E230: The Last Untouched Dataset

<p>In this episode of AI For Pharma Growth, Dr Andree Bates speaks with Nijat Ahmadov, CEO of Nucs AI, about molecular imaging as one of pharma’s most underused data assets.</p><p>Nijat explains why PET, CT and other molecular imaging data remain largely “untouched”: clinically valuable and created at scale, but still too often trapped in qualitative reads rather than structured, standardised data that can support decision making. As radioligand therapies expand in oncology, that gap becomes harder to ignore.</p><p>The conversation explores how AI can help turn molecular imaging into computable, decision-grade data for patient selection, response monitoring and companion diagnostic strategy. Nijat argues that AI is no longer a nice-to-have in this space. Without it, pharma risks losing confidence in the outcomes that affect adoption, reimbursement and commercial success.</p><p>They also discuss what it will take for AI-derived imaging biomarkers to become regulatory grade: analytical validation, reproducibility, diverse data sets, clinical validation and evidence that endpoints are meaningful, not just technically impressive.</p><p>The key message is that imaging is not only diagnostic. Once structured properly, it can reveal predictive signals about disease behaviour and treatment response, making it a powerful asset for pharma teams building the next generation of oncology trials.</p><p>Topics Covered</p><ul><li><p>Why molecular imaging is still underused</p></li><li><p>Turning PET and CT scans into structured data</p></li><li><p>Radioligand therapy and patient selection</p></li><li><p>Moving beyond eligible vs not eligible</p></li><li><p>AI-derived imaging biomarkers</p></li><li><p>Clinical validation and regulatory trust</p></li><li><p>Imaging data as a competitive moat</p></li><li><p>Why prediction matters more than diagnosis</p></li></ul><p>Eularis helps pharma and biotech leaders turn AI activity into board-defensible governed strategy and measurable commercial outcomes.</p><p>If your CFO asked tomorrow for the projected return of each major AI initiative - by year, across three years, with explicit adoption, operating cost and redeployment assumptions - could you produce an answer that survives scrutiny?</p><p>And if you could: would you know which of those initiatives most moves the company toward the outcomes it&#39;s exposed on over the next three years? Those are two different questions, and most organisations can&#39;t answer either. A strong