AI-enabled imaging and diagnostics previously thought impossible
In partnership with health organizations globally, we’re harnessing the potential of AI to assist clinicians with diagnostics and make specialized expertise more accessible. Our efforts span the full spectrum of AI development - from pioneering research models that push the boundaries of what's possible, to providing open-weight models that empower developers, and offering readily available cloud solutions that are designed to enhance clinical workflows.
-
Google Cloud’s Medical Imaging Suite
90% of healthcare data consists of images, which are large, complex, and dependent on humans to interpret. Google Cloud’s Medical Imaging Suite helps organizations realize the full potential of AI by accelerating imaging diagnostics with interoperability, enabling increased productivity, and helping improve access to better patient care.
Learn more -
Health AI Developer Foundations
Health AI Developer Foundations (HAI-DEF) is a collection of open-weight models and companion resources to help developers building AI models for healthcare. HAI-DEF includes multimodal open-weight models, like MedGemma and TxGemma, instructional notebooks, and demos. Using HAI-DEF resources, developers can choose to build medical imaging applications, relating to medical imaging, medical text comprehension, bioacoustics or therapeutics development.
Learn more
-
Using AI to improve breast cancer detection
With Northwestern Medicine, we’ve researched how AI could potentially help with the detection of breast cancer by reducing the time to diagnosis. We’re also working with Imperial College London and three NHS trusts to explore how AI could alleviate the workload pressure of clinical reviewers.
Learn more -
A promising step forward for predicting lung cancer
Our research, published in Nature Medicine, shows that deep learning may eventually help physicians more accurately screen for lung cancer. To advance this work, we’ve partnered with DeepHealth and Apollo Radiology International to validate our AI systems and bring these models into clinical care.
Learn more -
Exploring AI advancements in radiotherapy planning to improve efficiency
We are collaborating with Mayo Clinic to study the use of AI to help clinicians plan radiotherapy treatment for cancer. We’ve joined forces to research, train and validate an algorithm to assist physicians with segmenting healthy tissue and organs from tumors to reduce treatment planning time and improve the efficiency of radiotherapy, hopefully allowing clinicians to spend less time planning and more time with their patients.
Learn more
-
Advancing AI systems for tuberculosis (TB) screenings
AI can help screen TB from chest x-rays, making screenings more accurate and accessible. That’s why we’ve partnered with Apollo Radiology International and Nexus Intelligence to deploy AI-powered screenings across TB endemic countries. These partnerships include commitments to provide millions of no cost screens to help eradicate TB. Our bioacoustics foundation model, HeAR, can also help researchers build AI models that flag early signs of TB through sound.
Learn more -
Making eyesight-saving screenings more accessible
Diabetic retinopathy (DR) is a leading cause of preventable blindness. Working with partners in India and Thailand, we’ve developed an AI system to help expand DR screenings on a large scale and bring it to millions of patients at no cost.
Learn more -
AI-Assisted Ultrasound for Maternal Health
Ultrasound is a versatile and increasingly more accessible early disease detection tool. That’s why we’re building AI models to expand access to ultrasound, allowing health care providers with limited to no background in ultrasonography collect clinically useful ultrasound scans.
Learn more