AI Innovation Lab

Some chapters close quietly. I’ve been reflecting on a period shaped by building, leading, and translating AI into real-world impact - alongside a remarkable team and partners across the ecosystem. I’m deeply grateful for the trust, the collaboration, and the learning that shaped this experience. With that chapter now complete, I look ahead with energy and curiosity - and welcome conversations about what meaningful work might come next.

𝐅𝐫𝐨𝐦 𝐦𝐨𝐝𝐞𝐥𝐬 𝐭𝐨 𝐚𝐠𝐞𝐧𝐭𝐬 — the shift toward intelligent systems. At the AI Innovation Lab, we’ve been exploring how agentic AI can move medical imaging beyond isolated models toward fully orchestrated clinical pipelines. In our work, “A Multi-Agent Framework for Automated Brain MRI Segmentation and Anatomical Volume Analysis,” a Supervisor Agent coordinates multiple specialized agents — segmentation, automated quality control, voxel quantification, and structured report generation — to turn a single T1-weighted brain MRI into a fully validated volumetric report. The system achieved an average Dice score of 0.94 across major brain regions, with automated validation before producing clinician-ready summaries. This is a step toward AI systems that don’t just predict, but reason through imaging workflows in ways that are robust, interpretable, and scalable. Congratulations to Hoda Helmy and the team — excited to see this work presented at IEEE International Symposium on Biomedical Imaging. More to come. #AgenticAI #Neuroimaging #MedicalImaging #HealthcareAI #AI #MultiAgent #BrainMRI #Radiology #AIInnovation #LLM #RAG #TranslationalAI #ISBI #FutureOfHealthcare

𝗡𝗲𝘄 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱! Radiology reporting is one of the most time‑consuming parts of clinical practice, and spinal MRI is especially challenging: 3D anatomy, multiple sequences, and subtle findings that really matter for patient outcomes. In our latest work, we introduce 𝐒𝐏𝐈𝐍𝐄 – 𝐒𝐞𝐠𝐦𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧-𝐠𝐮𝐢𝐝𝐞𝐝 𝐏𝐫𝐨𝐜𝐞𝐬𝐬𝐢𝐧𝐠 𝐚𝐧𝐝 𝐈𝐧𝐭𝐞𝐠𝐫𝐚𝐭𝐢𝐨𝐧 𝐨𝐟 𝐌𝐮𝐥𝐭𝐢𝐦𝐨𝐝𝐚𝐥 𝐒𝐩𝐢𝐧𝐚𝐥 𝐌𝐑𝐈 𝐟𝐨𝐫 𝐍𝐚𝐭𝐮𝐫𝐚𝐥-𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐄𝐧𝐡𝐚𝐧𝐜𝐞𝐝 𝐑𝐞𝐩𝐨𝐫𝐭 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧, a 3D vision–language framework that fuses T1, T2, and segmentation maps to generate anatomically aware spine MRI reports. What we built • A 3D-aware VLM pipeline that ingests full lumbar spine volumes (axial and sagittal) instead of isolated 2D slices, better reflecting how radiologists read studies. • Segmentation-guided inputs where vertebrae, discs, canal, and key regions are encoded as additional channels (T1 + Seg, T2 + Seg, and T1 + T2 + Seg). • A report-generation stage that pairs volumetric MRI with LLM-standardized radiology reports, ensuring consistent, structured language for training. Key findings • Adding segmentation consistently improved report quality across BLEU, ROUGE, METEOR, and BERTScore compared to using MRI alone. • The T1 + T2 + Seg configuration delivered the most balanced and robust performance overall, with higher lexical precision and strong semantic alignment. • Models trained on LLM-standardized reports outperformed those trained on raw human-written text, highlighting how linguistic consistency boosts image–text learning. • For synthetic report generation from structured gradings, GPT‑4o produced markedly more fluent and clinically detailed narratives than Grok‑3 across all language metrics. • Expert review of generated reports showed high scores for clarity and terminology, with clinically acceptable accuracy. Why this matters SPINE shows that segmentation-aware, multimodal 3D VLMs can move automated reporting beyond generic image captioning toward anatomically grounded, clinically useful narratives. This opens the door to AI systems that support radiologists with more consistent, interpretable, and scalable spine MRI reporting—particularly valuable in settings with high workload and limited subspecialty expertise. This work was led by Hoda Helmy, with AI Innovation Lab team members Abdullah Hosseini and Ahmed Ibrahim, in collaboration with Mr. Ahmed-Ramadan Sadek and Asfand Baig Mirza from Barking, Havering and Redbridge University Hospitals NHS Trust. 📄 Article: https://lnkd.in/dgxgtnU6 👩💻 Code: https://lnkd.in/du8Xqd4g #AI #MedicalImaging #Radiology #SpineMRI #VisionLanguageModels #Segmentation #ReportGeneration #GenerativeAI #HealthcareAI #AppliedAI #WeillCornellMedicine #Qatar #NHS #Neurosurgery

I had the privilege of speaking at the opening of LifeLines Hackathon 2026 at Carnegie Mellon University in Qatar. In front of hundreds of students, I spoke about a critical question: How do we ensure AI strengthens humanity during its most vulnerable moments? From emergency triage to healthcare resilience and resource optimization, AI has transformative potential in times of crisis. But power without governance is risk. Innovation without responsibility is fragility. I also served as a judge for the Health theme, where I witnessed impressive maturity in how teams approached real-world constraints, ethics, and impact. Encouragingly, many of the winning teams emerged from this track. The AI Innovation Lab was proud to contribute through active mentorship - guiding teams to build solutions that are not only technically strong, but responsible and scalable. This is the generation that will define ethical AI in practice - not theory. Congratulations to all participating teams, and thank you to the organizers, mentors, and partners for making this initiative possible: Khaled Harras, Nour Elsayed Ali, Chaima Ben Rabah, Eng-PhD, Lamiaa Basyoni, Sandra Sapia and Dr. Ali AlSanousi, MD, MBA, PhD. #AIForGood #ResponsibleAI #HealthcareInnovation #InnovationLeadership #AI

Less than a week to go - looking forward to being back home in Egypt and discussing AI from research to real-world impact. #AIEverythingMEAEgypt #GITEXGLOBAL #ArtificialIntelligence #AIInnovation #DigitalTransformation #AIinMEA #CairoTech #TechLeadership

It was an honour to welcome Ahmed Serag, PhD, Chief AI Officer, Professor of Artificial Intelligence at Weill Cornell Medicine, and Founder of the AI Innovation Lab, as a Guest of Honor at the Forttuna Global Excellence Awards 2025 Global Edition in Dubai. 💫 A globally recognized AI expert with nearly two decades of experience, Ahmed has been at the forefront of developing and commercializing cutting-edge AI technologies. His work spans healthcare, data science, and ethical AI, with leadership roles including VP Global Director of Data Science and AI Innovation at Novartis and advancing AI algorithms for cancer diagnostics at Philips. Holding a PhD from Imperial College London, Ahmed has authored numerous publications, delivered keynote addresses worldwide, and advised organizations on AI strategy and governance. His research and innovations continue to shape the global landscape of artificial intelligence, bridging advanced technology with real-world application to improve outcomes across sectors. 👏 We extend our heartfelt gratitude to Ahmed Serag for sharing his expertise, inspiring global leaders, and enriching the 2025 Global Edition with his vision for AI-driven impact. #2025GlobalEdition #ForttunaGlobalExcellenceAwards #AhmedSerag #ArtificialIntelligence #AIInnovation #HealthcareAI #EthicalAI #GlobalLeadership #DubaiEvents

A special moment to close out the year. Honoured to receive the AI Innovation Leader of the Year award at the Forttuna Global Excellence Awards®. Grateful for the support along the journey - excited for what’s ahead. #AI #Innovation #Leadership #Grateful #Impact #Excellence #NewBeginnings