En Es

Industry News

New AI Technique Dramatically Improves Quality of Medical Imaging

By Medimaging International staff writers
05 Apr 2018

Image: A new artificial-intelligence-based approach to image reconstruction – called AUTOMAP – yields higher quality images from less data, reducing radiation doses for CT and PET and shortening scan times for MRI. Shown here are MR images reconstructed from the same data with conventional approaches (left) and AUTOMAP (right) (Photo courtesy of Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital).Researchers have developed a new technique based on artificial intelligence (AI) and machine learning that enables radiologists to acquire higher quality images without having to collect additional data at the cost of increased radiation dose for computed tomography (CT) and positron emission tomography (PET) or uncomfortably long scan times for magnetic resonance imaging (MRI).

The technique named AUTOMAP (automated transform by manifold approximation) marks a significant step forward for biomedical imaging. Researchers from the Athinoula A. Martinos Center for Biomedical Imaging at Massachusetts General Hospital (MGH) developed the technique by taking advantage of the various strides made in recent years in the neural network models used for AI and in the graphical processing units (GPUs) that drive the operations. This is because image reconstruction, particularly in the context of AUTOMAP, requires an immense amount of computation, particularly during the training of the algorithms. The availability of large datasets ("big data") required to train large neural network models such as AUTOMAP was another important factor that helped researchers to develop this technique.

In addition to producing high-quality images in less time with MRI or with lower doses with X-ray, CT and PET, AUTOMAP offers several potential benefits for clinical care. For instance, its processing speed can help the technique aid in real-time decision making about imaging protocols while the patient is in the scanner. The technique can also help in advancing other AI and machine learning applications. Since most of the current excitement surrounding machine learning in clinical imaging is focused on computer-aided diagnostics, AUTOMAP could play a role in advancing them for future clinical use as these systems rely on high-quality images for accurate diagnostic evaluations.

"With AUTOMAP, we've taught imaging systems to 'see' the way humans learn to see after birth, not through directly programming the brain but by promoting neural connections to adapt organically through repeated training on real-world examples," said Bo Zhu, PhD, a research fellow in the MGH Martinos Center and first author of the paper published in the journal Nature. "This approach allows our imaging systems to automatically find the best computational strategies to produce clear, accurate images in a wide variety of imaging scenarios."

"Our AI approach is showing remarkable improvements in accuracy and noise reduction and thus can advance a wide range of applications," said senior author Matt Rosen, PhD, director of the Low-field MRI and Hyperpolarized Media Laboratory and co-director of the Center for Machine Learning at the MGH Martinos Center. "We're incredibly excited to have the opportunity to roll this out into the clinical space where AUTOMAP can work together with inexpensive GPU-accelerated computers to improve clinical imaging and outcomes."

E-mail Print
FaceBook Twitter Google+ Linked in

Additional news

24 Apr 2018
Fujifilm Showcases Extended Product Line at ECR 2018
Fujifilm Medical Systems Europe, a provider of diagnostic imaging products and medical informatics solutions, showcased its broad, enhanced line up of products and solutions at the European Congress of Radiology (ECR) 2018. The products and solutions showcased by Fujifilm at ECR 2018 focused on women’s health, healthcare IT, artificial intelligence (AI), digital radiography (DR), computed tomography (CT), computed radiography and ultrasound.
Read More
24 Apr 2018
AI Device for Diabetic Retinopathy Receives FDA Approval
The first-ever medical device to use artificial intelligence (AI) for detecting diabetic retinopathy has received marketing approval from the US Food and Drug Administration (FDA). The AI-based diagnostic system named IDx-DR, which has been developed by privately-held AI diagnostics company IDx, is the first device to be authorized for marketing that provides a screening decision without the need for a clinician to also interpret the image or results. This means that the device can also be used by health care providers who may not normally be involved in eye care.
Read More
24 Apr 2018
AI-Based Platform Designed to Classify Strokes Quickly
An artificial intelligence (AI)-based stroke diagnosis platform designed to assist doctors in quickly classifying the cause of a stroke has completed clinical trials and is expected to provide key information to determine treatment for stroke, leading to faster and more-precise decision-making for patients.
Read More
24 Apr 2018
Breast Density Assessment Software Receives FDA Clearance
The US Food and Drug Administration (FDA) has given 510(k) clearance to a machine learning breast density assessment software that empowers radiologists with standardized, personalized and automated density reports to optimize women’s breast health and follow-up care decisions. The software is now cleared for clinical use in the US, Europe, Canada and Australia, and is the first of several follow-on products to be launched by Densitas Inc., a developer of breast imaging analytics.
Read More
19 Apr 2018
Seegene Unveils Combination Test at ECCMID 2018
Seegene Inc., a developer of multiplex PCR technologies, introduced a combination test at the 28th European Congress of Clinical Microbiology and Infectious Diseases (ECCMID 2018) held in Madrid, Spain, from April 21 to 24, 2018. The combination test is a high-efficiency solution that diagnoses various causes of diseases with multiplex molecular diagnosis assays. Seegene also showcased its molecular diagnostic system SGSTAR (Seegene Sameday Test and Report), which allows order-to-report on the same day and enables the running of the combination test.
Read More
18 Apr 2018
Breast Imaging Market Worth USD 7 Billion by 2024
The global breast imaging market size was estimated at USD 2.9 billion in 2016 and is expected to reach USD 7.3 billion by 2024, driven by the increasing prevalence of breast cancer and other breast-related diseases such as infections, lesions and fibrocysts, as well as supportive government initiatives to increase awareness.
Read More
17 Apr 2018
Veritas Capital Acquires IT Unit of GE Healthcare
Veritas Capital, a private equity investment firm, has entered into a definitive agreement with General Electric, to acquire the Enterprise Financial Management (Revenue-Cycle, Centricity Business), Ambulatory Care Management (Centricity Practice Solution) and Workforce Management (formerly API Healthcare) assets comprising GE Healthcare’s Value-Based Care Division for USD 1.05 billion in cash.
Read More
16 Apr 2018
Interactive VR Assists in Treatment Planning
Interactive virtual reality (VR) shows a patient's unique internal anatomy to interventional radiologists in order to help physicians effectively prepare and tailor their approach to complex treatments, such as splenic artery aneurysm repair. In a new study, researchers compared the VR technology to the use of images from a commonly used visualization software system that displays images on a standard two-dimensional platform and found the accuracy to be similar with both methods, though confidence improved substantially with VR.
Read More
05 Apr 2018
Canon Medical Systems Initiates Collaborative Research On AI in MR Imaging
Canon Medical Systems Corporation, along with Kumamoto University and the University of Bordeaux, has initiated collaborative research on the application of Deep Learning Reconstruction (DLR), an Artificial Intelligence (AI)-based technology in magnetic resonance (MR) imaging.
Read More
Copyright © 2000-2018 TradeMed.com. All rights reserved. | Terms And Conditions