Algorithm compares 3D medical images up to 1000x faster
Medical image registration – the process of transforming different sets of data into one coordinate system – is a common technique that involves overlaying two images, such as magnetic resonance imaging (MRI) scans, to compare and analyze anatomical differences in great detail. For example, doctors can overlap a brain scan from several months ago onto a more recent scan to analyze small changes in a patient’s brain, such as the progress of a tumor.
Traditionally, this process has involved meticulously aligning each of potentially a million pixels in the combined scans, and can often take two hours or more. The new machine learning algorithm, however, is able to map all pixels on one image to another all at once.
The algorithm works by “learning” while registering thousands of pairs of images, and in the process acquires information about how to align images and estimates some optimal alignment parameters, which it then uses to do the mapping. This reduces registration time to a minute or two using a normal computer, or less than a second using a GPU with comparable accuracy to state-of-the-art systems, say the researchers.
“The tasks of aligning a brain MRI shouldn’t be that different when you’re aligning one pair of brain MRIs or another,” says Guha Balakrishnan, a graduate student in MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Department of Engineering and Computer Science (EECS). “There is information you should be able to carry over in how you do the alignment. If you’re able to learn something from previous image registration, you can do a new task much faster and with the same accuracy.”
The researchers’ algorithm – called “VoxelMorph” – is powered by a convolutional neural network (CNN), a machine-learning approach commonly used for image processing. These networks consist of many nodes that process image and other information across several layers of computation.
The researchers trained their algorithm on 7,000 publicly available MRI brain scans and then tested it on 250 additional scans. They found that their algorithm could accurately register all of their 250 test brain scans.
In addition to analyzing brain scans, say the researchers, the algorithm has a wide range of potential applications. For example, MIT researchers are currently running the algorithm on lung images.
The algorithm could also pave the way for image registration during operations, say the researchers. Currently, various scans of different qualities and speeds are used before or during some surgeries, but those images are not registered until after the operation.
For example, surgeons sometimes scan a patient’s brain before and after surgery to see if they’ve removed all of a tumor, which can result in having to schedule further surgeries. With the new algorithm, say the researchers, surgeons could potentially register scans in near real time, getting a much clearer picture on their progress.
For more, see “An Unsupervised Learning Model for Deformable Medical Image Registration.” (PDF)
Related articles:
Nvidia supercomputing platform to ‘revolutionize’ medical imaging
Algorithm beats radiologists in diagnosing x-rays
Deep learning improves medical imaging
AI more effective than humans at analyzing heart scans
Google algorithm predicts cardiovascular risk from eye images
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
