The easiest way for researchers to activate their AI algorithms for clinical use.

Start to train, validate, and distribute in the Bunkerhill Consortium for free.

Get in Touch
Hero

Meet the Bunkerhill Consortium

A powerhouse of leading research institutions that train, validate, and distribute
AI algorithms together according to a shared set of rules

Stanford
UCSF
ucsf
DASA
Medstar
Medstar
Dasa
Stanford
Rochester
University of
Kentucky
University of
Rochester
UK
University of
Colorado
Children’s Hospital Colorado
Children
University of
Virginia

See our previous work

Automated AI coronary artery calcium scoring is live on all UCSF non-contrast chest CTs

By John Mongan, MD, PhD
Published:
October 20, 2021

An artificial intelligence (AI) algorithm using deep learning can enable clinicians to estimate the CAC score on routine non-contrast chest CT, potentially allowing opportunistic early preventive interventions. A multi-center team (including UCSF) took part in a study and developed a fully automatic, end-to-end deep learning model for automated CAC scoring using routine non-gated unenhanced chest CT exams. The model was trained using traditional CAC scores based on gated CT as ground truth; the trained model was evaluated on multiple external datasets. Investigators released labeled datasets of gated and non-gated scans with annotations to potentially help fuel further efforts in this domain by other investigators. The result was good news.

Read the Press

AI aids assessment of skeletal age on radiographs

By Erik L. Ridley, AuntMinnie.com staff writer
Published:
September 30, 2021

Radiologists can assess skeletal age on hand radiographs faster and more accurately with assistance from an artificial intelligence (AI) algorithm, according to a prospective analysis published online September 28 in Radiology. A group of researchers led by David Eng of Stanford University trained a deep-learning algorithm and then conducted a prospective and randomized multicenter controlled trial to evaluate its performance across six different sites. Although results varied among the centers, AI yielded an overall improvement in speed and accuracy.

Read the Press
Read the Manuscript

Automated coronary calcium scoring using deep learning with multicenter external validation

Abstract:
Published:
June 01, 2021

Coronary artery disease (CAD), the most common manifestation of cardiovascular disease, remains the most common cause of mortality in the United States. Risk assessment is key for primary prevention of coronary events and coronary artery calcium (CAC) scoring using computed tomography (CT) is one such non-invasive tool. Despite the proven clinical value of CAC, the current clinical practice implementation for CAC has limitations such as the lack of insurance coverage for the test, need for capital-intensive CT machines, specialized imaging protocols, and accredited 3D imaging labs for analysis (including personnel and software).

Read the Manuscript
Read the Press

Testimonials

Our AI algorithim can help determine which patients are at risk and improve treatment accuracy.

“Neque ac, nunc gravida lacus massa purus, cursus sed sed at tincidunt ut cras at integer commodo, sagittis justo condimentum tortor ipsum mi massa dui auctor tristique commodo fringilla auctor egestas viverra in aliquam scelerisque tempor cursus enim maecenas libero vitae aliquam tortor ultricies mi lorem quis tortor fermentum semper nisl lorem et, metus, nullam et consectetur nibh aliquetaliquet tortor.

John Doe, Head Researcher

Train, validate, and distribute AI algorithms together, using a unified software platform.

See your AI algorithm's predictions in multi-institutional collaborations. Understand its behavior in retrospective and prospective settings.
See your AI algorithm's predictions in multi-institutional collaborations. Understand its behavior in retrospective and prospective settings.