From the January/February 2022 issue of HealthCare Business News magazine
"We see this technology specifically valuable to characterize structural damage to the heart, its function after myocardial infarction, and whether the heart can be fully repaired," Dr. Borja Ibáñez, director of the Clinical Research Department of CNIC, Cardiologist at the University Hospital Fundación Jiménez Díaz, and clinical leader of this work, told HCB News.
In just over 20 seconds, the shape and function of the heart can be acquired with the approach, as can the degree of fibrosis after cardiac muscle death in another 20-second acquisition. This enables the cardiac study to be completed in less than a minute.
Ad Statistics
Times Displayed: 186447
Times Visited: 4950 For those who need to move fast and expand clinical capabilities -- and would love new equipment -- the uCT 550 Advance offers a new fully configured 80-slice CT in up to 2 weeks with routine maintenance and parts and Software Upgrades for Life™ included.
A patient simply holds their breath during an MR scan so that everything within their chest remains static, except for the beating heart. ESSOS allows clinicians to capture an image of the static outer volume part, only for this data to then be temporarily removed. The MR signal of the beating heart can now be more easily subtracted from subsequent scan data, and allows for up to four times faster acquisition of a 3D image of the heart, with a net acceleration factor of up to 32.
British researchers label over 100,000 MR exams in under 30 minutes
In July, researchers in London announced they had devised a technique to label more than 100,000 MR exams in less than 30 minutes.
The group at the School of Biomedical Engineering & Imaging Sciences at King’s College London automated brain MR image labeling to teach machine learning image recognition models to identify and accurately assign important labels from radiology reports to corresponding MR exams.
"By overcoming this bottleneck, we have massively facilitated future deep learning image recognition tasks and this will almost certainly accelerate the arrival into the clinic of automated brain MR readers,” they wrote. “The potential for patient benefit through, ultimately, timely diagnosis, is enormous."
Senior author Dr. Tom Booth and his colleagues evaluated model performance on unseen radiology reports as well as on unseen images. The latter of these tasks has been a challenge, he says, due to the enormous team of radiologists required.
The study adds further insight on recent breakthroughs in natural language processing, including the launch of larger transformer-based models such as BERT and BioBERT. Both have been trained on huge collections of unlabeled text such as all of English Wikipedia and all PubMed Central abstracts and free articles.
In addition, the authors say the elimination of manually labeling large numbers of MR exams will allow radiologists to focus on other challenges, such as the need to perform deep learning recognition tasks that also have multiple technical challenges. Once this is achieved, they can work to ensure the developed models still perform accurately across different hospitals with different scanners.
