MIT Neural Network Accelerates MRI Image Processing by 1,000 Times

MIT Neural Network Accelerates MRI Image Processing by 1,000 Times

Doctors often need to compare two MRI images to track changes in the body over time, but the process of lining up the images to make accurate measurements is extremely time-consuming. It can take hours for a computer to match all the locations in a 3D map, but researchers from MIT have developed an algorithm that could cut that time to less than a second.

MRI scans are cumbersome to manage because of how much information they contain. Each scan is essentially hundreds of stacked 2D images. These form the 3D map known as a volume. The volume is made up of 3D pixels known as voxels. When a computer aligns two different MRI scans, it’s sifting through millions of voxels to assign them locations in a new, unified image. Scans can also come from different machines with varying spatial properties, slowing the work even more.

Several hours of computing time is considered quite good for MRI analysis. Researchers trying to analyze data from large populations across multiple patients with the same disease can end up waiting hundreds of hours for a computer to generate aligned images. Simply throwing more processing power at the problem isn’t practical, but the “VoxelMorph” system from MIT researchers might do the trick.

VoxelMorph is a convolutional neural network, so the team started by training it with 7,000 publicly available MRI brain scans. In a neural network, you add data at one end, and the network passes it through numerous nodes that feed forward into other nodes. Depending on the weighting of each node, you end up with an output that should provide the desired results. VoxelMorph learned about common groups of voxels and anatomical shapes.

MIT Neural Network Accelerates MRI Image Processing by 1,000 Times

After training, the team used 250 new scans to test the network’s effectiveness. VoxelMorph completed in two minutes what would have taken a conventional MRI analysis program several hours to do. That’s just with a regular CPU. When VoxelMorph runs on a GPU, the process takes less than a second. If you were building a machine to process MRI images, you’d probably configure it to run calculations on the GPU.

So, we’ve effectively gone from hours to instantaneous. The team suggests this could change the way doctors perform some surgeries. It may be possible to make new scans during a surgery and get real-time analysis of the images. The system could also potentially work on other types of 3D scans with additional training.

Continue reading

Voyager 2 Probe Talks to Upgraded NASA Network After 8 Months of Silence
Voyager 2 Probe Talks to Upgraded NASA Network After 8 Months of Silence

NASA just said "hello" to Voyager 2, and the probe said it back.

Verizon’s New 4G Network Is Faster Than Its 5G
Verizon’s New 4G Network Is Faster Than Its 5G

After some recent upgrades, Verizon's LTE is now faster than its 5G.

Nokia Is Developing a 4G Network on the Moon With 5 KM Range
Nokia Is Developing a 4G Network on the Moon With 5 KM Range

According to Thierry Klein, who runs the Enterprise and Industrial Automation Research Lab at Bell Labs, a previously aborted space LTE project has given it a headstart on deploying LTE on the moon.

A Surprising Winner Emerges in New US Mobile Networks Test
A Surprising Winner Emerges in New US Mobile Networks Test

New results for the fastest mobile network of 2021 are in, and this time, Verizon didn't win.