Models are not the bottleneck in precision medicine; data is. Specifically, diverse, multi-institutional data that pairs imaging with real clinical context and outcomes.”

He added that combining large-scale imaging with clinical outcome data would allow the company to focus on clinically important questions while improving the accuracy and applicability of its predictive models.

Jie Wu, co-founder and chief data officer at Segmed, said: “We have spent years building the data foundation that precision oncology requires. The next step has always been finding partners who know how to use it.”

The collaboration will also support the creation of disease-specific registries, curated research cohorts and real-world evidence programmes intended to validate imaging biomarkers across multiple healthcare settings.

As AI continues to play a growing role in oncology, access to large, diverse and well-curated datasets is increasingly recognised as a key requirement for developing clinically useful models. By combining real-world imaging with patient outcomes across multiple institutions, Nucs AI and Segmed aim to strengthen the evidence needed to support the wider adoption of AI-driven precision medicine.