Each year, billions of medical images are scanned worldwide as a vital tool in diagnosing patients. About 90 per cent of all healthcare data is imaging-related, and up until now, reading these intricate images has primarily depended on humans. The strain on radiologists and other healthcare professionals entrusted with analysing these images for physicians and patients is also growing as the number of images keep rising. The development of artificial intelligence (AI) for imaging on Google Cloud supports faster and more accurate image diagnosis, enhanced productivity for healthcare professionals, and better patient access and treatment outcomes.
“Google pioneered the use of AI and computer vision in Google Photos, Google Image Search, and Google Lens, and now we’re making our imaging expertise, tools, and technologies available for healthcare and life sciences enterprises. Our Medical Imaging Suite shows what’s possible when tech and healthcare companies come together,” said Alissa Hsu Lynch, Global Lead of Google Cloud’s MedTech Strategy and Solutions.
Google Cloud’s Medical Imaging Suite addresses common challenges that enterprises experience while developing AI and machine learning models, and it does so to enable data interoperability. The Medical Imaging Suite includes the following components:
- Imaging Storage – The Cloud Healthcare API, part of the Medical Imaging Suite, enables simple and secure data transmission utilising the worldwide DICOMweb imaging standard. Cloud Healthcare API offers a fully managed, highly scalable, enterprise-grade development environment incorporating DICOM de-identification. NetApp for seamless on-premises to cloud data management and Change Healthcare, a cloud-native enterprise imaging PACS in clinical usage by radiologists, are two imaging technology partners.
- Imaging Lab – NVIDIA and MONAI AI-assisted annotation technologies help automate the tedious and repetitive work of identifying medical pictures. Google Cloud also provides native connectivity with any DICOMweb viewer.
- Imaging Datasets & Dashboards – BigQuery and Looker enable organisations to see and search petabytes of imaging data to do advanced analytics and produce training datasets with zero operational overhead.
- Imaging AI Pipelines – Vertex AI on Google Cloud can help accelerate the construction of AI pipelines for building scalable machine learning models by using 80 per cent fewer lines of code for custom modelling.
- Imaging Deployment – Finally, the Medical Imaging Suite provides organisations with flexible options for cloud, on-premises, or edge deployment to meet a variety of sovereignty, data security, and privacy requirements—all while providing centralised management and policy enforcement via Google Distributed Cloud, enabled by Anthos.
Earlier detection of prostate cancer
A network of healthcare facilities in New Jersey called Hackensack Meridian Health is starting to use the Medical Imaging Suite to de-identify petabytes of images to develop AI algorithms to predict metastasis in prostate cancer patients. This potentially fatal outcome disproportionately affects Black men in the United States.
“We are working towards building AI capabilities that will support image-based clinical diagnosis across a range of imaging, and be an integral part of our clinical workflow. Google Cloud’s imaging capabilities, including standardized storage and de-identification, are helping us unlock the value of our imaging data so clinicians and researchers are equipped with digitized decision support that fits into their clinical workflow. Google’s Medical Image Suite is also fundamental to us applying AI and machine learning to this data to predict and prevent disease, helping to save more lives,” Hackensack Meridian Health SVP and Chief Data and Analytics Officer Sameer Sethi said.
Improving cervical cancer diagnostics
Global medical technology company Hologic created the first digital cytology platform for labs with a CE certification that combines a novel AI algorithm for detecting cervical cancer with cutting-edge volumetric imaging technology. The platform aids in the detection of cervical cancer cells and precancerous lesions in females. Next, Hologic intends to use the Medical Imaging Suite to increase the platform’s functionality.
“We’ve partnered with Google Cloud to use the Medical Imaging Suite to enhance our current Genius Digital Diagnostics System. By complementing our expertise in diagnostics and Al with Google Cloud’s expertise in AI, deep learning, and its cloud-based technologies for imaging storage, we’re evolving our market-leading technologies to improve laboratory performance, healthcare provider decision-making, and patient care,” said Michael Quick, vice president of Research and Development, Innovation at Hologic.
Medical Imaging suite privacy and security
In every part of the Google Cloud Medical Imaging Suite, privacy and security are of the utmost concern. Customers can safeguard the access to and use of patient data by implementing Google Cloud’s dependable infrastructure and secure data storage that enable HIPAA compliance—along with each customer’s levels of security, privacy controls, and protocols.
To assist healthcare and life sciences enterprises in deploying Medical Imaging Suite at scale, Google Cloud’s ecosystem of delivery partners offers professional implementation of services. CitiusTech, Deloitte, Omnigen, Slalom, and Quantiphi are a few of these collaborators.