New Image Reconstruction Technique Combines Data Science with ML for Faster MRIs
By MedImaging International staff writers Posted on 15 Sep 2022 |
For the last decade or so, scientists have been making Magnetic Resonance Imaging (MRI) 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. Now, using a combination of modern data science tools and machine learning ideas, researchers have found a way to fine-tune the traditional compressing method to make it nearly as high-quality as deep learning. This finding by scientists and engineers at the University of Minnesota (Minneapolis, MN, USA) provides a new research direction for the field of MRI reconstruction. It can improve the performance of traditional MRI reconstruction techniques, allowing for faster MRIs to improve healthcare.
“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. “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.”
“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.”
Related Links:
University of Minnesota
Latest MRI News
- World's First Whole-Body Ultra-High Field MRI Officially Comes To Market
- World's First Sensor Detects Errors in MRI Scans Using Laser Light and Gas
- Diamond Dust Could Offer New Contrast Agent Option for Future MRI Scans
- Combining MRI with PSA Testing Improves Clinical Outcomes for Prostate Cancer Patients
- PET/MRI Improves Diagnostic Accuracy for Prostate Cancer Patients
- Next Generation MR-Guided Focused Ultrasound Ushers In Future of Incisionless Neurosurgery
- Two-Part MRI Scan Detects Prostate Cancer More Quickly without Compromising Diagnostic Quality
- World’s Most Powerful MRI Machine Images Living Brain with Unrivaled Clarity
- New Whole-Body Imaging Technology Makes It Possible to View Inflammation on MRI Scan
- Combining Prostate MRI with Blood Test Can Avoid Unnecessary Prostate Biopsies
- New Treatment Combines MRI and Ultrasound to Control Prostate Cancer without Serious Side Effects
- MRI Improves Diagnosis and Treatment of Prostate Cancer
- Combined PET-MRI Scan Improves Treatment for Early Breast Cancer Patients
- 4D MRI Could Improve Clinical Assessment of Heart Blood Flow Abnormalities
- MRI-Guided Focused Ultrasound Therapy Shows Promise in Treating Prostate Cancer
- AI-Based MRI Tool Outperforms Current Brain Tumor Diagnosis Methods