News | Artificial Intelligence | May 20, 2021

Carestream Accelerates Development and Delivery of AI Applications for Medical Imaging

Carestream selects HPE GreenLake Cloud Services to power transformative artificial intelligence-as-a-service (AIaas)

Carestream selects HPE GreenLake Cloud Services to power transformative artificial intelligence-as-a-service (AIaas)

May 20, 2021 — Carestream Health is transforming and accelerating the way it develops and delivers AI applications for medical imaging that help improve patient care. The state-of-the-art initiative is based on Hewlett Packard Enterprise’s (HPE) GreenLake for Machine Learning Operations (ML Ops). The machine-learning-optimized cloud service infrastructure makes it easier and faster to get started with ML/AI projects, and seamlessly scale them to production deployments.

“Carestream has been a leader in leveraging powerful AI technology to help improve image quality, optimize dose and increase workflow efficiency in medical imaging,” said Dharmendu Damany, Chief Technology Officer at Carestream. “Now we are accelerating the pace of our development by providing our industry-leading medical imaging scientists with the optimal AI platform/framework for their research. Our partnership with HPE and their industry leadership with HPE GreenLake Cloud Services gives us the framework to support the operationalization of AI to deliver more solutions that can help improve diagnosis and patient care.”

HPE GreenLake cloud services provide customers with a powerful foundation to drive digital transformation through an elastic as-a-service platform that can run on premises, at the edge or in a colocation facility. HPE GreenLake for ML Ops, one of a suite of cloud services offered by HPE, enables customers to deploy AI/ML workloads on HPE's ML-optimized cloud services infrastructure. This HPE cloud service, powered by HPE Ezmeral and HPE Pointnext AI Services, is designed to address all aspects of the ML lifecycle from data preparation to model building, training, deployment, monitoring and collaboration.

Carestream’s partnership with HPE paves the way for time-consuming local software updates to eventually be replaced by cloud hardware and service upgrades, enabling imaging facilities to evolve their medical imaging capabilities more quickly. When it becomes available in the future, artificial intelligence-as-a-service also has the potential to reduce the cost-of-entry to new features; and reduce solution costs. Carestream’s collaboration with HPE will impact medical imaging technology on a global scale, as Carestream’s X-ray platforms are in use across 140 countries, spanning over 100,000 pieces of equipment and 35 different hardware configurations.

“Delivering AI services and software updates through the cloud will allow medical imaging facilities and their patients to benefit from enhancements more quickly. In the future, they can seamlessly deploy them where their data resides and where they care for patients—whether it is at the micro edge, edge or cloud,” said Mr. Damany.

“Our partnership with Carestream, one of the worldwide leaders in the critical medical imaging space, closely aligns with HPE’s vision for innovation from edge-to-cloud, and provides cloud services to achieve outcome-driven digital transformations,” said Keith White, Senior Vice President and General Manager, HPE GreenLake Cloud Services. “It’s been so exciting working with Carestream to develop a scalable, next generation AI as a service platform that enables their continued leadership in helping to improve patient outcomes and provide impactful insights to their customers.”

The HPE servers include graphic processing units (GPUs) developed by NVIDIA, a key AI hardware partner in the project, enabling each server to tackle multiple imaging and analysis tasks simultaneously. HPE and NVIDIA technology also will facilitate federated learning—the aggregation of anonymized machine learning data across multiple provider facilities. Federated learning is expected to revolutionize healthcare research and development over the next decade, enabling researchers to increase diagnostic intelligence and automation without compromising patient privacy.

For more information: www.carestream.com

Related Content

Researchers have developed an artificial intelligence (AI)-based brain age prediction model to quantify deviations from a healthy brain-aging trajectory in patients with mild cognitive impairment, according to a study published in Radiology: Artificial Intelligence. The model has the potential to aid in early detection of cognitive impairment at an individual level.

Flowchart showing the framework of the brain age prediction model. A, The imaging data were split into training and test datasets. The training dataset consisted of structural magnetic resonance imaging data from 974 healthy individuals, whereas the test dataset included data from 2 groups, 231 healthy controls and 224 aMCI subjects. B, A Conventional Statistical Parametric Mapping structural preprocessing pipeline was used to generate GMV maps in the MNI space. C, The intensity values from the GMV maps were extracted and concatenated to create a feature matrix that was then cleaned and normalized. D, The best elastic net model was obtained by performing supervised learning on the training dataset. To optimize the hyperparameters, a grid search was performed. E, The test dataset was input into the trained model. An age was predicted for every participant included in the test dataset. The PAD scores were calculated by subtracting the participant's chronological age from his or her predicted age. aMCI = amnestic mild cognitive impairment, GMV = gray matter volume, MNI = Montreal Neurologic Institute, Dartel = Diffeomorphic Anatomic Registrations Through Exponentiated Lie Algebra, PAD = predicted age difference. Chart courtesy of Radiological Society of North America

News | Artificial Intelligence | June 23, 2021
June 23, 2021 — Researchers have developed an...
An example of a COVID-19 pneumonia of a chest CT scan. The COVID appears as white ground glass opacities (GGOs) in the lungs. Normal lungs on CT should appear black.

An example of a COVID-19 pneumonia of a chest CT scan. The COVID appears as white ground glass opacities (GGOs) in the lungs. Normal lungs on CT should appear black.

News | Coronavirus (COVID-19) | June 23, 2021
June 23, 2021 — The Radiological Society of North America (...
Led by a Michigan Medicine physician, the research team examined treatment outcomes over two years for patients who fractured their distal radius, the larger of two bones in the forearm. They found no one-size-fits all method for treating the fracture, which more than 85,000 Medicare beneficiaries sustain annually.

Getty Images

News | Radiology Imaging | June 23, 2021
June 23, 2021 — A decade-long...
According to a new study, by the Harvey L. Neiman Health Policy Institute and the American College of Radiology’s National Mammography Database Committee, the most influential radiologist characteristics impacting mammography interpretive performance were geography, breast sub-specialization, performance of diagnostic mammography, and performance of diagnostic ultrasound.

Getty Images

News | Breast Imaging | June 23, 2021
June 23, 2021 — According to a new ...
A phase III clinical trial has validated the effectiveness of the prostate-specific membrane antigen (PSMA)-targeted radiotracer 18F-DCFPyL in detecting and localizing recurrent prostate cancer.

Figure 1. Case example: A 54-year-old man with a history of RP+LND and a subsequent PSA of 1.25 ng/mL had no evidence of disease by baseline imaging. Piflufolastat F 18 (18F-DCFPyL)- PET/CT accurately detected biochemically recurrent prostate cancer with the PSMA PET/CT scan identifying positive left (left panel) and right peri-rectal lymph nodes (right panel).

News | Prostate Cancer | June 21, 2021
June 21, 2021 — A phase III clinica...
The Persona RF PREMIUM is an innovative radiography and fluoroscopy system designed for hospitals and medical centers of all sizes, providing real-time imaging for skeletal, digestive, urinary, respiratory, reproductive systems; and specific organs including the heart, lung and kidneys.
News | Digital Radiography (DR) | June 21, 2021
June 21, 2021 — FUJIFILM Medical Systems U.S.A., Inc., a leading provider of diagnostic imaging and medical informati
The impact of deploying artificial intelligence (AI) for radiation cancer therapy in a real-world clinical setting has been tested by Princess Margaret researchers in a unique study involving physicians and their patients.

Getty Images

News | Artificial Intelligence | June 15, 2021
June 15, 2021 — The impact of deploying ...
A cardiac MRI of athletes who had COVID-19 is seven times more effective in detecting inflammation of the heart than symptom-based testing, according to a study led by researchers at The Ohio State University Wexner Medical Center and College of Medicine with 12 other Big Ten programs.

Cardiac Magnetic Resonance Imaging in Athletes With Clinical and Subclinical Myocarditis A-D, Athlete A with subclinical possible myocarditis was asymptomatic with normal electrocardiogram (ECG), echocardiogram, and high-sensitivity troponin findings. A, T2 mapping showing elevated T2 in basal-mid inferolateral wall in short axis view. B, late gadolinium enhancement (LGE) in the basal inferolateral wall in short axis view. C, Postcontrast steady state-free precession (SSFP) images showing contrast uptake in the basal-mid inferolateral wall in short axis view. D, LGE in the inferolateral wall in 3-chamber view. E-H, Athlete B with subclinical probable myocarditis was asymptomatic with normal ECG, normal echocardiogram, and elevated high-sensitivity troponin findings. E, T2 mapping showing elevated T2 in the anteroseptal wall in short axis view. F, LGE in the anteroseptal wall in 3-chamber view. G, T2 mapping showing elevated T2 in the anteroseptal wall in 3-chamber view. F, Postcontrast SSFP image showing pericardial effusion in short axis view. I-K, Athlete C with clinical myocarditis and chest pain, dyspnea, abnormal ECG, normal echocardiogram, and normal troponin findings. I, T2 mapping showing elevated T2 in the lateral wall short axis view. J, Postcontrast SSFP images showing contrast uptake in midlateral wall in short axis view. K, LGE in the epicardial midlateral wall in short axis view. L-N, Athlete D with clinical myocarditis, chest pain, abnormal ECG, echocardiogram, and troponin findings. L, T1 mapping showing elevated native T1 in midlateral wall in short axis view. M, T2 mapping showing elevated T2 in the midlateral wall in short axis view. N, LGE in the epicardial midlateral wall in short axis view. IR indicates inferior right view; IRP, inferior, right, posterior view; PLI, posterior, left, inferior view; SL, superior left view; SLA, superior, left, anterior view. Image courtesy of JAMA Cardiol. Published online May 27, 2021. doi:10.1001/jamacardio.2021.2065

News | Cardiac Imaging | June 15, 2021
June 15, 2021 — A...