Stanford University, VinBrain to Develop AI-Enabled Diagnostic and Treatment Platform

Stanford University and VinBrain signed a data use agreement (DUA) to improve the precision of radiology interpretation using a multi-modal “RadGraph” method.
 
The DUA grants Stanford University and VinBrain the collaborative power to improve efficiency in radiology reports and advance AI in healthcare by sharing relevant de-identified data for model training and testing while tackling complexity, ambiguity, and limitations in medical image interpretation. 

Starting with 240,000 anonymized medical images and report pairs provided by Stanford through this DUA, VinBrain will work to improve the accuracy of the RadGraph method through a research collaboration with Stanford to extract clinical entities and relation annotations from a large dataset of full-text radiology reports. VinBrain is attempting to raise the bar for research on AI solutions by collaborating beyond Vietnam to improve product quality while continuing to add and develop the most massive data source in Vietnam to date, with more than 2.3 million images being analyzed through the DrAid platform so far. 

RadGraph is a method introduced by Prof. Pranav Rajpurkar (Harvard University) and Prof. Curtis Langlotz at Stanford. This collaboration works between Stanford University and VinBrain to address complexity, ambiguity, and limitations for interpreting medical images. 

DrAid is a platform of comprehensive artificial intelligence (AI) doctor-assistant software developed by VinBrain to assist medical teams and doctors in diagnosing heart, lung, liver, and bone diseases based on digital medical images. The platform is evaluated to have superior efficiency compared to traditional methods in observing and analyzing medical images, helping in reducing overload and improving early detection in diagnosis. 

“VinBrain always strictly adheres to data security regulations according to U.S. standards,” VinBrain Founder/CEO Steven Truong said. He also emphasized DUA demonstrates Stanford’s trust in VinBrain’s commitment to data privacy and security.

The DUA is the result of more than three years of collaboration that has beget many research projects. 

“I remember the first time I met Steven at RSNA Spotlight organized by Stanford near San Francisco Airport. It was the beginning of this wonderful relationship that developed over time,” said Professor Curtis Langlotz, director of the Center for Artificial Intelligence in Medicine at Stanford University. “We appreciate VinBrain’s leadership in research and the capabilities that they have. The speed of work is incredible, and I also appreciate the collaborative spirit of VinBrain. I know that we’ve done a lot, but there’s still a lot more to do. I look forward to continued collaborations. I’m glad we sat down together to sign this agreement.” 

The agreement promises to comprehensively expand cooperation in the next areas of development, strengthen VinBrain’s relationship with the university, and enable VinBrain to further research AI-developed solutions. 

DrAid Radiology V1 is an AI-enabled triage and notification software designed to aid the clinical assessment of adult chest X-ray cases with features suggestive of pneumothorax. This software has been granted 510(k) clearance byu the U.S. Food and Drug Administration.  

DrAid Appliance is an AI-enabled system to classify an adult chest X-ray between normal and nearly 60 abnormal findings with higher-than-average quality standards of primary care physicians.

VinBrain is an AI healthcare products company funded by Vingroup, the largest conglomerate by market capitalization in Vietnam.