En Es
Categories

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

15 Oct 2018
AI Algorithm Uses Key Signatures to Predict Onset of AD
A team of researchers has designed an artificial intelligence (AI) algorithm that learns signatures from magnetic resonance imaging (MRI), genetics, and clinical data to accurately predict cognitive decline leading to Alzheimer’s disease. The algorithm can help predict whether an individual’s cognitive faculties are likely to deteriorate towards Alzheimer’s in the next five years.
Read More
15 Oct 2018
Breast Cancer Screening Machine Learning Software Receives CE Mark
A new deep learning-based breast cancer screening software has received the CE mark and will be launched within the UK’s National Health Service (NHS) and European healthcare systems. The software has been developed by Kheiron Medical Technologies, a start-up that combines novel deep learning methods, data science, and radiology expertise to enable diagnostics designed to detect cancers and improve patient outcomes.
Read More
15 Oct 2018
GE Healthcare to Implement First AI-Powered Hospital Command Centers
GE Healthcare is collaborating with hospital service providers in Europe and the US for implementing an artificial intelligence (AI)-powered command center to effectively and efficiently synchronize all elements of a patient's hospital experience. The AI-powered system will support caregivers to enhance patient safety, orchestrate seamless care delivery and get patients back home sooner.
Read More
11 Oct 2018
Scientists Use Machine Learning and MRI Scans to Predict Learning Difficulties
A team of scientists from the Medical Research Council (MRC) Cognition and Brain Sciences Unit at the University of Cambridge used machine learning - a type of artificial intelligence - with data from hundreds of children who struggle at school to identify clusters of learning difficulties, which did not match their previous diagnosis. According to the researchers, this reinforces the need for children to receive detailed assessments of their cognitive skills to identify the best type of support.
Read More
10 Oct 2018
Utilization of X-Ray Mammography Systems Expected to Increase
Over the last 20 years, hospitals and imaging centers in the developed economies have adopted X-ray mammography systems for the screening and diagnosis of breast cancer. This has resulted in a significant reduction in mortality and encouraged emerging countries to make investments in population-base, organized screening. These significant investments in mammography technology have paved the way for radiation safety, patient comfort and 3D imaging that enables precise tumor detection.
Read More
09 Oct 2018
Compact Devices Emerge As Segment of Ultrasound Market
The global ultrasound devices market was valued at USD 6.5 billion in 2017 and is projected to grow at a CAGR of 5.6% from 2018 to 2026 to reach USD 10.6 billion by 2026, as a surge in the incidence of disorders such as cardiovascular diseases, respiratory and abdominal disorders is likely to boost the demand for ultrasound devices.
Read More
02 Oct 2018
AI and fMRI Show How Brain Connects Memories to Solve Problems
A team of German neuroscientists and Artificial Intelligence (AI) researchers have published results from their study that provided insights into the way the human brain connects individual episodic memories, or memories of specific events, to solve problems.
Read More
02 Oct 2018
Medical Robots Market to Reach USD 28 Billion in 2025
The global medical robots market is estimated to grow with a CAGR of 22.3% from USD 5.74 billion in 2017 to USD 28.78 billion in 2025, driven by increasing training programs for robotic surgeries and a rise in the usage of robots across various healthcare fields such as surgeries, therapies, rehabilitation, pharmacy dispensing, sanitation and others. These are the latest findings of Research and Markets, a global market research company.
Read More
01 Oct 2018
AI Tool Identifies Cancer Type and Changes in Lung Tumor
Researchers from the NYU School of Medicine have developed a new computer program that can analyze the images of patients' lung tumors, specify cancer types, and even identify altered genes driving abnormal cell growth. In their study, the researchers found that the artificial intelligence (AI), or "machine learning," program could distinguish -- with 97% accuracy -- between adenocarcinoma and squamous cell carcinoma, two lung cancer types that experienced pathologists at times struggle to parse without confirmatory tests. Additionally, the study found that the AI was also able to determine from analyzing the images whether the abnormal versions of six genes linked to lung cancer – including EGFR, KRAS and TP53 – were present in cells, with an accuracy ranging from 73% to 86%, depending upon the gene.
Read More
Copyright © 2000-2018 TradeMed.com. All rights reserved. | Terms And Conditions