<a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms">Send us a text</a>Why does it take three years to deploy a digital pathology tool that only took three weeks to build? That’s the reality no one talks about—but every lab feels every time they deploy a new tool...In this episode, I sit down with Andrew Janowczyk, Assistant Professor at Emory University and one of the leading voices in computational pathology, to unpack the practical, messy, real-world truth behind deploying, validating, and accrediting digital pathology tools in the clinic.We walk through Andrew’s experience building and implementing an H. pylori detection algorithm at Geneva University Hospital—a project that exposed every hidden challenge in the transition from research to a clinical-grade tool.From algorithmic hardening, multidisciplinary roles, usability studies, and ISO 15189 accreditation, to the constant tug-of-war between research ambition and clinical reality… this conversation is a roadmap for anyone building digital tools that actually need to work in practice. Episode Highlights<ul><li>[00:00–04:20] Why multidisciplinary collaboration is the non-negotiable cornerstone of clinical digital pathology deployment</li><li>[04:20–08:30] Real-world insight: The H. pylori detection tool and how it surfaces “top 20” likely regions for pathologist review</li><li>[08:30–12:50] The painful truth: Algorithms take weeks to build—but years to deploy, validate, and accredit</li><li>[12:50–17:40] Why curated research datasets fail in the real world (and how to fix it with unbiased data collection)</li><li>[17:40–23:00] Algorithmic hardening: turning fragile research code into production-ready clinical software</li><li>[23:00–28:10] Why every hospital is a snowflake: no standard workflows, no copy-paste deployments</li><li>[28:10–33:00] The 12 validation and accreditation roles every lab needs to define (EP, DE, QE, IT, etc.)</li><li>[33:00–38:15] Validation vs. accreditation—what they are, how they differ, and when each matters</li><li>[38:15–43:40] Version locking, drift prevention, and why monitoring is as important as deployment</li><li>[43:40–48:55] Deskilling concerns: how AI changes perception and what pathologists need before adoption</li><li>[48:55–55:00] Usability testing: why naive users reveal the truth about your UI</li><li>[55:00–61:00] Scaling to dozens of algorithms: bottlenecks, documentation, and the future of clinical digital pathology and AI workflows </li></ul>Resources From This Episode <ul><li><a href='https://www.preprints.org/manuscript/202509.1090'>Janowczyk &amp; Ferrari: Guide to Deploying Clinical Digital Pathology Tools</a> (discussed)</li><li><a href='https://medical.sectra.com/product/sectra-digital-pathology-solution/'>Sectra Image Management System (IMS)</a></li><li><a href='https://pubmed.ncbi.nlm.nih.gov/40816301/'>Endoscopist deskilling risk after exposure to artificial intelligence in colonoscopy: a multicentre, observational study - PubMed</a></li><li><a href='https://www.aleksandrazuraw.com/book'>Digital Pathology 101 (Aleksandra Zuraw) </a> </li></ul>Key Takeaways <ul><li>Algorithm creation is the easy part—deployment is the mountain.</li><li>Clinical algorithms require multidisciplinary ownership across 12 institutional roles.</li><li>Real-world data is messy—and that’s exactly why algorithms must be trained on it.</li><li>No two hospitals are alike; every deployment requires local adaptation.</li><li>Usability matters as much as accuracy—naive users expose real workflow constraints.</li><li>Patho</li></ul><a rel="payment" href="https://www.buzzsprout.com/410071/support">Support the show</a>Get the <a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'>&quot;Digital Pathology 101&quot; FREE E-book and join us!</a>

<description>&lt;p&gt;&lt;a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms"&gt;Send us a text&lt;/a&gt;&lt;/p&gt;&lt;p&gt;&lt;em&gt;Why does it take three years to deploy a digital pathology tool that only took three weeks to build? That’s the reality no one talks about—but every lab feels every time they deploy a new tool...&lt;/em&gt;&lt;/p&gt;&lt;p&gt;In this episode, I sit down with Andrew Janowczyk, Assistant Professor at Emory University and one of the leading voices in computational pathology, to unpack the practical, messy, real-world truth behind deploying, validating, and accrediting digital pathology tools in the clinic.&lt;/p&gt;&lt;p&gt;We walk through Andrew’s experience building and implementing an H. pylori detection algorithm at Geneva University Hospital—a project that exposed every hidden challenge in the transition from research to a clinical-grade tool.&lt;/p&gt;&lt;p&gt;From algorithmic hardening, multidisciplinary roles, usability studies, and ISO 15189 accreditation, to the constant tug-of-war between research ambition and clinical reality… this conversation is a roadmap for anyone building digital tools that actually need to work &lt;em&gt;in practice&lt;/em&gt;.&lt;/p&gt;&lt;p&gt;&lt;br/&gt;Episode Highlights&lt;/p&gt;&lt;ul&gt;&lt;li&gt;[00:00–04:20] Why multidisciplinary collaboration is the &lt;em&gt;non-negotiable&lt;/em&gt; cornerstone of clinical digital pathology deployment&lt;/li&gt;&lt;li&gt;[04:20–08:30] Real-world insight: The H. pylori detection tool and how it surfaces “top 20” likely regions for pathologist review&lt;/li&gt;&lt;li&gt;[08:30–12:50] The painful truth: Algorithms take weeks to build—but &lt;em&gt;years&lt;/em&gt; to deploy, validate, and accredit&lt;/li&gt;&lt;li&gt;[12:50–17:40] Why curated research datasets fail in the real world (and how to fix it with unbiased data collection)&lt;/li&gt;&lt;li&gt;[17:40–23:00] Algorithmic hardening: turning fragile research code into production-ready clinical software&lt;/li&gt;&lt;li&gt;[23:00–28:10] Why every hospital is a snowflake: no standard workflows, no copy-paste deployments&lt;/li&gt;&lt;li&gt;[28:10–33:00] The 12 validation and accreditation roles every lab needs to define (EP, DE, QE, IT, etc.)&lt;/li&gt;&lt;li&gt;[33:00–38:15] Validation vs. accreditation—what they are, how they differ, and when each matters&lt;/li&gt;&lt;li&gt;[38:15–43:40] Version locking, drift prevention, and why monitoring is as important as deployment&lt;/li&gt;&lt;li&gt;[43:40–48:55] Deskilling concerns: how AI changes perception and what pathologists need before adoption&lt;/li&gt;&lt;li&gt;[48:55–55:00] Usability testing: why naive users reveal the truth about your UI&lt;/li&gt;&lt;li&gt;[55:00–61:00] Scaling to dozens of algorithms: bottlenecks, documentation, and the future of clinical digital pathology and AI workflows&lt;br/&gt;&lt;br/&gt;&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;Resources From This Episode&lt;/b&gt;&lt;br/&gt;&lt;br/&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;&lt;a href='https://www.preprints.org/manuscript/202509.1090'&gt;Janowczyk &amp;amp; Ferrari: Guide to Deploying Clinical Digital Pathology Tools&lt;/a&gt; (discussed)&lt;/li&gt;&lt;li&gt;&lt;a href='https://medical.sectra.com/product/sectra-digital-pathology-solution/'&gt;Sectra Image Management System (IMS)&lt;/a&gt;&lt;/li&gt;&lt;li&gt;&lt;a href='https://pubmed.ncbi.nlm.nih.gov/40816301/'&gt;Endoscopist deskilling risk after exposure to artificial intelligence in colonoscopy: a multicentre, observational study - PubMed&lt;/a&gt;&lt;/li&gt;&lt;li&gt;&lt;a href='https://www.aleksandrazuraw.com/book'&gt;Digital Pathology 101 (Aleksandra Zuraw)&lt;br/&gt;&lt;/a&gt;&lt;br/&gt;&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;Key Takeaways&lt;/b&gt;&lt;br/&gt;&lt;br/&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;Algorithm creation is the easy part—deployment is the mountain.&lt;/li&gt;&lt;li&gt;Clinical algorithms require multidisciplinary ownership across 12 institutional roles.&lt;/li&gt;&lt;li&gt;Real-world data is messy—and that’s exactly why algorithms must be trained on it.&lt;/li&gt;&lt;li&gt;No two hospitals are alike; every deployment requires local adaptation.&lt;/li&gt;&lt;li&gt;Usability matters as much as accuracy—naive users expose real workflow constraints.&lt;/li&gt;&lt;li&gt;Patho&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;a rel="payment" href="https://www.buzzsprout.com/410071/support"&gt;Support the show&lt;/a&gt;&lt;/p&gt;&lt;p&gt;Get the &lt;a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'&gt;&amp;quot;Digital Pathology 101&amp;quot; FREE E-book and join us!&lt;/a&gt;&lt;/p&gt;</description>

Send us a text Why does it take three years to deploy a digital pathology tool that only took three weeks to build? That’s the reality no one talks about—but every lab feels every time they deploy a new tool... In this episode, I sit down with Andrew Janowczyk, Assistant Professor at Emory University and one of the leading voices in computational pathology, to unpack the practical, messy, real-world truth behind deploying, validating, and accrediting digital pathology tools in the clinic. We ...

175: Deploying Digital Pathology Tools - Challenges and Insights with Dr. Andrew Janowczyk 

<a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms">Send us a text</a>Why are billions of people still invisible in genomic research—and what does that mean for the future of precision medicine?In this episode, I sit down with Victor Angel Mosti, founder and CEO of Omica.Ai, for one of the most insightful conversations I’ve recorded about data equity and building ethical, community-centered AI.Victor shares not only his personal cancer story but also the staggering truth: Hispanic and Latino populations make up less than 1% of genomic datasets. This underrepresentation isn’t just a data gap—it’s a clinical risk.We dive into disparities between healthcare systems, the promise of digital pathology as a low-cost entry point, the dangers of “parachute science,” and how Victor is building a living, ethical, transparent biobank through Omica. AI—built for true precision medicine rooted in community trust. Highlights with Timestamps<ul><li>[00:00–01:40] Personal cancer experiences and diagnostic uncertainty</li><li>[01:40–06:50] Victor’s medical journey across Mexico and the U.S.</li><li>[06:50–11:42] The digitization gap: empathy vs. tech</li><li>[11:42–16:43] The “coffee diversity” metaphor for genomic diversity</li><li>[16:43–19:34] Funding disparities &amp; the biotech cold-start problem</li><li>[19:34–25:44] Digital pathology as a gateway to precision medicine</li><li>[25:44–31:44] Avoiding “parachute science” and building community-first research</li><li>[31:44–36:05] The Nagoya Protocol and benefit-sharing</li><li>[36:05–41:47] Omica.Ai’s work, goals, and clinical-embedded approach</li><li>[41:47–49:36] Creating future-proof, embedded biobanks</li><li>[49:36–53:35] Blockchain for transparency and patient trust</li><li>[53:35–54:39] Victor’s call to action: collaborate, include, and stay human </li></ul>Resources from This Episode<ul><li><a href='https://www.omica.bio/'>Omica.Ai</a> – Community-driven precision medicine platform</li><li><a href='https://www.cbd.int/abs/default.shtml2'>Nagoya Protocol</a> – Framework for equitable biological use </li></ul>Key Insights<ul><li>Cancer is personal—even for experts</li><li>&lt;1% representation of Latino genomes threatens clinical accuracy</li><li>Digital pathology + AI can leapfrog infrastructure gaps</li><li>Ethical biobanking requires trust, transparency, and local benefit</li><li>Avoiding “parachute science” is essential</li><li>Genetic diversity drives discovery—but only if we capture it</li><li>Blockchain + dynamic consent = future of patient-centered data </li></ul><a rel="payment" href="https://www.buzzsprout.com/410071/support">Support the show</a>Get the <a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'>&quot;Digital Pathology 101&quot; FREE E-book and join us!</a>

<description>&lt;p&gt;&lt;a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms"&gt;Send us a text&lt;/a&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;&lt;em&gt;Why are billions of people still invisible in genomic research—and what does that mean for the future of precision medicine?&lt;/em&gt;&lt;/b&gt;&lt;/p&gt;&lt;p&gt;In this episode, I sit down with Victor Angel Mosti, founder and CEO of Omica.Ai, for one of the most insightful conversations I’ve recorded about data equity and building ethical, community-centered AI.&lt;/p&gt;&lt;p&gt;Victor shares not only his personal cancer story but also the staggering truth: Hispanic and Latino populations make up less than 1% of genomic datasets. This underrepresentation isn’t just a data gap—it’s a clinical risk.&lt;/p&gt;&lt;p&gt;We dive into disparities between healthcare systems, the promise of digital pathology as a low-cost entry point, the dangers of “parachute science,” and how Victor is building a living, ethical, transparent biobank through Omica. AI—built for true precision medicine rooted in community trust.&lt;/p&gt;&lt;p&gt;&lt;br/&gt;&lt;b&gt;Highlights with Timestamps&lt;/b&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;[00:00–01:40] Personal cancer experiences and diagnostic uncertainty&lt;/li&gt;&lt;li&gt;[01:40–06:50] Victor’s medical journey across Mexico and the U.S.&lt;/li&gt;&lt;li&gt;[06:50–11:42] The digitization gap: empathy vs. tech&lt;/li&gt;&lt;li&gt;[11:42–16:43] The “coffee diversity” metaphor for genomic diversity&lt;/li&gt;&lt;li&gt;[16:43–19:34] Funding disparities &amp;amp; the biotech cold-start problem&lt;/li&gt;&lt;li&gt;[19:34–25:44] Digital pathology as a gateway to precision medicine&lt;/li&gt;&lt;li&gt;[25:44–31:44] Avoiding “parachute science” and building community-first research&lt;/li&gt;&lt;li&gt;[31:44–36:05] The Nagoya Protocol and benefit-sharing&lt;/li&gt;&lt;li&gt;[36:05–41:47] Omica.Ai’s work, goals, and clinical-embedded approach&lt;/li&gt;&lt;li&gt;[41:47–49:36] Creating future-proof, embedded biobanks&lt;/li&gt;&lt;li&gt;[49:36–53:35] Blockchain for transparency and patient trust&lt;/li&gt;&lt;li&gt;[53:35–54:39] Victor’s call to action: collaborate, include, and stay human&lt;br/&gt;&lt;br/&gt;&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;Resources from This Episode&lt;/b&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;&lt;a href='https://www.omica.bio/'&gt;&lt;b&gt;&lt;em&gt;Omica.Ai&lt;/em&gt;&lt;/b&gt;&lt;/a&gt; – Community-driven precision medicine platform&lt;/li&gt;&lt;li&gt;&lt;a href='https://www.cbd.int/abs/default.shtml2'&gt;&lt;b&gt;&lt;em&gt;Nagoya Protocol&lt;/em&gt;&lt;/b&gt;&lt;/a&gt; – Framework for equitable biological use&lt;br/&gt;&lt;br/&gt;&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;Key Insights&lt;/b&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;Cancer is personal—even for experts&lt;/li&gt;&lt;li&gt;&amp;lt;1% representation of Latino genomes threatens clinical accuracy&lt;/li&gt;&lt;li&gt;Digital pathology + AI can leapfrog infrastructure gaps&lt;/li&gt;&lt;li&gt;Ethical biobanking requires trust, transparency, and local benefit&lt;/li&gt;&lt;li&gt;Avoiding “parachute science” is essential&lt;/li&gt;&lt;li&gt;Genetic diversity drives discovery—but only if we capture it&lt;/li&gt;&lt;li&gt;Blockchain + dynamic consent = future of patient-centered data&lt;br/&gt;&lt;br/&gt;&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;a rel="payment" href="https://www.buzzsprout.com/410071/support"&gt;Support the show&lt;/a&gt;&lt;/p&gt;&lt;p&gt;Get the &lt;a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'&gt;&amp;quot;Digital Pathology 101&amp;quot; FREE E-book and join us!&lt;/a&gt;&lt;/p&gt;</description>

Send us a text Why are billions of people still invisible in genomic research—and what does that mean for the future of precision medicine? In this episode, I sit down with Victor Angel Mosti, founder and CEO of Omica.Ai, for one of the most insightful conversations I’ve recorded about data equity and building ethical, community-centered AI. Victor shares not only his personal cancer story but also the staggering truth: Hispanic and Latino populations make up less than 1% of genomic datasets....

174: How Do We Fix the Bias in Biomedical AI Podcast with Victor CEO and Founder of Omica.Ai

<a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms">Send us a text</a>How far can AI go in helping us diagnose disease—without losing the human judgment patients rely on?In this episode, I break down four studies shaping the future of digital pathology, oncology, and neurology. From spatial biology updates at SITC to voice-based Alzheimer’s detection, deep learning for sarcoma prognosis, and new guidelines for safe AI deployment, this week’s digest highlights where AI is making a real impact—and where caution still matters.Episode Highlights1️⃣ SITC Trends &amp; Spatial Biology (00:00 → 07:40)I share key updates from SITC 2025, including the growing role of multiplex immunofluorescence (mIF) and the need for integrated staining-to-scanning workflows. I also preview new educational content and upcoming podcast guests in global AI research.2️⃣ Digital Neuropathology &amp; Alzheimer’s (07:40 → 13:01)A major review confirms that digital neuropathology is now robust enough for large-scale Alzheimer’s studies—opening doors for computational tools to link histology with cognition.3️⃣ Patient Safety in AI (13:01 → 19:56)An Italian review underscores the foundations of trustworthy AI: dataset quality, transparency, oversight, and continuous validation. I discuss why “patient-centered AI” must remain our standard.4️⃣ Voice Biomarkers for Cognitive Decline (19:56 → 26:43)AI models analyzing short speech recordings are showing high accuracy for early Alzheimer’s detection. This could make future screening simple, noninvasive, and more accessible.5️⃣ Deep Learning for Sarcoma Prognosis (34:06 → 35:59)A multi-instance CNN outperforms FNCLCC grading by identifying prognostic patterns in tumor center and periphery regions, offering new insights into soft-tissue sarcoma biology.Takeaways<ul><li>mIF is maturing quickly but needs standardized, end-to-end workflows.</li><li>Digital neuropathology is ready for broader Alzheimer’s research.</li><li>Safe AI requires multidisciplinary collaboration and rigorous validation.</li><li>Voice biomarkers may become powerful tools for early cognitive assessment.</li><li>Deep learning can refine prognosis and reveal hidden tumor patterns.</li></ul>ResourcesHamamatsu (MoxiePlex) • Biocare Medical (ONCORE Pro X) • SITC Programs • Recent publications on AI biomarkers and computational pathology.Thanks for listening—and for being part of this growing digital pathology community.<a rel="payment" href="https://www.buzzsprout.com/410071/support">Support the show</a>Get the <a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'>&quot;Digital Pathology 101&quot; FREE E-book and join us!</a>

<description>&lt;p&gt;&lt;a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms"&gt;Send us a text&lt;/a&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;&lt;em&gt;How far can AI go in helping us diagnose disease—without losing the human judgment patients rely on?&lt;/em&gt;&lt;/b&gt;&lt;/p&gt;&lt;p&gt;In this episode, I break down four studies shaping the future of digital pathology, oncology, and neurology. From spatial biology updates at SITC to voice-based Alzheimer’s detection, deep learning for sarcoma prognosis, and new guidelines for safe AI deployment, this week’s digest highlights where AI is making a real impact—and where caution still matters.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Episode Highlights&lt;/b&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;1️⃣ SITC Trends &amp;amp; Spatial Biology (00:00 → 07:40)&lt;/b&gt;&lt;/p&gt;&lt;p&gt;I share key updates from SITC 2025, including the growing role of &lt;b&gt;multiplex immunofluorescence (mIF)&lt;/b&gt; and the need for integrated staining-to-scanning workflows. I also preview new educational content and upcoming podcast guests in global AI research.&lt;/p&gt;&lt;p&gt;&lt;b&gt;2️⃣ Digital Neuropathology &amp;amp; Alzheimer’s (07:40 → 13:01)&lt;/b&gt;&lt;/p&gt;&lt;p&gt;A major review confirms that digital neuropathology is now robust enough for large-scale Alzheimer’s studies—opening doors for computational tools to link histology with cognition.&lt;/p&gt;&lt;p&gt;&lt;b&gt;3️⃣ Patient Safety in AI (13:01 → 19:56)&lt;/b&gt;&lt;/p&gt;&lt;p&gt;An Italian review underscores the foundations of trustworthy AI: dataset quality, transparency, oversight, and continuous validation. I discuss why “patient-centered AI” must remain our standard.&lt;/p&gt;&lt;p&gt;&lt;b&gt;4️⃣ Voice Biomarkers for Cognitive Decline (19:56 → 26:43)&lt;/b&gt;&lt;/p&gt;&lt;p&gt;AI models analyzing short speech recordings are showing high accuracy for early Alzheimer’s detection. This could make future screening simple, noninvasive, and more accessible.&lt;/p&gt;&lt;p&gt;&lt;b&gt;5️⃣ Deep Learning for Sarcoma Prognosis (34:06 → 35:59)&lt;/b&gt;&lt;/p&gt;&lt;p&gt;A multi-instance CNN outperforms FNCLCC grading by identifying prognostic patterns in tumor center and periphery regions, offering new insights into soft-tissue sarcoma biology.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Takeaways&lt;/b&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;mIF is maturing quickly but needs standardized, end-to-end workflows.&lt;/li&gt;&lt;li&gt;Digital neuropathology is ready for broader Alzheimer’s research.&lt;/li&gt;&lt;li&gt;Safe AI requires multidisciplinary collaboration and rigorous validation.&lt;/li&gt;&lt;li&gt;Voice biomarkers may become powerful tools for early cognitive assessment.&lt;/li&gt;&lt;li&gt;Deep learning can refine prognosis and reveal hidden tumor patterns.&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;Resources&lt;/b&gt;&lt;/p&gt;&lt;p&gt;Hamamatsu (MoxiePlex) • Biocare Medical (ONCORE Pro X) • SITC Programs • Recent publications on AI biomarkers and computational pathology.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Thanks for listening—and for being part of this growing digital pathology community.&lt;/b&gt;&lt;/p&gt;&lt;p&gt;&lt;a rel="payment" href="https://www.buzzsprout.com/410071/support"&gt;Support the show&lt;/a&gt;&lt;/p&gt;&lt;p&gt;Get the &lt;a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'&gt;&amp;quot;Digital Pathology 101&amp;quot; FREE E-book and join us!&lt;/a&gt;&lt;/p&gt;</description>

Send us a text How far can AI go in helping us diagnose disease—without losing the human judgment patients rely on? In this episode, I break down four studies shaping the future of digital pathology, oncology, and neurology. From spatial biology updates at SITC to voice-based Alzheimer’s detection, deep learning for sarcoma prognosis, and new guidelines for safe AI deployment, this week’s digest highlights where AI is making a real impact—and where caution still matters. Episode Highlights 1️...

173: AI and the Human Touch: Patient Safety, Prognosis & Voice Biomarkers

<a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms">Send us a text</a>If your pathology reports and other data could talk, what would they say about the future of precision medicine? The truth is, most labs already have the data—they’re just not having a conversation with it.In this episode, I talk with Peter O’Toole, President and Chief Software Architect at<a href='https://www.mtuitive.com/'> mTuitive</a>. We recorded live at Pathology Visions and are covering the power of structured data and how it’s redefining the future of pathology reporting, AI, and clinical decision support.We explore how structured reporting evolved from checklists to intelligence, why data hygiene and workflow integration matter more than AI buzzwords, and how collaboration across companies like <a href='https://www.mtuitive.com/'>mTuitive</a> is helping labs turn their reports into clinically actionable data. Highlights with Timestamps<ul><li>[00:00–05:40] Data as the new currency in pathology — Why structured data is the foundation for clinical, research, and trial insights.</li><li>[05:40–10:30] AI &amp; Large Language Models (LLMs) — What AI can (and can’t) do when your data isn’t structured.</li><li>[10:30–19:25] AI workflow integration &amp; voice recognition — How AI and structured reporting work together inside the LIS and IMS.</li><li>[19:25–25:27] Overcoming resistance — Why pathologists initially resisted structured reports and how perceptions are shifting globally.</li><li>[25:27–29:53] Decision support &amp; beyond cancer — Expanding structured data to liver, skin, and even mental health pathology.</li><li>[29:53–34:15] Collaboration as the catalyst — How partnerships create seamless ecosystems for pathology data.</li><li>[34:15–37:03] Demo: Synoptic reporting in action — Real-time staging, automation, and compliance made easy. </li></ul>Resources from this Episode<ul><li>mTuitive website:<a href='https://mtuitive.com'> https://mtuitive.com</a></li><li><a href='https://www.cap.org/protocols-and-guidelines/cancer-reporting-tools/cancer-protocol-templates'>CAP Synoptic Reporting Protocols</a> – Standardized templates for structured pathology reports.</li><li><a href='https://www.youtube.com/playlist?list=PLPYjKofDEhNO3PBcCnbJORk9vJF6--arq'>Pathology Visions Conference 2025</a> – Event where this discussion took place. </li></ul>Key Takeaways✅ Structured reporting transforms pathology data from static text into actionable intelligence. ✅ AI and LLMs complement structured data—but can’t replace its clinical readiness. ✅ Clean data in = clean data out—data hygiene defines AI reliability and efficiency. ✅ Workflow integration and user-friendly design drive real-world adoption. ✅ Structured data unlocks clinical trials access, research potential, and decision support tools. ✅ Collaboration is key to building the connected ecosystem pathology needs.<a rel="payment" href="https://www.buzzsprout.com/410071/support">Support the show</a>Get the <a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'>&quot;Digital Pathology 101&quot; FREE E-book and join us!</a>

<description>&lt;p&gt;&lt;a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms"&gt;Send us a text&lt;/a&gt;&lt;/p&gt;&lt;p&gt;If your pathology reports and other data could talk, what would they say about the future of precision medicine? The truth is, most labs already &lt;em&gt;have&lt;/em&gt; the data—they’re just not having a conversation with it.&lt;/p&gt;&lt;p&gt;In this episode, I talk with Peter O’Toole, President and Chief Software Architect at&lt;a href='https://www.mtuitive.com/'&gt; &lt;b&gt;&lt;em&gt;mTuitive&lt;/em&gt;&lt;/b&gt;&lt;/a&gt;. We recorded live at Pathology Visions and are covering the power of structured data and how it’s redefining the future of pathology reporting, AI, and clinical decision support.&lt;/p&gt;&lt;p&gt;We explore how structured reporting evolved from checklists to intelligence, why data hygiene and workflow integration matter more than AI buzzwords, and how collaboration across companies like &lt;a href='https://www.mtuitive.com/'&gt;&lt;b&gt;&lt;em&gt;mTuitive&lt;/em&gt;&lt;/b&gt;&lt;/a&gt; is helping labs turn their reports into &lt;em&gt;clinically actionable data&lt;/em&gt;.&lt;/p&gt;&lt;p&gt;&lt;br/&gt;&lt;b&gt;Highlights with Timestamps&lt;/b&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;[00:00–05:40] &lt;em&gt;Data as the new currency in pathology&lt;/em&gt; — Why structured data is the foundation for clinical, research, and trial insights.&lt;/li&gt;&lt;li&gt;[05:40–10:30] &lt;em&gt;AI &amp;amp; Large Language Models (LLMs)&lt;/em&gt; — What AI can (and can’t) do when your data isn’t structured.&lt;/li&gt;&lt;li&gt;[10:30–19:25] &lt;em&gt;AI workflow integration &amp;amp; voice recognition&lt;/em&gt; — How AI and structured reporting work together inside the LIS and IMS.&lt;/li&gt;&lt;li&gt;[19:25–25:27] &lt;em&gt;Overcoming resistance&lt;/em&gt; — Why pathologists initially resisted structured reports and how perceptions are shifting globally.&lt;/li&gt;&lt;li&gt;[25:27–29:53] &lt;em&gt;Decision support &amp;amp; beyond cancer&lt;/em&gt; — Expanding structured data to liver, skin, and even mental health pathology.&lt;/li&gt;&lt;li&gt;[29:53–34:15] &lt;em&gt;Collaboration as the catalyst&lt;/em&gt; — How partnerships create seamless ecosystems for pathology data.&lt;/li&gt;&lt;li&gt;[34:15–37:03] &lt;em&gt;Demo: Synoptic reporting in action&lt;/em&gt; — Real-time staging, automation, and compliance made easy.&lt;br/&gt;&lt;br/&gt;&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;Resources from this Episode&lt;/b&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;mTuitive website:&lt;a href='https://mtuitive.com'&gt; https://mtuitive.com&lt;/a&gt;&lt;/li&gt;&lt;li&gt;&lt;a href='https://www.cap.org/protocols-and-guidelines/cancer-reporting-tools/cancer-protocol-templates'&gt;CAP Synoptic Reporting Protocols&lt;/a&gt; – Standardized templates for structured pathology reports.&lt;/li&gt;&lt;li&gt;&lt;a href='https://www.youtube.com/playlist?list=PLPYjKofDEhNO3PBcCnbJORk9vJF6--arq'&gt;Pathology Visions Conference 2025&lt;/a&gt; – Event where this discussion took place.&lt;br/&gt;&lt;br/&gt;&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;Key Takeaways&lt;/b&gt;&lt;/p&gt;&lt;p&gt;✅ Structured reporting transforms pathology data from static text into actionable intelligence.&lt;br/&gt;✅ AI and LLMs complement structured data—but can’t replace its clinical readiness.&lt;br/&gt;✅ Clean data in = clean data out—data hygiene defines AI reliability and efficiency.&lt;br/&gt;✅ Workflow integration and user-friendly design drive real-world adoption.&lt;br/&gt;✅ Structured data unlocks clinical trials access, research potential, and decision support tools.&lt;br/&gt;✅ Collaboration is key to building the connected ecosystem pathology needs.&lt;/p&gt;&lt;p&gt;&lt;a rel="payment" href="https://www.buzzsprout.com/410071/support"&gt;Support the show&lt;/a&gt;&lt;/p&gt;&lt;p&gt;Get the &lt;a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'&gt;&amp;quot;Digital Pathology 101&amp;quot; FREE E-book and join us!&lt;/a&gt;&lt;/p&gt;</description>

Send us a text If your pathology reports and other data could talk, what would they say about the future of precision medicine? The truth is, most labs already have the data—they’re just not having a conversation with it. In this episode, I talk with Peter O’Toole, President and Chief Software Architect at mTuitive. We recorded live at Pathology Visions and are covering the power of structured data and how it’s redefining the future of pathology reporting, AI, and clinical decision support. W...

172: Why Structured Reporting Is the Future of Pathology | mTuitive on Workflow, Data & Compliance with Peter O'Toole 

<a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms">Send us a text</a>Is your lab truly digitally ready—or just scanning slides?That’s the question I unpack in this live discussion from Day 2 of SITC’s 40th Anniversary Meeting, joined by David Anderson (Biocare Medical) and Don Ariyakumar (Hamamatsu Photonics). Together, we explore what digital readiness really means for multiplex immunofluorescence (mIF) and how to build reliable, reproducible workflows that scale from research to clinical settings.What We DiscussThe Discovery Funnel I open by situating mIF within the broader discovery funnel: researchers begin with hundreds of biomarkers, narrowing down to focused 4–10 marker panels where true clinical utility begins. But this only works if the lab is digitally prepared from the start—from slide prep to data capture.Defining Digital Readiness David Anderson reframes digital readiness as everything that happens before the scanner turns on:<ul><li>Reagent consistency</li><li>Antibody optimization</li><li>Automation</li><li>Standardized protocols  All these elements ensure that downstream AI and image analysis tools work on clean, reproducible data instead of “fixing” noise later.</li></ul>The Pre-Analytical Foundation Don Ariyakumar emphasizes that scanning can’t fix variability. If staining or section quality isn’t standardized, digitization simply amplifies inconsistencies. True readiness starts at the bench, not the monitor.Integration Across Vendors We also talk about how interoperability between stainers, scanners, and spatial biology software is becoming essential. A disconnected workflow—mixing manual, unaligned steps—adds variables that no algorithm can fully normalize.Lessons from IHC’s Evolution The team draws parallels between multiplex IF today and IHC’s early days: once complex, now routine. Multiplex IF promises even richer tumor microenvironment insights, but only if standardization and automation catch up to the technology.Beyond the Funnel I revisit the “funnel” metaphor in a new light—arguing that as precision medicine grows, the bottom of the funnel broadens, not narrows. That means more tailored, smaller panels rather than one-size-fits-all assays, and a growing need for efficient, reproducible digital workflows.Key Takeaways<ul><li>“Digital readiness” starts before scanning — with chemistry, automation, and process control.</li><li>Consistent pre-analytical quality = reproducible, AI-ready data.</li><li>Interoperability between systems (like Biocare’s ONCORE Pro X and Hamamatsu’s MoxiePlex) accelerates workflow standardization.</li><li>Multiplex IF is maturing quickly, just as IHC once did—on its way to becoming a cornerstone of precision pathology.</li></ul>Resources Mentioned🔹 Biocare Medical (Booth 717) — ONCORE Pro X™ open slide stainer automating mIF, IHC, FISH, and ISH protocols. 🌐 <a href='https://www.biocare.net'>biocare.net</a> 🔹 Hamamatsu Photonics (Booth 415) — MoxiePlex™ multispectral imaging platform for high-plex spatial analysis. 🌐 <a href='https://www.hamamatsu.com'>hamamatsu.com</a> 🔹 Society for Immunotherapy of Cancer (SITC) — 40th Anniversary Meeting information and programs. 🌐 <a href='https://www.sitcancer.org'>sitcancer.org</a> Timestamp Highlights00:00 — Welcome from SITC<a rel="payment" href="https://www.buzzsprout.com/410071/support">Support the show</a>Get the <a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'>&quot;Digital Pathology 101&quot; FREE E-book and join us!</a>

<description>&lt;p&gt;&lt;a target="_blank" href="https://www.buzzsprout.com/twilio/text_messages/410071/open_sms"&gt;Send us a text&lt;/a&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;&lt;em&gt;Is your lab truly digitally ready—or just scanning slides?&lt;/em&gt;&lt;/b&gt;&lt;/p&gt;&lt;p&gt;That’s the question I unpack in this live discussion from &lt;b&gt;Day 2 of SITC’s 40th Anniversary Meeting&lt;/b&gt;, joined by &lt;b&gt;David Anderson (Biocare Medical)&lt;/b&gt; and &lt;b&gt;Don Ariyakumar (Hamamatsu Photonics)&lt;/b&gt;. &lt;/p&gt;&lt;p&gt;Together, we explore what &lt;em&gt;digital readiness&lt;/em&gt; really means for &lt;b&gt;multiplex immunofluorescence (mIF)&lt;/b&gt; and how to build reliable, reproducible workflows that scale from research to clinical settings.&lt;/p&gt;&lt;p&gt;&lt;b&gt;What We Discuss&lt;/b&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;The Discovery Funnel&lt;/b&gt;&lt;br/&gt; I open by situating mIF within the broader &lt;em&gt;discovery funnel&lt;/em&gt;: researchers begin with hundreds of biomarkers, narrowing down to focused 4–10 marker panels where true clinical utility begins. But this only works if the lab is &lt;b&gt;digitally prepared from the start&lt;/b&gt;—from slide prep to data capture.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Defining Digital Readiness&lt;/b&gt;&lt;br/&gt; David Anderson reframes digital readiness as &lt;em&gt;everything that happens before the scanner turns on&lt;/em&gt;:&lt;/p&gt;&lt;ul&gt;&lt;li&gt;Reagent consistency&lt;/li&gt;&lt;li&gt;Antibody optimization&lt;/li&gt;&lt;li&gt;Automation&lt;/li&gt;&lt;li&gt;Standardized protocols&lt;br/&gt; All these elements ensure that downstream &lt;b&gt;AI and image analysis tools&lt;/b&gt; work on clean, reproducible data instead of “fixing” noise later.&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;&lt;b&gt;The Pre-Analytical Foundation&lt;/b&gt;&lt;br/&gt; Don Ariyakumar emphasizes that &lt;b&gt;scanning can’t fix variability&lt;/b&gt;. If staining or section quality isn’t standardized, digitization simply amplifies inconsistencies. True readiness starts at the bench, not the monitor.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Integration Across Vendors&lt;/b&gt;&lt;br/&gt; We also talk about how interoperability between &lt;b&gt;stainers, scanners, and spatial biology software&lt;/b&gt; is becoming essential. A disconnected workflow—mixing manual, unaligned steps—adds variables that no algorithm can fully normalize.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Lessons from IHC’s Evolution&lt;/b&gt;&lt;br/&gt; The team draws parallels between multiplex IF today and &lt;b&gt;IHC’s early days&lt;/b&gt;: once complex, now routine. Multiplex IF promises even richer tumor microenvironment insights, but only if &lt;b&gt;standardization and automation&lt;/b&gt; catch up to the technology.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Beyond the Funnel&lt;/b&gt;&lt;br/&gt; I revisit the “funnel” metaphor in a new light—arguing that as precision medicine grows, the bottom of the funnel broadens, not narrows. That means more &lt;b&gt;tailored, smaller panels&lt;/b&gt; rather than one-size-fits-all assays, and a growing need for &lt;b&gt;efficient, reproducible digital workflows&lt;/b&gt;.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Key Takeaways&lt;/b&gt;&lt;/p&gt;&lt;ul&gt;&lt;li&gt;“Digital readiness” starts before scanning — with chemistry, automation, and process control.&lt;/li&gt;&lt;li&gt;Consistent pre-analytical quality = reproducible, AI-ready data.&lt;/li&gt;&lt;li&gt;Interoperability between systems (like &lt;b&gt;Biocare’s ONCORE Pro X&lt;/b&gt; and &lt;b&gt;Hamamatsu’s MoxiePlex&lt;/b&gt;) accelerates workflow standardization.&lt;/li&gt;&lt;li&gt;Multiplex IF is maturing quickly, just as IHC once did—on its way to becoming &lt;b&gt;a cornerstone of precision pathology&lt;/b&gt;.&lt;/li&gt;&lt;/ul&gt;&lt;p&gt;Resources Mentioned&lt;/p&gt;&lt;p&gt;🔹 &lt;b&gt;Biocare Medical (Booth 717)&lt;/b&gt; — ONCORE Pro X™ open slide stainer automating mIF, IHC, FISH, and ISH protocols.&lt;br/&gt; 🌐 &lt;a href='https://www.biocare.net'&gt;biocare.net&lt;/a&gt;&lt;br/&gt;&lt;br/&gt;&lt;/p&gt;&lt;p&gt;🔹 &lt;b&gt;Hamamatsu Photonics (Booth 415)&lt;/b&gt; — MoxiePlex™ multispectral imaging platform for high-plex spatial analysis.&lt;br/&gt; 🌐 &lt;a href='https://www.hamamatsu.com'&gt;hamamatsu.com&lt;/a&gt;&lt;br/&gt;&lt;br/&gt;&lt;/p&gt;&lt;p&gt;🔹 &lt;b&gt;Society for Immunotherapy of Cancer (SITC)&lt;/b&gt; — 40th Anniversary Meeting information and programs.&lt;br/&gt; 🌐 &lt;a href='https://www.sitcancer.org'&gt;sitcancer.org&lt;/a&gt;&lt;br/&gt;&lt;br/&gt;&lt;/p&gt;&lt;p&gt;&lt;b&gt;Timestamp Highlights&lt;/b&gt;&lt;/p&gt;&lt;p&gt;00:00 — Welcome from SITC&lt;/p&gt;&lt;p&gt;&lt;a rel="payment" href="https://www.buzzsprout.com/410071/support"&gt;Support the show&lt;/a&gt;&lt;/p&gt;&lt;p&gt;Get the &lt;a href='https://digitalpathology.club/digital-pathology-beginners-guide-notification'&gt;&amp;quot;Digital Pathology 101&amp;quot; FREE E-book and join us!&lt;/a&gt;&lt;/p&gt;</description>

Send us a text Is your lab truly digitally ready—or just scanning slides? That’s the question I unpack in this live discussion from Day 2 of SITC’s 40th Anniversary Meeting, joined by David Anderson (Biocare Medical) and Don Ariyakumar (Hamamatsu Photonics).  Together, we explore what digital readiness really means for multiplex immunofluorescence (mIF) and how to build reliable, reproducible workflows that scale from research to clinical settings. What We Discuss The Discovery Funnel  I...

171: Real-World Digital Readiness: Turning Stains into Reliable Scans

Aleksandra Zuraw from Digital Pathology Place discusses digital pathology from the basic concepts to the newest developments, including image analysis and artificial intelligence. She reviews scientific literature and together with her guests discusses the current industry and research digital pathology trends.  

Digital Pathology Podcast

Details

Recent Episodes