{"id":94783,"date":"2023-09-29T08:30:00","date_gmt":"2023-09-29T06:30:00","guid":{"rendered":"https:\/\/cms.munich-startup.net\/?p=94783"},"modified":"2023-09-28T15:36:07","modified_gmt":"2023-09-28T13:36:07","slug":"ryver-ai-7-questions","status":"publish","type":"post","link":"https:\/\/cms.munich-startup.net\/en\/94783\/ryver-ai-7-questions\/","title":{"rendered":"Ryver.ai: Synthetic data for radiology AI"},"content":{"rendered":"
\n

Munich Startup:<\/em> What does your startup do? What problem do you solve? <\/strong><\/p>\n\n\n\n

Kathrin Khadra, Ryver.ai:<\/em> AI applications supporting radiology often struggle with accuracy and robustness. In the broader context, this means that AI is less effective at detecting diseases in underrepresented patient groups, such as people of color or those with rare diseases.<\/p>\n\n\n\n

This is because access to test and training data is generally very difficult due to data protection and fragmented IT infrastructure. To obtain data, radiology AI providers either negotiate 12-24 month collaborations with hospitals or purchase data from brokers for up to \u20ac200 per image.<\/p>\n\n\n\n

Ryver.ai solves this data bottleneck with AI-generated radiology data (e.g., X-rays, CT scans, MRIs). Our software can be thought of as an art forger. Based on real images, it understands the specific characteristics and can then generate completely new images, so-called synthetic data. These images can then be used to train radiology AI applications in clinical practice. Because the synthetic data can no longer be directly attributed to real patients, it protects privacy.<\/p>\n\n\n\n

Munich Startup:<\/em><\/strong> But that's been around for a long time! <\/strong><\/p>\n\n\n\n

Kathrin Khadra<\/em>:<\/em> That's right. Similar solutions have been used for years in the development of autonomous vehicles. A large portion of the training data is merely simulations of real-world traffic situations.<\/p>\n\n\n\n

Ryver.ai uses the latest findings from generative AI research to achieve a level of quality that makes synthetic data relevant for the healthcare market. <\/p>\n\n\n\n

Solution to urgent problem<\/h2>\n\n\n\n

Munich Startup:<\/em><\/strong> What is your founding story? <\/strong><\/p>\n\n\n\n

Kathrin Khadra<\/em>:<\/em> We met a few years ago through scholarships. I know Jonas from Manage and More Scholarship<\/a> the UnternehmerTUM<\/a> and Simona about the Femtec scholarship.<\/p>\n\n\n\n

In 2020, at the beginning of the lockdown, we jointly founded a voucher platform for small local shops in Munich to provide them with a revenue stream while they were forced to close. It all went well, but we quickly realized it wasn't something we wanted to work on for the next 10 years. So we handed it over to Regional Hero, who had built a very similar concept in Berlin and are still pursuing it.<\/p>\n\n\n\n

We then sat down together and started considering which problem out there urgently needed a solution. We quickly became convinced that the large amount of data required for AI development and the high relevance of data protection represented a growing challenge. We tested several solutions for different industries, and one survived: synthetic data for radiology AI.<\/p>\n\n\n\n

Munich Startup:<\/em><\/strong> What have been your biggest challenges so far?<\/strong> <\/p>\n\n\n\n

Kathrin Khadra<\/em>:<\/em> Of course, the development of the technology is very complex. Generating synthetic data of a quality that allows it to be used in a medical context poses many challenges.<\/p>\n\n\n\n

Introducing this technology, especially in a very risk-averse market, is at least as difficult. We had to invest a lot of effort to gain the trust of potential customers.<\/p>\n\n\n\n

Munich Startup:<\/em><\/strong> Where would you like to be in one year, where in five years?<\/strong><\/p>\n\n\n\n

Kathrin Khadra<\/em>:<\/em> We aim to launch the first product for lung CT with tumor indications by next year, following the initial pilot studies. After that, we will further expand our generative models. This means adding new body parts such as the head and abdomen, as well as additional imaging modalities such as MRI.<\/p>\n\n\n\n

In about five years, our solutions will then be able to address data for a very broad spectrum of use cases in clinical AI but also in the pharmaceutical industry.<\/p>\n\n\n\n

\u201cDriving force in the background\u201d<\/h2>\n\n\n\n

Munich Startup:<\/em><\/strong> How have you experienced Munich as a startup location so far? <\/strong><\/p>\n\n\n\n

Kathrin Khadra<\/em>:<\/em> Jonas and I have been part of the UnternehmerTUM ecosystem practically since day one. We started with the Manage and More grant, refined our idea in the Xplore program, and recently completed our funding round with the support of Xpreneurs.<\/p>\n\n\n\n

We have also received continuous support from the TUM Venture Labs<\/a>Antoine Leboyer, our mentor, for example, provided the crucial contact to our first investor.<\/p>\n\n\n\n

The environment of fellow founders who all face similar challenges is incredibly valuable and always helps us when we have to make difficult decisions.<\/p>\n\n\n\n

Munich Startup:<\/em><\/strong> Hidden champion or shooting star?<\/strong> <\/p>\n\n\n\n

Kathrin Khadra<\/em>:<\/em> First and foremost, we want to solve a serious and major problem: safe medical AI for every patient. If that requires us to shine a spotlight on it, then we're happy to be the shooting star; otherwise, we're simply the driving force behind the scenes.<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

Ryver.ai aims to use generative artificial intelligence (AI) to generate diverse test and training data, thus solving the data bottleneck in radiology. Co-founder Kathrin Khadra explains in an interview how the company, founded in 2021 by Simona Santamaria, Kathrin Khadra, and Jonas Ils, intends to implement this project.<\/p>","protected":false},"author":24,"featured_media":94784,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[5634,5638,4074,1083],"tags":[2258,243,4980],"acf":[],"yoast_head":"\nRyver.ai: Synthetische Daten f\u00fcr Radiologie-KI - Munich Startup<\/title>\n<meta name=\"description\" content=\"Ryver.ai m\u00f6chte mit generativer KI diverse Test- und Trainingsdaten generieren und so den Datenengpass in der Radiologie l\u00f6sen.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/cms.munich-startup.net\/en\/94783\/ryver-ai-7-questions\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Ryver.ai: Synthetische Daten f\u00fcr Radiologie-KI - Munich Startup\" \/>\n<meta property=\"og:description\" content=\"Ryver.ai m\u00f6chte mit generativer KI diverse Test- und Trainingsdaten generieren und so den Datenengpass in der Radiologie l\u00f6sen.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/cms.munich-startup.net\/en\/94783\/ryver-ai-7-questions\/\" \/>\n<meta property=\"og:site_name\" content=\"Munich Startup\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/munichstartup\/\" \/>\n<meta property=\"article:published_time\" content=\"2023-09-29T06:30:00+00:00\" \/>\n<meta name=\"author\" content=\"Regina Bruckschl\u00f6gl\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@munich_startup\" \/>\n<meta name=\"twitter:site\" content=\"@munich_startup\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Regina Bruckschl\u00f6gl\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/\",\"url\":\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/\",\"name\":\"Ryver.ai: Synthetische Daten f\u00fcr Radiologie-KI - Munich Startup\",\"isPartOf\":{\"@id\":\"https:\/\/cms.munich-startup.net\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/cms.munich-startup.net\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg\",\"datePublished\":\"2023-09-29T06:30:00+00:00\",\"author\":{\"@id\":\"https:\/\/cms.munich-startup.net\/#\/schema\/person\/4733256eff8ed883081bf4d616fa784f\"},\"description\":\"Ryver.ai m\u00f6chte mit generativer KI diverse Test- und Trainingsdaten generieren und so den Datenengpass in der Radiologie l\u00f6sen.\",\"breadcrumb\":{\"@id\":\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#primaryimage\",\"url\":\"https:\/\/cms.munich-startup.net\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg\",\"contentUrl\":\"https:\/\/cms.munich-startup.net\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg\",\"width\":2400,\"height\":1800,\"caption\":\"Das Gr\u00fcnderteam von Ryver.ai\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/cms.munich-startup.net\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Ryver.ai: Synthetische Daten f\u00fcr Radiologie-KI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/cms.munich-startup.net\/#website\",\"url\":\"https:\/\/cms.munich-startup.net\/\",\"name\":\"Munich Startup\",\"description\":\"Das offizielle Startup-Portal f\u00fcr M\u00fcnchen\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/cms.munich-startup.net\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/cms.munich-startup.net\/#\/schema\/person\/4733256eff8ed883081bf4d616fa784f\",\"name\":\"Regina Bruckschl\u00f6gl\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/cms.munich-startup.net\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/b783cd1e1497db1e22684a06f3369381?s=96&d=blank&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/b783cd1e1497db1e22684a06f3369381?s=96&d=blank&r=g\",\"caption\":\"Regina Bruckschl\u00f6gl\"},\"description\":\"Nach eigenen Startup-Erfahrungen blickt sie als Redakteurin von Munich Startup nun aus einer anderen Perspektive auf die M\u00fcnchner Startup-Szene \u2013 und entdeckt dabei jeden Tag, wie vielf\u00e4ltig das M\u00fcnchner \u00d6kosystem ist. Startup Stories, die erz\u00e4hlt werden wollen!\",\"sameAs\":[\"https:\/\/cms.munich-startup.net\"],\"url\":\"https:\/\/cms.munich-startup.net\/en\/author\/regina\/\"}]}<\/script>\n<meta property=\"og:image\" content=\"https:\/\/cms.munich-startup.net\/en\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2400\" \/>\n\t<meta property=\"og:image:height\" content=\"1800\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Ryver.ai: Synthetic data for radiology AI - Munich Startup","description":"Ryver.ai aims to use generative AI to generate diverse test and training data and thus solve the data bottleneck in radiology.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/cms.munich-startup.net\/en\/94783\/ryver-ai-7-questions\/","og_locale":"en_US","og_type":"article","og_title":"Ryver.ai: Synthetische Daten f\u00fcr Radiologie-KI - Munich Startup","og_description":"Ryver.ai m\u00f6chte mit generativer KI diverse Test- und Trainingsdaten generieren und so den Datenengpass in der Radiologie l\u00f6sen.","og_url":"https:\/\/cms.munich-startup.net\/en\/94783\/ryver-ai-7-questions\/","og_site_name":"Munich Startup","article_publisher":"https:\/\/www.facebook.com\/munichstartup\/","article_published_time":"2023-09-29T06:30:00+00:00","author":"Regina Bruckschl\u00f6gl","twitter_card":"summary_large_image","twitter_creator":"@munich_startup","twitter_site":"@munich_startup","twitter_misc":{"Written by":"Regina Bruckschl\u00f6gl","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/","url":"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/","name":"Ryver.ai: Synthetic data for radiology AI - Munich Startup","isPartOf":{"@id":"https:\/\/cms.munich-startup.net\/#website"},"primaryImageOfPage":{"@id":"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#primaryimage"},"image":{"@id":"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#primaryimage"},"thumbnailUrl":"https:\/\/cms.munich-startup.net\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg","datePublished":"2023-09-29T06:30:00+00:00","author":{"@id":"https:\/\/cms.munich-startup.net\/#\/schema\/person\/4733256eff8ed883081bf4d616fa784f"},"description":"Ryver.ai aims to use generative AI to generate diverse test and training data and thus solve the data bottleneck in radiology.","breadcrumb":{"@id":"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#primaryimage","url":"https:\/\/cms.munich-startup.net\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg","contentUrl":"https:\/\/cms.munich-startup.net\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg","width":2400,"height":1800,"caption":"Das Gr\u00fcnderteam von Ryver.ai"},{"@type":"BreadcrumbList","@id":"https:\/\/cms.munich-startup.net\/94783\/ryver-ai-7-fragen\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/cms.munich-startup.net\/"},{"@type":"ListItem","position":2,"name":"Ryver.ai: Synthetische Daten f\u00fcr Radiologie-KI"}]},{"@type":"WebSite","@id":"https:\/\/cms.munich-startup.net\/#website","url":"https:\/\/cms.munich-startup.net\/","name":"Munich Startup","description":"The official startup portal for Munich","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/cms.munich-startup.net\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/cms.munich-startup.net\/#\/schema\/person\/4733256eff8ed883081bf4d616fa784f","name":"Regina Bruckschl\u00f6gl","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/cms.munich-startup.net\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/b783cd1e1497db1e22684a06f3369381?s=96&d=blank&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/b783cd1e1497db1e22684a06f3369381?s=96&d=blank&r=g","caption":"Regina Bruckschl\u00f6gl"},"description":"After her own startup experiences, she now looks at the Munich startup scene from a different perspective as an editor at Munich Startup \u2013 and discovers every day how diverse the Munich ecosystem is. Startup stories that beg to be told!","sameAs":["https:\/\/cms.munich-startup.net"],"url":"https:\/\/cms.munich-startup.net\/en\/author\/regina\/"}]},"og_image":[{"width":2400,"height":1800,"url":"https:\/\/cms.munich-startup.net\/wp-content\/uploads\/2023\/09\/Ryver.ai_.jpg","type":"image\/jpeg"}]},"_showyear":"","_inactive":"","_show_financing":"","_hide_on_map":"","_edit_lock":"1697446915:25","_edit_last":"42","_yoast_wpseo_focuskw":"Ryver","_yoast_wpseo_metadesc":"Ryver.ai m\u00f6chte mit generativer KI diverse Test- und Trainingsdaten generieren und so den Datenengpass in der Radiologie l\u00f6sen.","_yoast_wpseo_linkdex":"71","_thumbnail_id":"94784","wbounce_status":"default","_yoast_wpseo_primary_category":"5634","_yoast_wpseo_focuskw_text_input":"","_yoast_wpseo_content_score":"30","ms_image_format":"contentwidth","_ms_image_format":"field_5cb8587572c8b","ms_dachzeile":"","_ms_dachzeile":"field_5cd9b7f365df5","ms_bump_post_date":"","_ms_bump_post_date":"field_5d1341edcf42a","guest_author_name":"","_guest_author_name":"field_5cee78a6016f9","guest_author_image":"","_guest_author_image":"field_5cee7914016fb","guest_author_description":"","_guest_author_description":"field_5cee78dd016fa","ms_post_image_caption":"","_ms_post_image_caption":"field_5f735b0735284","ms_post_image_credit":"","_ms_post_image_credit":"field_5f735b1435285","suppress_startupbox":"0","_suppress_startupbox":"field_60a64b0b6efc6","_yoast_wpseo_estimated-reading-time-minutes":"4","_wp_old_date":"","_yoast_wpseo_title":"","_yoast_wpseo_wordproof_timestamp":"","footnotes":"","easy_language_simplification_original_id":"","easy_language_source_language":"","easy_language_simplification_language":"","easy_language_api":"","easy_language_prevent_automatic_mode":"","_wp_old_slug":"","_wp_trash_meta_status":"","_wp_trash_meta_time":"","easy_language_simplification_state_changed_from":"","easy_language_de_EL_changed":"","ms_competition_deadline":"","_ms_competition_deadline":"","_wpbitly":"","enclosure":"","_yoast_wpseo_meta-robots-noindex":"","_yoast_wpseo_meta-robots-nofollow":"","wbounce_template":"","wbounce_title":"","wbounce_text":"","wbounce_cta":"","wbounce_url":"","wbounce_override":"","_yoast_wpseo_opengraph-title":"","_yoast_wpseo_opengraph-description":"","_oembed_7131efca3705e16bd9da2c41df237660":"","_oembed_time_7131efca3705e16bd9da2c41df237660":"","_pprredirect_type":"","_pprredirect_url":"","_yoast_wpseo_opengraph-image":"","_yoast_wpseo_opengraph-image-id":"","_newsletterglue":"","easy_language_text_language":"","_wp_desired_post_slug":"","_relevanssi_noindex_reason":"","_links":{"self":[{"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/posts\/94783"}],"collection":[{"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/users\/24"}],"replies":[{"embeddable":true,"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/comments?post=94783"}],"version-history":[{"count":3,"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/posts\/94783\/revisions"}],"predecessor-version":[{"id":94862,"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/posts\/94783\/revisions\/94862"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/media\/94784"}],"wp:attachment":[{"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/media?parent=94783"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/categories?post=94783"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cms.munich-startup.net\/en\/wp-json\/wp\/v2\/tags?post=94783"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}