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