--- title: Building AI That Learns and Adapts: A Case Study in MRI... description: A conference talk exploring continual learning through a real-world MRI diagnostics case study focused on detecting focal cortical dysplasias (FCDs), a common... canonical: https://daily.dev/posts/building-ai-that-learns-and-adapts-a-case-study-in-mri-diagnostics---agata-chudzi-ska-h3ujzviju twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Building AI That Learns and Adapts: A Case Study in MRI Diagnostics - Agata Chudzińska | daily.dev og:description: A conference talk exploring continual learning through a real-world MRI diagnostics case study focused on detecting focal cortical dysplasias (FCDs), a common... og:url: https://daily.dev/posts/building-ai-that-learns-and-adapts-a-case-study-in-mri-diagnostics---agata-chudzi-ska-h3ujzviju og:image: https://api.daily.dev/og/posts/H3uJZvIJU.png og:image:alt: Building AI That Learns and Adapts: A Case Study in MRI Diagnostics - Agata Chudzińska og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Building AI That Learns and Adapts: A Case Study in MRI Diagnostics - Agata Chudzińska **[NDC Conferences](https://daily.dev/sources/ndc)** · 42 min read · 0 upvotes · 0 comments ## Summary A conference talk exploring continual learning through a real-world MRI diagnostics case study focused on detecting focal cortical dysplasias (FCDs), a common cause of drug-resistant epilepsy. The speaker walks through building a U-Net based model, the challenges of small and imbalanced medical datasets, and how catastrophic forgetting undermines naive fine-tuning. Three families of continual learning methods are explained: regularization-based (elastic weight consolidation), memory replay, and architecture-based approaches. The team applied EWC to adapt their model to new data distributions without retraining from scratch, achieving comparable sensitivity with significantly fewer false positives. The talk concludes with broader applicability of continual learning in production ML systems and highlights Google's new 'nested learning' paradigm as a promising research direction. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Democratizing Alzheimer’s diagnosis: How interpretable AI brings early detection to underserved communities](https://daily.dev/posts/democratizing-alzheimer-s-diagnosis-how-interpretable-ai-brings-early-detection-to-underserved-comm-j53xoq2rx) · All Things Open · 0 upvotes · 0 comments - [I Built a Medical AI Model That Knows When to Say “I’m Not Sure”](https://daily.dev/posts/i-built-a-medical-ai-model-that-knows-when-to-say-i-m-not-sure--ylthvv71p) · Medium · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#neural-networks](https://daily.dev/tags/neural-networks) [View this post on daily.dev](https://daily.dev/posts/building-ai-that-learns-and-adapts-a-case-study-in-mri-diagnostics---agata-chudzi-ska-h3ujzviju) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Building AI That Learns and Adapts: A Case Study in MRI Diagnostics - Agata Chudzińska","url":"https://daily.dev/posts/building-ai-that-learns-and-adapts-a-case-study-in-mri-diagnostics---agata-chudzi-ska-h3ujzviju","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/building-ai-that-learns-and-adapts-a-case-study-in-mri-diagnostics---agata-chudzi-ska-h3ujzviju"},"datePublished":"2026-03-03T11:11:55.201Z","dateModified":"2026-03-03T11:12:16.257Z","description":"A conference talk exploring continual learning through a real-world MRI diagnostics case study focused on detecting focal cortical dysplasias (FCDs), a common...","image":"https://i.ytimg.com/vi/gBI-uOq9btU/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/gBI-uOq9btU/sddefault.jpg","isAccessibleForFree":true,"articleSection":"NDC Conferences","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NDC Conferences","logo":"https://media.daily.dev/image/upload/s--SiIyojEj--/f_auto/v1748760369/logos/ndc","url":"https://daily.dev/sources/ndc"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/building-ai-that-learns-and-adapts-a-case-study-in-mri-diagnostics---agata-chudzi-ska-h3ujzviju","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,neural-networks","timeRequired":"PT42M","video":{"@type":"VideoObject","name":"Building AI That Learns and Adapts: A Case Study in MRI Diagnostics - Agata Chudzińska","description":"A conference talk exploring continual learning through a real-world MRI diagnostics case study focused on detecting focal cortical dysplasias (FCDs), a common...","thumbnailUrl":"https://i.ytimg.com/vi/gBI-uOq9btU/sddefault.jpg","uploadDate":"2026-03-03T11:11:55.201Z","duration":"PT42M","url":"https://api.daily.dev/r/H3uJZvIJU","embedUrl":"https://www.youtube.com/embed/gBI-uOq9btU"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NDC Conferences","item":"https://daily.dev/sources/ndc"},{"@type":"ListItem","position":3,"name":"Building AI That Learns and Adapts: A Case Study in MRI Diagnostics - Agata Chudzińska"}]} ```