If you've ever fought through a PACS migration, wrestled with malformed DICOM data, or wondered why two systems that supposedly speak the same standard can't talk to each other — this one's for you.

Jason sits down with Larry Sitka, founder of Acuo Technologies and one of the earliest architects of the Vendor Neutral Archive (VNA) concept, to unpack three decades of building enterprise imaging infrastructure from the ground up.

Larry got his start writing network drivers at Bell Labs, helped shape DICOM 3.0 at 3M, and then built Acuo — a company he grew from a sketch on a napkin in 1997 into an enterprise imaging powerhouse acquired twice over.In this episode, Larry and Jason dig into why DICOM interoperability is still a mess, how AI false positives are driving radiologist frustration, and why the next evolution of enterprise imaging isn't about storing data — it's about perceiving it. They also tackle the knowledge gap that's forming as experienced imaging IT professionals retire, what AI governance for radiology actually looks like, and why Larry thinks the industry has been building things for the wrong user all along.

Whether you're a PACS administrator, imaging informatics professional, or just someone who cares about getting radiology AI right, this conversation will give you a lot to chew on.If you're looking to build a stronger foundation in imaging informatics or sharpen your DICOM knowledge, check out the CIIP Foundations Program and the upcoming DICOM training with hands-on live imaging learning labs at nagelsconsulting.com.

Learn more at nagelsconsulting.comKey Topics Covered

• The origin story of Acuo and why the VNA concept emerged in 1997 — before anyone had a name for it
• Why DICOM interoperability remains broken and what a real conformance testing standard would look like
• The shift from data persistence to data perception — and how AI changes what we actually need from a VNA
• How AI false positives are burning out radiologists and what multi-algorithm inference engines could do instead
• The knowledge gap in imaging IT: what gets lost when experienced DICOM engineers retire
• AI governance for enterprise imaging — why recalibrating AI models is the next big challenge in PACS/VNA
• The future of enterprise imaging: running a million AI inferences a night at population scale

If your digital pathology deployment has a brand-new whole-slide scanner, a solid IMS, and petabytes of storage — but your pathologists are reading on consumer monitors — you may have a serious problem you haven't budgeted for yet.In this episode of Imaging Informatics Unplugged, Jason sits down with Tom Kimpe, VP of Technology & Innovation for Healthcare at Barco, for a deep-dive webinar from Canada Health Infoway on the critical role the display plays in the digital pathology imaging chain. Tom unpacks why color gamut matters more in pathology than almost any other imaging domain, how color variability sneaks in at every step of the workflow — from tissue staining through scanner to viewer to display — and what the peer-reviewed science actually says about diagnostic accuracy and reading efficiency when pathologists use medical-grade versus consumer monitors.Spoiler: a 6–8% reduction in reading time. 100% diagnostic concordance on medical displays versus measurable drop-off on consumer hardware. Missed concurrent diseases. These aren't marketing claims — they're published, peer-reviewed findings.Whether you're a PACS admin, imaging informatics specialist, or radiology IT leader expanding into enterprise imaging and digital pathology, this is the kind of workflow and display standardization knowledge that will save your organization from an expensive mid-project scramble. If you're working toward your CIIP credential, the CIIP Foundations Program at nagelsconsulting.com is exactly where this conversation fits into the bigger picture — and keep an eye out for the upcoming DICOM training program with hands-on live imaging learning labs that will make concepts like ICC profiles and DICOM WG-26 click in a whole new way.Learn more at nagelsconsulting.comKey Topics Covered

• Why pathology tissue has a broader colour gamut than sRGB displays can reproduce — and what that means clinically
• How colour variability is introduced at every link in the digital pathology chain: lab prep, scanner, viewer, and display
• The difference between consumer, professional, and medical-grade displays — and why it matters for pathology specifically
• ICC colour profiles: what they are, how they work, and why adoption is accelerating toward an industry standard
• Peer-reviewed evidence showing measurable impact of display quality on diagnostic accuracy, concordance, and reading efficiency
• The DICOM WG-26 ecosystem: how file format standardization is finally catching up to scanner adoption
• Where display procurement falls through the cracks in digital pathology deployments — and how to fix it

If you have ever watched a radiology AI demo hit 98% accuracy in testing and then wonder why nobody is actually using it in the clinic, this episode is for you. Hit subscribe so you never miss a conversation like this one.Jason sits down with Satvik Tripathi, incoming Medical Physics and Imaging Informatics PhD student at the University of Pennsylvania, AI scientist for RAD-AID International, and one of the sharpest voices in the field on the gap between research performance and real clinical value. Satvik has been working at the intersection of AI and radiology since 2019 and brings a perspective that cuts through the noise.They get into the hard questions: why multiple-choice benchmarks are a terrible way to evaluate medical LLMs, what data leakage is quietly doing to published performance numbers, and why a fine-tuned model is not always the winner in a clinical context. Satvik also breaks down what it actually takes to build a benchmark that means something, and shares early findings from his team's head-to-head testing of over 20 models on an internally annotated clinical dataset.The conversation also digs into agentic AI in imaging informatics, global health deployments through RAD-AID in Botswana and India, AI-assisted oncology workflows, and why running smaller open-source models locally might be smarter than everyone thinks. Plus, Satvik makes a case that prompt engineering is not a productivity shortcut but a legitimate scientific method.Whether you are a PACS administrator, imaging analyst, radiology IT professional, or just someone trying to figure out which AI tools are actually worth your time, this is the kind of conversation that helps you cut through the hype and think more clearly about what is coming.If this episode is useful to you, please subscribe, leave a review, and share it with a colleague in the imaging informatics community. It makes a real difference. And if you are working toward your CIIP credential or want to go deeper on the foundations of this field, check out the CIIP Foundations Program and the upcoming DICOM training with hands-on live imaging learning labs at nagelsconsulting.com.Learn more at nagelsconsulting.comKey Topics Covered

• Why AI model performance metrics often fail to predict real-world clinical impact, and the two questions every AI deployment team should be asking before going live
• The flaws in how medical LLMs are benchmarked today, including multiple-choice test limitations, data leakage, and the gap between controlled evaluations and actual clinical usefulness
• How Satvik's team built an internal annotated dataset and tested more than 20 models head-to-head, with results that challenge conventional assumptions about fine-tuned models
• The promise and current limitations of agentic AI in radiology, including what true agentic systems require versus what vendors are actually shipping• Using AI to democratize global healthcare through RAD-AID's work in Botswana and India, including Google-funded foundation model deployments and lessons that translate back to Western healthcare systems
• Why prompt engineering is a scientific method, not just a productivity trick, and how structured prompting can reduce hallucinations and improve reproducibility in clinical AI applications
• The practical case for smaller, on-premises open-source models over large cloud-based generalist models, including cost, privacy, sustainability, and compliance considerations

Thinking about the CIIP, but have no clue where to start?This video breaks down the exam, the eligibility rules, the 10 domains, and the smartest way to figure out what you actually need to study before wasting time. If you work in imaging informatics, PACS, VNA, radiology IT, enterprise imaging, clinical engineering, or healthcare technology, this gives you a practical starting point.In this video, you’ll learn:• what the CIIP actually signals to employers• how the exam is structured• what the 10 test content outline domains are• how the questions are weighted across domains• what the ABII seven-point qualification system is• how to check whether you qualify before diving in• how a free 50-question practice quiz can help you find strengths, spot gaps, and focus your prepThe CIIP is not just for “technical people.” It sits at the intersection of healthcare, operations, systems, workflow, and imaging technology. That’s what makes it valuable, and that’s also why a lot of people feel overwhelmed when they first look at it. This video is meant to make that starting point clearer.I also introduce the CIIP Foundations Program from Nagels Consulting, a structured prep path aligned to the same 10 domains covered on the exam. The goal is simple: help you study with direction rather than guess.Start here:Free 50-Question CIIP Practice Quiz: https://learn.nagelsconsulting.com/course/ciip-practice-tools ABII Eligibility Guide: https://www.abii.org/Qualification-Requirements.aspx Learn more: www.nagelsconsulting.com First five CIIP Foundations courses:CIIP_PROC101: Procurement as a Repeatable Thinking Processhttps://learn.nagelsconsulting.com/course/ciip-proc101 CIIP_PM101: Project Management as a CIIP Core Competencyhttps://learn.nagelsconsulting.com/course/ciip-pm101 CIIP_OPS101: CIIP Operations & System Reliabilityhttps://learn.nagelsconsulting.com/course/ciip-ops101 CIIP_COM101: Communication as a Cross-Domain Disciplinehttps://learn.nagelsconsulting.com/course/ciip-com101 CIIP_EDU101: Training & Education in Imaging Operationshttps://learn.nagelsconsulting.com/course/ciip-edu101 #CIIP #CIIPExam #CIIPCertification #ImagingInformatics #EnterpriseImaging #PACS #VNA #ImagingIT #HealthcareIT #ClinicalEngineering #MedicalImaging #ABII #ExamPrep #NagelsConsulting

How close is AI to real clinical adoption in radiology and medical imaging?In this episode of Imaging Informatics Unplugged, Jason Nagels talks with Dr. Khaled Younis about where AI and machine learning really stand today in radiology, why adoption is still uneven, and what needs to happen next.Dr. Younis brings deep experience across AI research, clinical imaging, and global standards. You can learn more about his work here:https://medaiconsult.com/https://www.linkedin.com/in/dryounis/The conversation digs into the biggest barriers holding imaging AI back, including clinical validation, FDA and regulatory scrutiny, interoperability challenges across PACS, RIS, EHR, DICOM, HL7 and FHIR, as well as bias, trust, explainability and real-world deployment. It also looks at how early CAD systems compare with today’s deep learning era, why many AI vendors still treat standards as an afterthought, and how IHE and ISO are shaping the future of trustworthy AI in imaging.You’ll also hear a practical discussion on federated learning, multi-site collaboration, synthetic data, tumor segmentation, structured AI results, and the role of standards in making AI outputs usable across clinical workflows. Dr. Younis shares where he sees the biggest opportunities ahead, including real-time decision support, AI-assisted intervention, multimodal data integration, and more open, interoperable healthcare ecosystems.If you’re looking to build a stronger foundation in imaging informatics, workflows, and standards like DICOM, HL7, FHIR, and IHE, visit:https://www.nagelsconsulting.com/You can also check out the CIIP Foundations program for a structured, practical approach to understanding how these concepts apply in real-world imaging environments.Topics coveredAI in radiology adoptionMedical imaging AI barriersFDA approval and post-market surveillanceInteroperability in radiology AIIHE profiles and AI resultsISO and trustworthy AIBias in healthcare AIFederated learning in medical imagingSynthetic data for AI trainingStructured reporting and TID 1500Real-time decision supportMultimodal AI in healthcareHashtags#AI #Radiology #MedicalImaging #ImagingInformatics #HealthcareAI #MachineLearning #FederatedLearning #DICOM #IHE #FHIR #HL7 #ClinicalAI #TrustworthyAI #Interoperability #DigitalHealth

Is radiology AI finally living up to the hype — or are we still waiting for the revolution Geoff Hinton promised back in 2012?

In this episode of Imaging Informatics Unplugged, Jason sits down with Dr. Ben Fine, a radiologist with a deep background in imaging informatics, AI deployment, and enterprise imaging strategy.

Ben shares a refreshingly honest take on where radiology AI actually stands today: only about 1% of imaging workflows are meaningfully augmented by AI tools, and real ROI is still rare — driven more by FOMO than outcomes. But he argues the corner is being turned, as the field shifts from narrow deep learning models to foundation models capable of assisting with full radiology reports.

The conversation digs into real-world AI deployment lessons from the AIDE Lab at Trillium Health Partners, where Ben’s team developed a pre-deployment evaluation methodology for PACS-integrated AI tools that has since become best practice. They also explore the Swiss cheese model of human-AI collaboration, why operational workflow use cases (like protocol automation and procedure nomenclature mapping) often beat flashy diagnostic AI for ROI, and what effective AI governance looks like for health systems.

Whether you’re a PACS Admin, Imaging Manager, Radiologist, or Healthcare IT professional thinking about enterprise imaging and AI in radiology, this episode is packed with practical, colleague-to-colleague insights.

Learn more at nagelsconsulting.com

KEY TOPICS COVERED

• Amara’s Law and the realistic 3-year outlook for radiology AI — why we’re finally at the inflection point after years of overhype
• The AIDE Lab at Trillium Health: how pre-deployment evaluation of PACS-integrated AI tools became a best-practice framework across Ontario
• The Swiss cheese model of human-AI collaboration — why AI and radiologists fail in such different ways, and how to design systems that catch what neither misses alone
• Operational AI use cases that deliver real ROI: procedure nomenclature mapping, CT/MRI protocol automation, and bone mineral density (BMD) workflow assistance• Ontario’s centralized diagnostic imaging repository (OCINet/DIR) as an untapped opportunity for population health AI and opportunistic screening at scale
• AI governance frameworks for health systems — applying a pharmaceutical-committee model to the selection, validation, deployment, and monitoring of AI tools
• The future skills that matter: why domain expertise combined with AI fluency — not just soft skills — will define the next generation of imaging informatics professionals

What do The Beatles have to do with the invention of the CT scanner?At first glance… nothing.By the time CT scanning was introduced in the early 1970s, The Beatles had already broken up. But the connection between one of the most influential bands in history and one of the most important technologies in modern medicine runs through a company called EMI.In this episode, we explore the surprising story of how revenue generated by Beatles records helped sustain the research division at EMI where Godfrey Hounsfield developed the first computed tomography (CT) scanner.We also explore how CT imaging transformed diagnostic medicine and how the field of imaging informatics helps manage imaging safely today.Topics covered include:• The invention of CT scanning• The role of EMI and Godfrey Hounsfield• The first clinical CT brain scan in 1971• Ionizing radiation and medical imaging• Radiation safety principles like ALARA• The Cedars-Sinai CT dose incident• Standards such as DICOM Radiation Dose Structured Reports (RDSR)• Regional and national dose registriesMedical imaging has revolutionized healthcare, allowing clinicians to see inside the body with unprecedented clarity. But the story behind these technologies sometimes has unexpected connections to music, culture, and history.And in this case… it starts with The Beatles.⸻Learn more about imaging informatics and enterprise imaging: https://www.nagelsconsulting.com⸻#imaginginformatics #medicalimaging #CTscan #radiology #healthcaretechnology #DICOM #ALARA #patientSafety #diagnosticImaging #healthIT

AI in healthcare is everywhere — but very little of it actually works in real clinical environments.

In this episode of Imaging Informatics Unplugged, Jason Nagels sits down with Dr. Franz Pfister, physician, data scientist, and CEO of deepc, to discuss what it really takes to operationalize AI in radiology and healthcare workflows.

They explore why model accuracy alone isn’t enough, how hospitals deploy AI safely at scale, and what separates real operational AI from marketing hype.

If you work in enterprise imaging, radiology, PACS, VNA, healthcare IT, or clinical AI, this conversation is essential

⸻

What You’ll Learn

• Why most healthcare AI pilots never become operational
• The difference between model performance and workflow integration
• How AI is deployed safely inside clinical environments
• Privacy, governance, and regulatory challenges (GDPR, AI Act)
• Performance drift and real-world AI reliability
• Agentic AI in healthcare: hype vs reality
• How AI will reshape roles in radiology and imaging informatics• Treating AI as infrastructure, not just a tool

⸻

About the Guest

Dr. Franz MJ Pfister is a medical doctor, data scientist, and entrepreneur working at the intersection of AI, healthcare, and clinical operations. He studied medicine at Ludwig Maximilian University of Munich and Harvard Medical School, holds a doctorate in neuroscience, an MBA, and a Master’s in Data Science. He is CEO and co-founder of deepc, a company focused on operational AI infrastructure for radiology.

⸻

About Imaging Informatics Unplugged

Imaging Informatics Unplugged explores enterprise imaging strategy, interoperability, PACS, VNA, clinical workflows, healthcare AI, and the future of medical imaging technology.

Hosted by Jason Nagels of Nagels Consulting.

⸻

Learn More

Website: https://www.nagelsconsulting.com

Book a Meeting with Jason https://meetings.hubspot.com/jason-nagels

Watch on YouTube: https://www.youtube.com/@NagelsConsulting

⸻

Courses & Training in Imaging Informatics

Nagels Consulting provides professional training in:

• Enterprise Imaging
• Imaging Informatics
• PACS & VNA Strategy
• Interoperability Standards (DICOM, HL7, FHIR)
• Healthcare AI Implementation
• Clinical Workflow Optimization

New courses launching soon → https://www.nagelsconsulting.com

Artificial intelligence is rapidly entering dermatology — but what does it actually take to make AI work in real clinical practice?In this episode of Imaging Informatics Unplugged, Jason Nagels sits down with Dr. Veronica Rotemberg, Director of Dermatology Informatics and Research at Memorial Sloan Kettering Cancer Center, to explore how dermatology is navigating AI, data quality, and real-world implementation challenges.Dermatology is one of the most image-driven specialties in medicine, yet its imaging workflows have evolved very differently from those in radiology and pathology. As AI models promise improved diagnostic performance, new questions emerge around benchmarking, overfitting, clinical context, and bias.In this conversation, we cover:• Why AI became a forcing function for dermatology informatics• The limits of single-image benchmarking and reader studies• The “ugly duckling” concept in melanoma detection• Overfitting risks from lighting, markers, camera differences, and workflow artifacts• Skin tone bias in AI models and why labelling is harder than it sounds• Why testing AI in its intended clinical use setting is critical⸻⏱ Chapters00:00 – Introduction: Dermatology & Imaging Informatics02:33 – Dr. Rotemberg’s Journey into Dermatology Informatics05:26 – The AI Inflection Point (2017) and the Data Wake-Up Call07:58 – The “Wild West” of Dermatology Image Capture09:42 – AI Hype vs. Clinical Reality11:17 – Where AI Actually Fits in Dermatology Today12:45 – Single-Image Benchmarking and Reader Studies15:23 – The “Ugly Duckling” Concept Explained17:58 – Overfitting: Lighting, Cameras, and Workflow Artifacts18:42 – Augmentation Strategies and Hidden Bias Signals21:22 – Skin Tone Bias in Dermatology AI24:47 – Testing AI in the Intended Clinical Use Setting26:09 – The Future of Dermatology Informatics27:38 – “You’re an Informaticist. You Just Don’t Know It Yet.”⸻Dr. Rotemberg holds a PhD in Biomedical Engineering, leads an NIH-funded AI and informatics research lab, chairs the Augmented Intelligence Committee of the American Academy of Dermatology, and serves on the Board of Directors of the Society for Imaging Informatics in Medicine.If you’re interested in enterprise imaging, clinical AI validation, dermatology informatics, or bias in machine learning, this episode delivers a grounded, clinician-informed perspective.🔔 Subscribe for more deep conversations on imaging informatics, AI in healthcare, enterprise imaging, DICOM, FHIR, and real-world clinical systems.🌐 Keep an eye on https://nagelsconsulting.com for upcoming course launches and major updates to our imaging informatics training programs.

If you work in medical imaging, DICOM is everywhere — even when you don’t see it.In this episode of Imaging Informatics Unplugged, Jason Nagels sits down with John Hally, Product Leader for Cloud and Technical Platforms at Merge, to break down what DICOM toolkits really do and why they matter more than ever as imaging expands beyond radiology.John brings over 15 years of medical imaging technical experience and more than a decade in product management, leading global strategy for the Merge VNA, DICOM and HL7 Toolkits, cloud platforms, and digital pathology. This conversation goes deep into the infrastructure that quietly powers interoperability across healthcare.What you’ll learn in this episode: • What a DICOM toolkit actually is (and what it isn’t) • Why AI vendors and new imaging startups often underestimate DICOM complexity • When organizations realize they need a toolkit instead of building DICOM from scratch • Open source vs commercial DICOM toolkits: tradeoffs, risk, and scalability • How cloud-native architectures, ARM processors, and containers are changing imaging platforms • Enterprise imaging beyond radiology: pathology, ophthalmology, scope video, and more • Why HTJ2K (High-Throughput JPEG 2000) is a big deal for large imaging datasets • How standards evolve and why “doing DICOM” doesn’t always mean doing it correctlyThis episode is essential listening for: • PACS administrators and imaging informatics professionals • AI companies entering healthcare imaging • Product managers and developers building imaging platforms • Clinical and technical leaders working on enterprise imaging strategies • Anyone preparing for CIIP or deepening their understanding of imaging standards👉 Like, subscribe, and turn on notifications so you don’t miss future episodes of Imaging Informatics Unplugged.🚀 Keep an eye on nagelsconsulting.com for upcoming courses focused on imaging standards, enterprise imaging, and real-world interoperability. Some big things are coming.