MRI Recon Gets Real with AI-Driven Protocols

AI-based data reconstruction for MRI scans took a step forward this week with studies showing how to generate 3T-like images from ultralow-field scanners, and improve scanner efficiency by cutting energy consumption.

MRI is radiology’s premier modality, but MRI scanners are cumbersome to install and expensive to operate. 

  • Ultralow-field scanners could help but some believe they lack the image quality for some clinical applications. 

Enter AI-based image reconstruction. Deep learning protocols are being developed for a wide range of imaging modalities, from PET to CT to MRI. 

  • These algorithms take images acquired with lower-quality input data – be it less CT radiation dose or lower MRI field strength – and upscale them to resemble full-fidelity images.

This trend is illustrated by research published this week in Radiology in which researchers tested a generative adversarial network algorithm called LowGAN for reconstructing data acquired on Hyperfine’s Swoop 0.064T portable ultralow-field MRI scanner.

  • Their goal was to enable Swoop to generate images resembling those acquired on a 3T system. 

After training LowGAN on paired 3T and 0.064T images, they tested the algorithm in 50 patients with multiple sclerosis and further validated it with a separate 13-patient cohort. They then judged LowGAN against several measures of MR image quality, finding that it …

  • Showed the biggest improvement on synthetic FLAIR and T1 images.
  • Improved conspicuity of white matter lesions, without introducing false lesions.
  • Increased consistency of cortical and subcortical volume measurements with 3T images.
  • But was unable to reveal brain lesions that were missed in the original low-field scans. 

AI-based data reconstruction also has environmental implications. Medical imaging is a major contributor to greenhouse gas emissions, and anyone who’s managed an MRI operation knows how much energy these massive scanners consume. 

  • A second paper published this week in Radiology described how MRI acceleration – scans acquired at a faster speed and then reconstructed for better image quality – reduced energy use, lowering carbon emissions while boosting imaging capacity. 

Researchers tried three techniques for speeding MRI acquisition – parallel acceleration, simultaneous multi-slice, and a deep learning algorithm. 

  • All three reduced energy consumption 21% to 65% and increased daily capacity by one to seven scanning slots, with deep learning showing the biggest effect.

The Takeaway

The new papers demonstrate an exciting future in which less powerful data acquisition technologies can be upscaled with AI to produce images that more closely resemble state-of-the-art scanning. The benefits will be enjoyed by both patients and the planet.

AI Recon Cuts CT Radiation Dose

Artificial intelligence got its start in radiology as a tool to help medical image interpretation, but much of AI’s recent progress is in data reconstruction: improving images before radiologists even get to see them. Two new studies underscore the potential of AI-based reconstruction to reduce CT radiation dose while preserving image quality. 

Radiology vendors and clinicians have been remarkably successful in reducing CT radiation dose over the past two decades, but there’s always room for improvement. 

  • In addition to adjusting CT scanning protocols like tube voltage and current, data reconstruction protocols have been introduced to take images acquired at lower radiation levels and “boost” them to look like full-dose images. 

The arrival of AI and other deep learning-based technologies has turbocharged these efforts. 

They compared DLIR operating at high strength to GE’s older ASiR-V protocol in CCTA scans with lower tube voltage (80 kVp), finding that deep learning reconstruction led to …

  • 42% reduction in radiation dose (2.36 mSv vs. 4.07)
  • 13% reduction in contrast dose (50 mL vs. 58 mL).
  • Better signal- and contrast-to-noise ratios.
  • Higher image quality ratings.

In the second study, researchers from China including two employees of United Imaging Healthcare used a deep learning reconstruction algorithm to test ultralow-dose CT scans for coronary artery calcium scoring. 

  • They wanted to see if CAC scoring could be performed with lower tube voltage and current (80 kVp/20 mAs) and how the protocol compared to existing low-dose scans.

In tests with 156 patients, they found the ultralow-dose protocol produced …

  • Lower radiation dose (0.09 vs. 0.49 mSv).
  • No difference in CAC scoring or risk categorization. 
  • Higher contrast-to-noise ratio.

The Takeaway

AI-based data reconstruction gives radiologists the best of both worlds: lower radiation dose with better-quality images. These two new studies illustrate AI’s potential for lowering CT dose to previously unheard-of levels, with major benefits for patients.

Can AI Direct Breast MRI?

A deep learning algorithm trained to analyze mammography images did a better job than traditional risk models in predicting breast cancer risk. The study shows the AI model could direct the use of supplemental screening breast MRI for women who need it most. 

Breast MRI has emerged (along with ultrasound) as one of the most effective imaging modalities to supplement conventional X-ray-based mammography. Breast MRI performs well regardless of breast tissue density, and can even be used for screening younger high-risk women for whom radiation is a concern. 

But there are also disadvantages to breast MRI. It’s expensive and time-consuming, and clinicians aren’t always sure which women should get it. As a result, breast MRI is used too often in women at average risk and not often enough in those at high risk. 

In the current study in Radiology, researchers from MGH compared the Mirai deep learning algorithm to conventional risk-prediction models. Mirai was developed at MIT to predict five-year breast cancer risk, and the first papers on the model emerged in 2019; previous studies have already demonstrated the algorithm’s prowess for risk prediction

Mirai was used to analyze mammograms and develop risk scores for 2.2k women who also received 4.2k screening breast MRI exams from 2017-2020 at four facilities. Researchers then compared the performance of the algorithm to traditional risk tools like Tyrer-Cuzick and NCI’s Breast Cancer Risk Assessment (BCRAT), finding that … 

  • In women Mirai identified as high risk, the cancer detection rate per 1k on breast MRI was far higher compared to those classified as high risk by Tyrer-Cuzick and BCRAT (20.6 vs. 6.0 & 6.8)
  • Mirai had a higher PPV for predicting abnormal findings on breast MRI screening (14.6% vs. 5.0% & 5.5%)
  • Mirai scored higher in PPV of biopsies recommended (32.4% vs. 12.7% & 11.1%) and PPV for biopsies performed (36.4% vs. 13.5% & 12.5%)

The Takeaway
Breast imaging has become one of the AI use cases with the most potential, based on recent studies like PERFORMS and MASAI, and the new study shows Mirai could be useful in directing women to breast MRI screening. Like the previous studies, the current research is pointing to a near-term future in which AI and deep learning can make breast screening more accurate and cost-effective than it’s ever been before. 

Get every issue of The Imaging Wire, delivered right to your inbox.

You might also like..

Select All

You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team

You're all set!