Example images reconstructed using (A) regridding or (B) the Phase2Phase method...
Example images reconstructed using (A) regridding or (B) the Phase2Phase method developed by Hongyu An and Ulugbek Kamilov. The Phase2Phase image was obtained by directly applying the Phase2Phase network trained on CAPTURE images to image in (A).

Image source: Washington University in St. Louis

Imaging assistance

Deep learning method boosts MRI results without new data

A team of researchers from Washington University in St. Louis has found a new deep learning method that can minimize artifacts and other noise in MRI images that come from movement and a short image-acquisition time.

When patients undergo an MRI, they are told to lie still because even the slightest movement compromises the quality of the images and can create blurred spots and speckles known as artifacts. Moreover, a long acquisition time is usually required to provide high-quality MRI images.

Hongyu An, a professor of radiology at the School of Medicine’s Mallinckrodt Institute of Radiology (MIR), and Ulugbek Kamilov, assistant professor of computer science and engineering and of electrical and systems engineering in the McKelvey School of Engineering, led an interdisciplinary team that developed the Phase2Phase deep learning method, which they trained using images with artifacts and without a ground truth, in this case, a perfect image without artifacts. Results of the work were published in Investigative Radiology.

In an MRI, it may be easy or hard to scan someone, depending on their physical health, but everyone still has to breathe

Ulugbek Kamilov

Deep learning learns directly from the training data how to determine the signal from artifacts and noise, or variations in signal intensity in an image. Many existing deep learning-based MRI reconstruction methods are able to remove artifacts and noise but they learn from a ground truth reference, which can be difficult to obtain. “In an MRI, it may be easy or hard to scan someone, depending on their physical health, but everyone still has to breathe,” Kamilov said. “When they breathe, their internal organs move, and we have to determine how to correct for those movements.”

In Phase2Phase, the team feeds the deep learning model with only sets of bad images and trains the neural network to predict a good image from a bad one without a ground truth reference. Weijie Gan, a doctoral student in Kamilov’s lab and a co-first author on the paper, wrote the software for Phase2Phase to remove noise and artifacts. Cihat Eldeniz, an instructor of radiology at the Mallinckrodt Institute of Radiology and co-first author, worked on the MRI acquisition and motion detection used in the study. They modeled Phase2Phase after an existing machine learning method known as Noise2Noise, which restores images without clean data.

In a retrospective study, the team evaluated MRI data from 33 participants — 15 healthy persons and 18 patients with liver cancer, all of whom were allowed to breathe normally while in the scanner. These results were compared with images reconstructed with another deep learning method, UNet3DPhase, which is trained on a high-quality ground truth; compressed sensing; and multicoil nonuniform fast Fourier transform (MCNUFFT). In addition, this Phase2Phase method has successfully reconstructed 66 MRI data sets acquired at another institution using different acquisition parameters, demonstrating its broad applicability.

Recommended article

Photo

Innovation

AI helpers simplify clinical MRI scans

The new 1.5 Tesla MRI from Siemens Healthineers, Magnetom Sola, is packed with helpful algorithms and other functions. AI-supported systems monitor patients and scan parameters and ensure consistent image quality. Whilst visitors at this year’s ECR-Expo admired the new device, Prof. Ulrike Attenberger has already tested it in practice.

Two radiologists, who were blinded to which reconstruction method was used on the images, reviewed the images for their sharpness, contrast and artifacts. They found that the Phase2Phase and UNet3DPhase images had higher contrast and fewer artifacts than the compressed sensing images. The UNet3DPhase and Phase2Phase images were reported to be sharper than the compressed sensing images by one reviewer, but not by the other. The Phase2Phase and UNet3DPhase images were similar in sharpness and contrast, while the UNet3DPhase images had fewer artifacts than the Phase2Phase. The Phase2Phase images preserve the motion vector fields, while the compressed sensing images artificially reduced the motion vector fields. “The Phase2Phase deep learning method provides an excellent solution for a rapid reconstruction of high-quality 4D liver images using only a fraction of acquisition time,” said An, who also is a professor of neurology. “It improves image quality for better clinical diagnosis.”

The research team and Siemens Healthineers collaborated to develop a work-in-progress (WIP) software. This WIP software was disclosed to the Washington University in St. Louis Office of Technology Management, and a patent application was jointly filed.


Source: Washington University in St. Louis

08.09.2021

Read all latest stories

Related articles

Photo

Deep learning in imaging

1.5T MR system receives FDA clearance for AI-based image reconstruction technology

Canon Medical Systems USA, Inc. has received 510(k) clearance on its Advanced intelligent Clear-IQ Engine (AiCE) for the Vantage Orian 1.5T MR system, continuing to expand access to its new Deep…

Photo

Survival of patients

Unsupervised AI predicts the progression of COVID-19

Unsupervised deep learning breaks new ground by predicting the progression of COVID-19 and survival of patients directly from their chest CT images.

Photo

Immersive imaging distraction

VR system to reduce MRI scan anxiety

Claustrophobia or anxiety can overwhelm small children and people with cognitive difficulties, especially in a confining and noisy MRI scanner tube. Their restless reactions can then render scan…

Related products

Canon – Advanced intelligent Clear-IQ Engine for MR

Artificial Intelligence

Canon – Advanced intelligent Clear-IQ Engine for MR

Canon Medical Systems Europe B.V.
Canon - Vantage Elan NX Edition

1.5 Tesla

Canon - Vantage Elan NX Edition

Canon Medical Systems Europe B.V.
Canon – Vantage Galan 3 T

3 Tesla

Canon – Vantage Galan 3 T

Canon Medical Systems Europe B.V.
Hitachi – Airis Vento Plus

Open

Hitachi – Airis Vento Plus

Hitachi Medical Systems Europe (Holding) AG
Hitachi – Aperto Lucent Plus

Open

Hitachi – Aperto Lucent Plus

Hitachi Medical Systems Europe (Holding) AG
Hitachi – Echelon Smart

1.5 Tesla

Hitachi – Echelon Smart

Hitachi Medical Systems Europe (Holding) AG
Subscribe to Newsletter