{"id":1378,"date":"2022-10-13T15:17:14","date_gmt":"2022-10-13T15:17:14","guid":{"rendered":"https:\/\/www.txd9.com\/?p=1378"},"modified":"2022-10-13T15:17:14","modified_gmt":"2022-10-13T15:17:14","slug":"google-cloud-introduces-new-ai-powered-medical-imaging-suite","status":"publish","type":"post","link":"https:\/\/www.txd9.com\/?p=1378","title":{"rendered":"Google Cloud Introduces New AI-Powered Medical Imaging Suite"},"content":{"rendered":"<p><\/p>\n<div>\n<p>Applying artificial intelligence to medical images can be beneficial to physicians and patients, but developing the tools to do it can be challenging. Google on Tuesday announced it\u2019s ready to meet that challenge with its new Medical Imaging Suite.<\/p>\n<p>\u201cGoogle pioneered the use of AI and computer vision in Google Photos, Google Image Search and Google Lens, and now we\u2019re making our imaging expertise, tools and technologies available for health care and life sciences enterprises,\u201d Alissa Hsu Lynch, global lead of Google Cloud MedTech Strategy and Solutions, said in a statement.<\/p>\n<p>Gartner Vice President and Distinguished Analyst Jeff Cribbs explained that health care providers who are looking for AI for diagnostic imaging solutions have generally been forced into one of two choices.<\/p>\n<p>\u201cThey can procure software from the device manufacturer, the image repository vendor or from a third-party, or they can build their own algorithms with industry agnostic image classification tools,\u201d he told TechNewsWorld.<\/p>\n<p>\u201cWith this release,\u201d he continued, \u201cGoogle is taking their low code AI development tooling and adding substantial health care-specific acceleration.\u201d<\/p>\n<p>\u201cThis Google product provides a platform for AI developers and also facilitates image exchange,\u201d added Ginny Torno, administrative director of innovation and IT clinical, ancillary and research systems at Houston Methodist, in Houston.<\/p>\n<p>\u201cThis is not unique to this market, but may provide interoperability opportunities that a smaller provider is not capable of,\u201d she told TechNewsWorld.<\/p>\n<h3>Robust Components<\/h3>\n<p>According to Google, Medical Imaging Suite addresses some common pain points organizations face when developing AI and machine learning models. Components in the suite include:<\/p>\n<ul style=\"margin-right: 40px;\">\n<li>Cloud Healthcare API, which allows for easy and secure data exchange using an international standard for imaging, DICOMweb. The API provides a fully managed, scalable, enterprise-grade development environment, with automated DICOM de-identification. Imaging technology partners include NetApp for seamless on-prem to cloud data management, and Change Healthcare, a cloud-native enterprise imaging PACS in clinical use by radiologists.<\/li>\n<li style=\"padding: 5px 0px;\">AI-assisted annotation tools from Nvidia and Monai to automate the highly manual and repetitive task of labeling medical images, as well as native integration with any DICOMweb viewer.<\/li>\n<li style=\"padding: 5px 0px;\">Access to BigQuery and Looker to view and search petabytes of imaging data to perform advanced analytics and create training datasets with zero operational overhead.<\/li>\n<li style=\"padding: 5px 0px;\">Use of Vertex AI to accelerate development of AI pipelines to build scalable machine learning models, with 80% fewer lines of code required for custom modeling.<\/li>\n<li>Flexible options for cloud, on-prem, or edge deployment to allow organizations to meet diverse sovereignty, data security, and privacy requirements \u2014 while providing centralized management and policy enforcement with Google Distributed Cloud, enabled by Anthos.<\/li>\n<\/ul>\n<h3>Full Deck of Tech<\/h3>\n<p>\u201cA key differentiator for Medical Imaging Suite is that we\u2019re offering a comprehensive suite of technologies that support the process of delivering AI from beginning to end,\u201d Lynch told TechNewsWorld.<\/p>\n<p>The suite provides everything from imaging data ingestion and storage to AI-assisted annotation tools to flexible model deployment options at the edge or in the cloud, she explained.<\/p>\n<p>\u201cWe are providing solutions that will make this process easier and more efficient for health care organizations,\u201d she said.<\/p>\n<p><center><\/p>\n<p>                    <!--ps: 55 crid: 10556:adsense_tnw_art cc:us s_c:10742,10726,10556 px:0--> <!--\/ps: 55 crid: 10556:adsense_tnw_art cc:us --><\/center><\/p>\n<p>Lynch added that the suite takes an open, standardized approach to medical imaging.<\/p>\n<p>\u201cOur integrated Google Cloud services work with a DICOM-standard approach, allowing customers to seamlessly leverage Vertex AI for machine learning and BigQuery for data discovery and analytics,\u201d she said.<\/p>\n<p>\u201cBy having everything built around this standardized approach, we are making it easier for organizations to manage their data and make it useful.\u201d<\/p>\n<h3>Image Classification Solution<\/h3>\n<p>The growing use of medical imaging, coupled with manpower issues, has made the field ripe for solutions based on artificial intelligence and machine learning.<\/p>\n<p>\u201cAs imaging systems become faster, offer higher resolution and capabilities such as functional MRI, it is tougher for the infrastructure supporting those systems to keep up and ideally, stay ahead of what is needed,\u201d Torno said.<\/p>\n<p>\u201cIn addition, there are shortages in the radiology workforce that complicate the personnel side of the workloads,\u201d she added.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-177175\" src=\"https:\/\/www.technewsworld.com\/wp-content\/uploads\/sites\/3\/2022\/10\/Google-Cloud-Medical-Imaging-Suite.jpg\" alt=\"Google Cloud Medical Imaging Suite\" width=\"1000\" height=\"587\" srcset=\"https:\/\/www.technewsworld.com\/wp-content\/uploads\/sites\/3\/2022\/10\/Google-Cloud-Medical-Imaging-Suite.jpg 1000w, https:\/\/www.technewsworld.com\/wp-content\/uploads\/sites\/3\/2022\/10\/Google-Cloud-Medical-Imaging-Suite-300x176.jpg 300w, https:\/\/www.technewsworld.com\/wp-content\/uploads\/sites\/3\/2022\/10\/Google-Cloud-Medical-Imaging-Suite-768x451.jpg 768w\" sizes=\"auto, (max-width: 1000px) 100vw, 1000px\"\/><\/p>\n<p style=\"color: #222; font-weight: 600; font-size: 13px; line-height: 18px;\">Google Cloud aims to make health care imaging data more accessible, interoperable, and useful with its Medical Imaging Suite (Image Credit: Google)<\/p>\n<hr\/>\n<p>She explained that AI can identify issues found in an image by comparing it to a learned set of images. \u201cIt can recommend a diagnosis that then just needs interpretation and confirmation,\u201d she noted.<\/p>\n<p>\u201cIt can also surface images to the top of a work queue if a potential life-threatening situation is detected in an image,\u201d she continued. \u201cAI can also organize workflows by reading images.\u201d<\/p>\n<p>Machine learning does for medical imaging what it did for facial recognition and image-based search. \u201cRather than identifying a dog, frisbee or chair in a photograph, the AI is identifying tumor boundary, bone fracture or lung lesion in a diagnostic image,\u201d Cribbs explained.<\/p>\n<h3>Tool, Not Substitute<\/h3>\n<p>Michael Arrigo, managing partner at No World Borders, a national network of expert witnesses on health care issues, based in Newport Beach Calif., agreed that AI might help some over-worked radiologists, but only if it\u2019s reliable.<\/p>\n<p>\u201cData must be structured in ways that are usable and consumable by AI,\u201d he told TechNewsWorld. \u201cAI doesn\u2019t work well with highly variable unstructured data in unpredictable formats.\u201d<\/p>\n<p><center><\/p>\n<p>                    <!--ps: 55 crid: 10742:emgnui_tnw_728-1s cc: s_c:10742,10726,10556 px:0--><\/p>\n<div class=\"cls-1665674233\">\n<div class=\"wa-ad-display-wrap wa-ads-55\" style=\"display: inline-block;\" data-adposition=\"55\" data-adname=\"TNW-STORY-1\">\n<p>A D V E R T I S E M E N T<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<p> <!--\/ps: 55 crid: 10742:emgnui_tnw_728-1s cc: --><\/center><\/p>\n<p>Torno added that many studies have been done around AI accuracy and will continue to be done.<\/p>\n<p>\u201cWhile there are examples of AI finding things that a human did not, or being \u2018just as good\u2019 as a human, there are also examples where AI misses something important, or isn\u2019t quite sure what to interpret as there could be multiple issues with the patient,\u201d she observed.<\/p>\n<p>\u201cAI should be seen as an efficiency tool to accelerate image interpretation and aid with emergent cases, but not completely replace the human element,\u201d she said.<\/p>\n<h3>Big Splash Potential<\/h3>\n<p>With its resources, Google can make a significant impact on the medical imaging market. \u201cHaving a major player like Google in this space could facilitate synergies with other Google products already in place at health care organizations, potentially enabling more seamless connectivity to other systems,\u201d Torno noted.<\/p>\n<p>\u201cIf Google concentrates on this market segment, they have the resources to make a splash,\u201d she continued. \u201cThere are many players in this space already. It will be interesting to see how this product can leverage other Google functionality and pipelines and be a differentiator.\u201d<\/p>\n<p>Lynch explained that with the launch of Medical Imaging Suite, Google hopes to help accelerate the development and adoption of AI for imaging by the health care industry.<\/p>\n<p>\u201cAI has the potential to help ease the burden for health care workers and significantly improve and even save people\u2019s lives,\u201d she said.<\/p>\n<p>\u201cBy offering our imaging tools, products and expertise to health care organizations, we believe the market and patients will benefit,\u201d she added.<\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Applying artificial intelligence to medical images can be beneficial to physicians and patients, but developing the tools to do it can be challenging. Google on<\/p>\n","protected":false},"author":1,"featured_media":1379,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[1119,684,47,1121,1118,1120,1122],"class_list":["post-1378","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news","tag-aipowered","tag-cloud","tag-google","tag-imaging","tag-introduces","tag-medical","tag-suite"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.txd9.com\/index.php?rest_route=\/wp\/v2\/posts\/1378","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.txd9.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.txd9.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.txd9.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.txd9.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1378"}],"version-history":[{"count":0,"href":"https:\/\/www.txd9.com\/index.php?rest_route=\/wp\/v2\/posts\/1378\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.txd9.com\/index.php?rest_route=\/wp\/v2\/media\/1379"}],"wp:attachment":[{"href":"https:\/\/www.txd9.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1378"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.txd9.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1378"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.txd9.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1378"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}