Advertise on podcast: Smart Medicine

Is AI actually making radiologists faster, or is it just creating more pop-up windows?In this episode of Smart Medicine, Dr. Ali Fatemi sits down with Dr. Woojin Kim—MSK radiologist, former CMIO at Rad AI, CMO of the ACR Data Science Institute, and co-founder of three successful healthtech companies.They dive deep into why billions of dollars have been poured into clinical AI, yet real-world adoption remains surprisingly low.Key Discussion Highlights: 📍 The 2 Biggest Gaps in Radiology AI: Why fancy standalone viewers fail and why benchmark accuracy (like 95% PPV) collapses when applied to low-prevalence real-world clinical data. 📍 Clinical Utility: Model Accuracy: Health system executives don't just care about model numbers; they care about workflow integration, throughput, ROI, and clinical utility. 📍 Building a #FrontierPractice: How health systems must approach AI by starting with real pain points, dirty data governance, and culture change rather than just buying software. 📍 Will AI Replace Radiologists? Why this is the wrong question when imaging volume grows 4–6% annually while workforce growth remains stagnant. 📍 Project Presto in Action: How Dr. Kim's team at Hopper uses vision-language models (VLMs) to auto-populate existing dictation templates💬 Question for you: What is the single biggest workflow friction point in your clinical practice right now? Let us know in the comments below! 👇🔔 Subscribe to Smart Medicine for more deep dives into AI, medical physics, and clinical practice!

Welcome to the Smart Medicine Podcast hosted by Dr. Ali Fatemi! In this episode, senior medical physicist Dr. Jihong Wang from MD Anderson shares his perspective on AI in medical imaging, the need for clinical validation, healthcare leadership, and why international scientific collaboration is vital to future medical breakthroughs.⏱️ Timestamps & Key Topics:00:00 - AI in Medical Imaging & Spectroscopy: Multi-dimensional data analysis (T1, T2, DWI, DCE) and automating prostate spectroscopy workflows.03:15 - Why Validation is Critical: Deep learning reconstruction risks, soft tissue artifacts, and FDA alerts.08:00 - Will AI Replace Medical Physicists & Physicians?: Task automation (contouring, coding) vs. expanding clinical capacity.11:30 - Healthcare Leadership & Vision: Leading by example and supporting early-career team members.15:00 - Global Scientific Collaboration: Why healthcare must transcend national boundaries, referencing lessons from early 20th-century physics.19:00 - Mentorship & Career Advice: Finding key mentors and learning how to learn.23:00 - The Future of Medicine: Upcoming "Penicillin moments" in cancer biology and the promise of FLASH radiotherapy.🔔 Subscribe & Connect: If you enjoyed this episode, please like, subscribe, and click the Notification Bell for more conversations on medical technology, radiation oncology, and healthcare leadership!💬 Question for the Community: How are AI tools currently impacting your clinical or research workflow? Let us know in the comments below!#MedicalPhysics #RadiationOncology #SmartMedicinePodcast #AIinMedicine #FLASHtherapy #Radiology #MedicalImaging #Mentorship

AI is the hottest topic in medicine, but why are so many clinical AI tools failing to deliver a real ROI?In this premier episode of the Smart Medicine Podcast, host Dr. Ali Fatemi (clinical medical physicist) sits down with Dr. Khan Siddiqui—a rare "quadruple threat": a practicing radiologist, academic researcher, software engineer, and deep-tech entrepreneur.Dr. Siddiqui has spent his career at the absolute cutting edge of technology. He learned to code in the 6th grade on a PDP-11 gamma camera system in Pakistan, built epidemiological linear regression models for the CDC in 1993, and went on to work at Microsoft, where his team's machine learning work laid the foundation for the Xbox Kinect, Azure ML, and the revolutionary ResNet neural network architecture. Later, he served as Chief Medical Officer and Chief Strategy Officer at Hyperfine, co-inventing the world's first portable bedside MRI. Today, he is the founder and CEO of Hopper, building multimodal foundation models to streamline clinical workflows.In this episode, Dr. Siddiqui breaks down why improving lesion detection is NOT the key to clinical AI success, explains why AI will never replace radiologists, and shares how we can build AI that actually saves clinicians from crushing burnout.⏱️ TIMESTAMPS TO WATCH:00:00 – Introduction & Dr. Siddiqui's remarkable background.02:15 – Coding in the 6th grade & building linear regression models for the CDC in 1993.06:30 – Choosing radiology and pioneering the world's first imaging informatics fellowship.12:00 – The Microsoft years: Random forests, Xbox Kinect, Azure ML, and the birth of ResNet.16:15 – Redefining medical imaging: The story behind Hyperfine's portable bedside MRI.21:30 – The Windows Kernel Story: "Treating a complex engineering bug like a difficult patient".24:00 – Why clinical AI tools fail: The 250-millisecond detection myth vs. workflow reality.33:00 – What is driving the crushing rise in global imaging volume?.40:30 – Demystifying Multimodal AI & vector representations in medical imaging.48:00 – Hopper & Presto: Creating an "ambient scribe" that integrates directly into existing templates.54:30 – Will AI replace radiologists? Jevons Paradox, horse carriages, and the autopilot analogy.59:00 – Dr. Siddiqui's personal "Why": Helping his overworked radiologist wife reclaim her evenings.1:02:15 – Personalized medicine, AlphaFold, and losing 130 lbs using data and LLMs.💡 KEY TAKEAWAY FROM THE EPISODE: "You always innovate at the edge of your experience." To solve healthcare's biggest challenges, we must stop building isolated AI "point solutions" and start building generalized models that adapt directly to clinicians' existing workflows.Subscribe for more deep dives into the future of smart medicine and medical technology! 🔔

In this episode of Smart Medicine, host Dr. Ali Fatemi sits down with Dr. John Roeske, Division Chair of Medical Physics at Mayo Clinic Arizona. Together, they explore the 30-year transformation of radiation oncology—moving from manual 2D wire contours to advanced AI integration, real-time MR-guided radiotherapy, and adaptive treatments.Dr. Roeske shares key clinical insights on dual-energy subtraction imaging for lung tumor tracking, overcoming serial workflow bottlenecks on MR-linacs, commercializing academic research, and addressing workforce shortages. They also discuss the balanced implementation of AI in clinical practice and software development, emphasizing why scientific rigor, patient safety, and human soft skills remain essential.📌 Timestamps / Chapter Markers:00:00 – Introduction & Dr. John Roske’s background in medical physics02:30 – 30 Years of Progress: Transitioning from 2D contours to personalized adaptive therapy05:45 – Dual-Energy Subtraction Imaging & Real-Time Tracking for Lung Tumors08:15 – Optimizing MR-Guided Radiotherapy: Parallel Workflows vs. Serial Bottlenecks10:45 – Translational Research: Pairing Physicists and Physicians for Breakthroughs13:30 – AI in Radiation Oncology: Auto-Contouring, Prototyping & Patient Safety [13–16]17:30 – Will AI Replace Medical Physicists? Workforce Shifts & Soft Skills20:00 – Future Frontiers: Radiobiology, Radiopharmaceuticals & Quantitative Imaging26:00 – Servant Leadership, Residency Shortages & AAPM Advocacy on Capitol Hill33:00 – Advice for Young Physicists: "Always Be the Student"🔔 Subscribe to Smart Medicine Podcast for more conversations on medical physics and clinical innovation! 👍 If you found this episode valuable, please like, comment, and share with your network.#medicalphysics #RadiationOncology #AIinHealthcare #SmartMedicine #AdaptiveRadiotherapy #MayoClinic #HealthcareInnovation

Historically, we’ve used MRI to take subjective "pictures" of the body. But a major revolution is happening in medical imaging: moving from qualitative pictures to objective, quantitative measurements (qMRI).In our latest episode of the Smart Medicine Podcast, clinical medical physicist Dr. Ali Fatemi sits down with the experts at CalibreMR (President Kelly and Chief Scientist Dr. Teodor Caralonov) to discuss how NIST-traceable phantoms are standardizing the future of MRI, clinical trials, and healthcare AI.Cast your vote below, and then click the link to watch the full episode to find out why the answer is changing the face of medicine!

Welcome back to Part 2 of our exclusive conversation with Dr. Mark Haacke, a pioneering force in vascular neuroimaging and magnetic resonance angiography (MRA). In this episode, we explore the cutting-edge future of Quantitative MRI (QMRI), the role of artificial intelligence, and how we are moving toward a new era of personalized, predictive medicine.Dr. Haacke shares exciting breakthroughs, including his new Avast sequence, the standardization of clinical MRI scans, the return of low-field imaging, and invaluable advice for the next generation of MR scientists working in the age of AI.📌 Key Topics & Timestamps:[00:00] The Motivation Behind Vascular Flow & Neurodegeneration: Why veins are the critical, overlooked key to understanding brain waste removal and folded proteins.[02:15] Introducing Avast (Artery Vein and Susceptibility Technology): A revolutionary sequence that combines MRA, SWI, and QSM into a single, highly efficient run.[04:00] Standardizing Quantitative MRI: How a volunteer scanned on 10 different scanners across China got identical results, and how "spirit" processing fits QSM, SWI, T1, and T2 maps into a single 4-minute protocol.[08:15] Big Data and AI in Radiology: Why standardized QMRI is the missing puzzle piece to feed AI models with millions of cases to analyze brain structures.[11:00] Super-Resolution & Sparse Sampling: Running reconstruction algorithms 10,000 times faster than in the 1980s.[13:30] Sub-Micron Imaging & Tagging Neurochemistry: Mapping the six layers of gray matter and using iron-tagging to view physiological processes like cancer and hormone production under an "MR microscope".[17:15] The Low-Field MRI Comeback: Why 0.5T scanners are highly viable, cost-effective options ($500k) for clinics, and how "spirit" processing can even rescue scans on ultra-low 0.08T corridor scanners.[21:45] Personalized & Preventative Medicine: Detecting Parkinson's disease years before clinical symptoms manifest by measuring neuromelanin and iron changes.[24:30] The "Green Bible" and AI: Why young scientists must learn the fundamental math and physics of MRI to avoid being controlled by AI.[28:00] Still the Enthusiasm of a 25-Year-Old: A lifetime of passion and teaching over 150 students.If you enjoyed this episode, please Like, Share, and Subscribe for more deep-dive conversations with leading minds in medical science!#DrMarkHaacke #QuantitativeMRI #Neuroimaging #AIinMedicine #Radiology #SmartMedicine #ParkinsonsBiomarkers #LowFieldMRI #VascularFlow

Welcome to another episode of the Smart Medicine Podcast! 🎥In Part 1 of this exclusive interview, host Dr. Ali Fatemi sits down with the legendary physicist Professor Mark Haacke. With over 500 publications, 50,000+ citations, and a lifetime of groundbreaking achievements, Dr. Haacke is a true pioneer of Magnetic Resonance Imaging (MRI). From inventing Susceptibility Weighted Imaging (SWI) to writing the definitive MR sequence "green book," his work has profoundly shaped neurodegenerative research and vascular imaging.In this episode, we take a nostalgic trip back to the "Wild West" days of early MR development and explore the beautiful math and physics that revolutionized modern medicine.Key Highlights in This Episode:00:00 – Introduction: Dr. Ali Fatemi welcomes MRI pioneer Professor Mark Haacke to discuss his monumental contributions to the MR field, including fast cardiovascular imaging, SWI, and QSM.02:30 – From High-Energy Physics to Oil Fields: How a young math and physics student from the University of Toronto transitioned from high-energy physics to helping invent geophysical tomography for mapping gas and oil.05:00 – The Dawn of MRI at Picker International (1983): What it was like entering the field of medical imaging when superconducting magnets were just starting, including a hilarious story of being the most "senior" staff member after only two weeks on the job!07:00 – Play It Loud! Playing Music with Magnets: The famous incident of programming the superconducting magnet to play Close Encounters of the Third Kind on reboot, echoing music through the entire company headquarters.08:30 – Pioneering 3D Imaging in the 1980s: How Dr. Haacke and his team pushed the limits of 1 cubic millimeter resolution brain and cardiac imaging long before computers had the processing power to easily handle the data.12:00 – The Fortuitous Discovery of SWI: The fascinating story of how analyzing raw phase data and developing homodyne filtering brought deep gray matter structures and veins to light in unprecedented detail.15:00 – Changing a Patient's Life: The very first clinical case of SWI with Dr. Dan Kido, where a scan successfully distinguished a harmless telangiectasia from a tumor, instantly saving a patient from unnecessary radiation treatment.16:00 – A Crucial Lesson for Physicists: Why getting tools into the hands of clinicians is vital, and why clinical users will always find clinical applications engineers never dreamed of.

In this episode of Smart Medicine, host Dr. Ali Fatemi sits down with a true pioneer at the intersection of clinical medicine, entrepreneurship, and venture capital. Today’s guest is Dr. Jesse Courtier, a Pediatric Radiologist, Stanford Adjunct Clinical Professor, and healthcare investor based in the San Francisco Bay Area. He is the Founder of Sira Medical—an FDA-cleared, venture-backed augmented reality MedTech startup and UCSF spinout—and the Managing Director of Radiologue Ventures, where he supports early-stage companies innovating in medical imaging. With 15+ years of experience, Dr. Courtier is a 2x UCSF Catalyst Award winner who has raised over $1 million and published multiple clinical studies. Solving the Communication Gap: How Sira Medical uses AR to help surgeons visualize complex 3D scans before operating.The Reality of FDA 510(k) Clearance: Key lessons on documentation, user testing, and budgeting for regulatory hurdles.AI in Radiology: Why the immediate future of clinical AI lies in operational workflows and chart summarization rather than replacing radiologists.Healthcare Venture Capital: What VCs look for in early-stage startups and why solving a real economic bottleneck is vital.The Future of Medical Training: How AI-powered "flight simulators" could revolutionize how residents learn to diagnose rare pathologies.

Welcome to another episode of the Smart Medicine Podcast with Dr. Ali Fatemi! In this episode, we have the great pleasure of hosting Dr. Paul Polak, an MR Physicist, biomedical engineer, and imaging scientist at Philips. Dr. Polak shares his fascinating journey from working as an IT consultant in software engineering to diving into the complex world of MR physics and biomedical engineering. We discuss the evolving landscape of medical imaging and dive deep into the most pressing topics in the field today. In this episode, we cover: The true value of a PhD: How having those three letters helps build respect with clinicians and instills a deep focus on solving scientific problems.The rise of AI in MR: How artificial intelligence is accelerating image acquisition, revolutionizing post-processing and segmentation, and even the future of AI writing MR pulse sequences (vibe coding).The future of Low-Field Magnets: Why advancements in computing power and hardware might soon make low-field MRI a ubiquitous tool in urgent care centers and primary doctors' offices.Academia vs. Industry: Dr. Polak explains his transition from the "publish or perish" academic world to industry, where the focus shifts to directly solving practical problems for clinicians and patients.Quantitative Imaging & Clinical Adoption: Why new MR innovations and quantitative imaging techniques must clearly demonstrate that they are faster, better, or easier to use before clinicians will adopt them into their workflow.Career Advice for Young Scientists: Why interpersonal skills become just as important as technical skills as your career progresses, and the importance of staying focused and optimistic

Welcome to another episode of the Smart Medicine Podcast! 🎙️ In this episode, host Dr. Ali Fatemi sits down with his good friend Dr. Dharanipathy Rangaraj PhD MBA, a medical physicist, entrepreneur, healthcare strategist, and venture builder who has led over $100 million in commercialization initiatives across oncology and medical technologies.In this deep dive, Dharanipathy Rangaraj PhD MBA shares his journey from a clinical physicist at Washington University in St. Louis to a business leader, and discusses the very real value of AI in modern radiation oncology.Key highlights from this episode include:- The Future of Healthcare Operations: Why the next era of medicine relies on intelligent systems. As Dani puts it, "the future isn't more software, the future is less friction".- Will AI Replace Medical Physicists?: Discover why AI won't take our jobs, but will instead evolve our roles so that we spend less time checking systems and more time designing them.- Transforming Motion Modeling (5DCT): An exclusive look at Respirati, a project Dharanipathy Rangaraj PhD MBA is working on with Dr. Daniel Low. Learn how 5DCT is set to revolutionize tumor tracking and solve the limitations of 4DCT so we "never miss again".- Advice for Healthcare Entrepreneurs: Dharanipathy Rangaraj PhD MBA rules for aspiring founders, including the importance of finding a "founder-problem fit," having the willingness to grind, and why you should "never be greedy" when building a business team.Don't miss this incredible conversation about scaling clinical expertise, overcoming the behavioral challenges of tech adoption, and the exciting future of personalized medicine.🔔 Subscribe for more conversations on the cutting edge of medicine and technology!

Description: Welcome to Episode 1 of the Smart Medicine Podcast! 🎙️ Today, Dr. Ali Fatemi is joined by tech powerhouse Nader Dabit to explore the bleeding edge of AI: Agentic Software Engineering.Can an AI really plan, write, test, and ship production code entirely on its own? Yes! Nader takes us behind the scenes of Cognition's autonomous AI developer, "Devon," to explain how AI is completely flipping traditional engineering on its head. But don't worry—AI isn't here to steal your job. We discuss why making coding easier will actually result in a massive explosion of new tech jobs. 🔥 Key Highlights in this episode: • Meet Devon: How Cognition's AI agent operates in a real development pipeline, handling everything from continuous integration to automated pull requests. • The Mercedes Miracle: Hear the incredible story of how an 8-month legacy code migration was completed in just 8 days using Devon. • The Jevons Paradox: Why the demand for software engineers will grow exponentially as AI tools become more powerful. • AI in Healthcare: We discuss the challenges of HIPAA and PHI, and why running local, highly capable models is the safest way to bring cutting-edge AI into medicine. • The "AI Engineer" Evolution: How traditional front-end and back-end roles are merging into new positions where developers orchestrate and supervise autonomous AI agents. • Everyday AI Automations: Nader shares his personal workflow, including an AI agent called "Hermes" that curates custom tech news for him every single morning.Whether you're a medical professional looking to prototype your next big idea, or a seasoned developer figuring out how to stay relevant in the age of AI, this conversation is packed with essential insights. Don't forget to like, subscribe, and let us know your thoughts in the comments! Do you think AI agents will make coding obsolete, or are we just entering a new golden age of software? 👇

Every patient is unique, and no two tumors are identical—yet in radiotherapy, we often try to treat all tumors with a single, standard dose. How can we change this? I am thrilled to share the latest episode of The Smart Medicine Podcast, featuring my good friend and colleague, Dr. Oliver Gurney-Champion, Associate Professor at UMC Amsterdam. Oliver's research group is doing incredible work at the intersection of quantitative MRI and deep learning. We had a fantastic conversation about moving beyond traditional anatomical MRI to characterize real-time tissue properties like cell density (diffusion) and oxygenation (perfusion). Here are a few key takeaways from our discussion: 🔹 Physics-Informed AI: How leveraging self-supervised, physics-based AI can drastically reduce the noise and scan times of quantitative MRI, doing in subseconds what used to take minutes. 🔹 The Vendor Bottleneck: The ongoing struggle to translate promising pulse sequences into the clinic and why standardizing quantitative values across different scanner vendors remains our biggest hurdle. 🔹 Personalized Dosing: The 5-year vision of making active clinical decisions based on daily MRI data—adapting radiation doses based on how the tumor and surrounding healthy organs (like the liver) are functioning that exact day. 🔹 Leadership in Science: Honest advice for young scientists on navigating the difficult transition from hands-on researcher to team manager, handling grant rejections, and the value of leadership training. If you are a medical physicist, radiologist, or just passionate about the future of AI and oncology, you won't want to miss this one.Let me know in the comments: Do you think AI or hardware advancements will be the biggest driver for bringing quantitative MRI into routine clinical practice?

What if a radiation treatment that normally takes minutes could be safely delivered in under a second?In this episode of Smart Medicine, Dr. Ali Fatemi sits down with medical physics expert Dr. Magdalena Bazalova to discuss the absolute bleeding edge of cancer treatment and medical imaging.In this video, we break down: ✅ FLASH Radiotherapy: How ultra-high dose rate radiation is sparing healthy tissue while destroying tumors, and the immense engineering challenges of bringing it to deep-seated human tumors. ✅ The Limits of X-Ray & CT: Why the clinical adoption of photon-counting CT and phase-contrast imaging could change diagnostic medicine forever. ✅ AI vs. Physicists: Is AI going to take over clinical physics jobs? We discuss why AI is great for drawing organ contours, but why human hands are still needed for hardware and QA.✅ The Future: Why radiopharmaceuticals and theranostics are the next frontier in fighting metastatic cancer.If you are a student, professional, or just fascinated by the incredible machines and physics used to save lives, this is a must-watch episode!👉 Watch the full episode now: [Insert Link Here]💬 Let us know in the comments: Do you think AI will eventually be able to run an entire clinical treatment autonomously?

our latest episode of Smart Medicine, we are joined by MRI experts Dr. Ricardo Latanzi and Dr. Mike Hoff to dive into the mind-blowing future of medical imaging. We are moving away from treating MRI as just a camera, and instead transforming it into a quantitative scientific instrument designed to make medicine an exact science.In this video, we explore how AI and physics are pushing the boundaries of what is possible:Quantitative MRI & Fingerprinting: Imagine capturing every vital tissue parameter in a single, fast scan to detect diseases (like cartilage degeneration) long before they appear on standard images.Mapping Electrical Properties: Discover how we are using AI to map the electrical conductivity of tissues based on electromagnetic interference patterns, which could act as a massive breakthrough biomarker for cancer detection and targeted ablation treatments.Trustworthy AI: Why "uncertainty quantification" is the key to getting AI into clinics, ensuring that algorithms don't accidentally erase real lesions to make an image look perfect.Autonomous MRI: From utilizing data from previous scans and wearable sensors, to the very real possibility of fully automated, "self-scanning" MRI machines that require zero human intervention.Personalized Medicine: How customized scanning workflows and digital twin technology will completely change hospital operations and patient care.Watch the full episode to see where the cutting-edge of medical physics is taking us!👇 Drop a comment: Would you trust a fully autonomous, robotic MRI scanner for your next hospital visit, or do you always want a human involved?

What if a life-saving stroke diagnosis could happen in the back of an ambulance? In this episode of Smart Medicine, Dr. Ali Fatemi sits down with medical physicist and entrepreneur Dr. Sergei Obruchkov to discuss the radical hardware innovations his companies are bringing to the MRI world. In this episode, we shine a spotlight on two game-changing products: 🧲 The Axana System: We discuss his spin-off company's flagship product, Axana—a 30-kilo, fully portable head MRI. Dr. Obruchkov explains the incredible engineering behind it, including how they used AI to map stroke anatomy and borrowed tech from the oil and gas industry to remove heavy conventional gradients entirely. The goal? To put an Axana system in ambulances so we can detect time-critical "wake-up strokes" instantly. 🏫 Resonant's 8-Kilo MRI: We also explore his company, Resonant, which builds tiny, 8-kilo benchtop MRI machines. Dr. Obruchkov shares his bold vision to put one of these systems in every high school to demystify medical imaging and inspire the next generation of scientists and engineers. If you love deep-tech, AI, and medical engineering, hit play to see how these unique products are changing the game! Don't forget to like, subscribe, and drop a comment below: Could a benchtop MRI have changed your high school science experience?