News | Magnetic Resonance Imaging (MRI) | September 15, 2022

New research closes the gap between traditional and deep learning methods 

University of Minnesota Twin Cities researchers have found a way to improve the performance of traditional Magnetic Resonance Imaging (MRI) reconstruction techniques, allowing for faster MRIs without relying on the use of newer deep learning methods. Credit: Intelligent Medical Imaging and Image Processing Lab, University of Minnesota

University of Minnesota Twin Cities researchers have found a way to improve the performance of traditional Magnetic Resonance Imaging (MRI) reconstruction techniques, allowing for faster MRIs without relying on the use of newer deep learning methods. Credit: Intelligent Medical Imaging and Image Processing Lab, University of Minnesota 


September 15, 2022 — University of Minnesota Twin Cities scientists and engineers have found a way to improve the performance of traditional Magnetic Resonance Imaging (MRI) reconstruction techniques, allowing for faster MRIs to improve healthcare. 

The paper is published in the Proceedings of the National Academy of Sciences of the United States of America (PNAS), a peer-reviewed, multidisciplinary, high-impact scientific journal. 

“MRIs take a long time because you’re acquiring the data in a sequential manner. You have to fill up the frequency space of your image in a successive manner,” explained Mehmet Akcakaya, the Jim and Sara Anderson Associate Professor in the University of Minnesota Department of Electrical and Computer Engineering and senior author of the paper. “We want to make MRIs faster so that patients are there for shorter times and so that we can increase the efficiency in the healthcare system. This paper explores a way of doing this while making sure that we maintain a good performance.” 

For the last decade or so, scientists have been making MRIs faster using a technique called compressed sensing, which uses the idea that images can be compressed into smaller sizes, akin to zipping a .jpeg on a computer.  

More recently, researchers have been looking into using deep learning, a type of machine learning, to speed up MRI image reconstruction. Instead of capturing every frequency during the MRI procedure, this process skips over frequencies and uses a trained machine learning algorithm to predict the results and fill in those gaps.  

Many studies have shown deep learning to be better than traditional compressed sensing by a large margin. However, there are some concerns with using deep learning—for example, having insufficient training data could create a bias in the algorithm that might cause it to misinterpret the MRI results. 

Using a combination of modern data science tools and machine learning ideas, the University of Minnesota Twin Cities researchers have found a way to fine-tune the traditional compressing method to make it nearly as high-quality as deep learning. 

Akcakaya said this finding provides a new research direction for the field of MRI reconstruction. 

“What we’re saying is that there’s a lot of hype surrounding deep learning in MRIs, but maybe that gap between new and traditional methods isn’t as big as previously reported,” Akcakaya said. “We found that if you tune the classical methods, they can perform very well. So, maybe we should go back and look at the classical methods and see if we can get better results. There is a lot of great research surrounding deep learning as well, but we’re trying to look at both sides of the picture to see where we can find the best performance, theoretical guarantees, and stability.” 

For more information: https://cse.umn.edu/


Related Content

News | Artificial Intelligence

March 1, 2024 — Royal Philips, a global leader in health technology, and magnetic resonance imaging (MRI) software ...

Time March 01, 2024
arrow
News | PACS

February 22, 2024 — aycan, a recognized leader in medical imaging, announced that Enspectra Health used aycan’s PACS ...

Time February 22, 2024
arrow
News | Breast Imaging

February 22, 2024 — The FAST-Forward randomized trial from the UK found that ultrahypofractionated whole breast ...

Time February 22, 2024
arrow
News | Cardiac Imaging

February 12, 2024 — According to the American Journal of Roentgenology (AJR), free-breathing cine-deep learning (DL) may ...

Time February 12, 2024
arrow
News | SNMMI

February 6, 2024 — The Society of Nuclear Medicine and Molecular Imaging (SNMMI) held its 2024 SNMMI Mid-Winter Meeting ...

Time February 06, 2024
arrow
News | Digital Pathology

January 26, 2024 — New research funded by the National Institute for Health and Care Research (NIHR) has led to the UK ...

Time January 26, 2024
arrow
News | Radiology Business

January 25, 2024 — Esaote Group, a leading Italian innovator in medical imaging, today unveiled its new brand identity ...

Time January 25, 2024
arrow
News | Artificial Intelligence

January 23, 2024 — Quibim announced it has added an industry-leading cancer detection capability to its prostate tool ...

Time January 22, 2024
arrow
News | Artificial Intelligence

December 22, 2023 — Quibim, a company pioneering imaging biomarkers for Precision Medicine that has created AI-based ...

Time December 22, 2023
arrow
News | Magnetic Resonance Imaging (MRI)

December 20, 2023 — Terran Biosciences, Inc., a biotech platform company developing therapeutics and technologies for ...

Time December 20, 2023
arrow
Subscribe Now