{"id":303,"date":"2025-09-10T16:03:31","date_gmt":"2025-09-10T16:03:31","guid":{"rendered":"http:\/\/iris-5d.org\/?page_id=303"},"modified":"2026-01-15T15:40:35","modified_gmt":"2026-01-15T15:40:35","slug":"the-platform","status":"publish","type":"page","link":"https:\/\/iris-5d.org\/?page_id=303","title":{"rendered":"The platform"},"content":{"rendered":"\n\n\n<p style=\"font-size:20px\">The platform we are developing is an <strong>AI-driven, fully automated system for high-throughput 5D fluorescence imaging and data analysis<\/strong>. It is designed to overcome the major limitations of current microscopy approaches:<\/p>\n\n\n\n<ul style=\"font-size:20px\" class=\"wp-block-list\">\n<li style=\"font-size:18px\">Low throughput (typically one cell at a time).<\/li>\n\n\n\n<li style=\"font-size:18px\">Heavy user dependence (manual training and oversight required).<\/li>\n\n\n\n<li style=\"font-size:18px\">Insufficient data volume for advanced ML\/AI applications.<\/li>\n<\/ul>\n\n\n\n<p style=\"font-size:20px\">By integrating <strong>cutting-edge optics, robotics, and artificial intelligence<\/strong>, the platform will autonomously acquire, process, and analyse very large datasets of living cells (&gt;10,000 cells\/condition) in <strong>5D (x, y, z, time, and multiple spectral channels)<\/strong> with high spatiotemporal resolution<\/p>\n\n\n\n\n\n<h3 class=\"wp-block-heading\">Core components<\/h3>\n\n\n\n<h4 class=\"wp-block-heading\">1. <strong>Optical Imaging System<\/strong><\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li style=\"font-size:20px\"><strong>Microscope design<\/strong>: A custom single-objective light-sheet system, based on an improved oblique plane microscopy (OPM) concept.<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>Capabilities<\/strong>:\n<ul class=\"wp-block-list\">\n<li style=\"font-size:18px\">Simultaneous multichannel volumetric imaging of large fields of view (300 \u00d7 300 \u00d7 20 \u03bcm\u00b3).<\/li>\n\n\n\n<li style=\"font-size:18px\">Spatial resolution of ~300 nm (xy) and ~800 nm (z), with acquisition speeds of 100\u2013500 ms per cell volume.<\/li>\n\n\n\n<li>Parallel acquisition of \u226560 cells with \u226430 s time resolution.<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>Features under development<\/strong>:\n<ul class=\"wp-block-list\">\n<li style=\"font-size:18px\"><strong>OP-SLIM (Oblique Plane Scattered Light-Sheet Imaging):<\/strong> A novel approach to generate high-contrast volumetric reference images in parallel with fluorescence imaging, useful for ML-based label-free inference.<\/li>\n\n\n\n<li><strong>Structured Illumination Microscopy (SIM):<\/strong> Integrated with OPM to achieve ~150 nm lateral resolution while maintaining throughput.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n\n\n\n<h4 class=\"wp-block-heading\">2. <strong>Automation and Robotics<\/strong><\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li style=\"font-size:20px\"><strong>Automated sample handling<\/strong>:\n<ul class=\"wp-block-list\">\n<li>Robotic arm with gripper for moving multiwell plates (96-well or higher).<\/li>\n\n\n\n<li>Barcode readers for sample tracking.<\/li>\n\n\n\n<li>Automated pipetting and drug application systems.<\/li>\n\n\n\n<li>Temperature-controlled microplate storage (\u201chotels\u201d).<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>Live-cell environment<\/strong>:\n<ul class=\"wp-block-list\">\n<li>Automated stage-top incubator with CO\u2082 and temperature control.<\/li>\n\n\n\n<li>Silicone-oil dispenser for long-term, stable imaging.<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>Continuous operation<\/strong>: 24\/7 autonomous imaging, enabling collection of 4,000\u201310,000 cells per day.<\/li>\n<\/ul>\n\n\n\n<h4 class=\"wp-block-heading\">3. <strong>Software Framework<\/strong><\/h4>\n\n\n\n<ul class=\"wp-block-list\">\n<li style=\"font-size:20px\"><strong>FPGA and Python-based control<\/strong> for all hardware components.<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>User interface<\/strong>:\n<ul class=\"wp-block-list\">\n<li style=\"font-size:18px\">Graphical User Interface (GUI) for experiment setup and data visualization.<\/li>\n\n\n\n<li>Python API for extensibility and integration of custom hardware\/software.<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>AI integration<\/strong>:\n<ul class=\"wp-block-list\">\n<li style=\"font-size:18px\">Automated cell search and selection based on user-defined criteria.<\/li>\n\n\n\n<li style=\"font-size:18px\">Adaptive imaging parameter optimisation (laser power, exposure, sampling strategy).<\/li>\n\n\n\n<li style=\"font-size:18px\">Natural language interface (in development) allowing users to interact with the system using written instructions.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n\n\n\n\n\n<h3 class=\"wp-block-heading\">Data Output and Integration<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li style=\"font-size:20px\"><strong>5D datasets<\/strong>: Large-scale single-cell volumes in multiple fluorescent channels, aligned with reference label-free imaging.<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>Metadata<\/strong>: Complete acquisition parameters, environmental conditions, and experimental annotations.<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>Analysis-ready<\/strong>: Data streamed directly into ML pipelines for segmentation, generative modelling, and population-level statistical analysis.<\/li>\n\n\n\n<li style=\"font-size:20px\"><strong>Throughput<\/strong>: Orders of magnitude higher than current high-resolution microscopy approaches, providing the scale required for AI\/ML-driven biological discovery.<\/li>\n<\/ul>\n\n\n\n\n\n<h3 class=\"wp-block-heading\">Applications<\/h3>\n\n\n","protected":false},"excerpt":{"rendered":"<p>The platform we are developing is an AI-driven, fully automated system for high-throughput 5D fluorescence imaging and data analysis. It is designed to overcome the major limitations of current microscopy approaches: By integrating cutting-edge optics, robotics, and artificial intelligence, the platform will autonomously acquire, process, and analyse very large datasets of living cells (&gt;10,000 cells\/condition) [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"saved_in_kubio":true,"footnotes":""},"class_list":["post-303","page","type-page","status-publish","hentry"],"kubio_ai_page_context":{"short_desc":"","purpose":"general"},"_links":{"self":[{"href":"https:\/\/iris-5d.org\/index.php?rest_route=\/wp\/v2\/pages\/303","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/iris-5d.org\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/iris-5d.org\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/iris-5d.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/iris-5d.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=303"}],"version-history":[{"count":13,"href":"https:\/\/iris-5d.org\/index.php?rest_route=\/wp\/v2\/pages\/303\/revisions"}],"predecessor-version":[{"id":766,"href":"https:\/\/iris-5d.org\/index.php?rest_route=\/wp\/v2\/pages\/303\/revisions\/766"}],"wp:attachment":[{"href":"https:\/\/iris-5d.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=303"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}