Google launches suite of digital tools around medical images

This audio is automatically generated. Please let us know if you have any feedback.

Google is rolling out a suite of tools designed to make medical images more interoperable and help organizations build artificial intelligence and machine learning models around them.

According to a Cornell University study, billions of medical images are scanned each year, and image data accounts for 90% of all healthcare data.

The images were at the center of efforts to use the technology to improve the quality of care, with hopes that AI can gain insights and come to diagnoses faster and more accurately than human clinicians, while reducing the workload of radiologists.

Google’s new Medical Imaging Suite includes cloud-based file storage with secure data sharing capabilities, automated image labeling through AI-assisted annotation, and tools to create training datasets for algorithms, accelerating the development of scalable machine learning models with less code Tech giant.

Some Google Cloud customers have already started using the suite of digital tools, including Hackensack Meridian Health in New Jersey, which uses them to anonymize images to develop AI algorithms capable of detecting metastases in patients with predict prostate cancer.

In addition, medical technology company Hologic is using the tools to expand the capabilities of its digital cytology platform for laboratories, which helps cytologists and pathologists identify precancerous lesions and cervical cancer cells in patients, Google said in a press release about the product.

Funding for AI in healthcare has exploded in recent years given its potential to transform healthcare delivery in the US, although potential benefits have largely yet to materialize. The technology faces barriers to deployment, including clinician approval, regulatory uncertainties, and concerns about health equity and bias.

READ :  Pfizer amplifies AI/ML to deliver transformative medicines to patients

Radiology is a promising area for AI, as proponents of the technology argue that AI systems can analyze data that is invisible to the human eye, making it a valuable diagnostic tool.

A number of healthcare organizations are implementing AI to create, analyze and interpret medical images, including New York University Langone Health, which worked with Facebook’s AI team to develop an algorithm that would enable a MRI takes just 15 minutes instead of an hour, and also developed a tool to predict the likelihood of breast cancer in MRI scans, capable of reducing unnecessary biopsies by up to 20%.