Nav: Home

Algorithm speeds up process for analyzing 3D medical images

June 18, 2018

Medical image registration 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. If a patient has a brain tumor, for instance, doctors can overlap a brain scan from several months ago onto a more recent scan to analyze small changes in the tumor's progress.

This process, however, can often take two hours or more, as traditional systems meticulously align each of potentially a million pixels in the combined scans. In a pair of upcoming conference papers, MIT researchers describe a machine-learning algorithm that can register brain scans and other 3-D images more than 1,000 times more quickly using novel learning techniques.

The algorithm works by "learning" while registering thousands of pairs of images. In doing so, it acquires information about how to align images and estimates some optimal alignment parameters. After training, it uses those parameters to map all pixels of one image to another, all at once. 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.

"The tasks of aligning a brain MRI shouldn't be that different when you're aligning one pair of brain MRIs or another," says co-author on both papers 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 papers are being presented at the Conference on Computer Vision and Pattern Recognition (CVPR), held this week, and at the Medical Image Computing and Computer Assisted Interventions Conference (MICCAI), held in September. Co-authors are: Adrian Dalca, a postdoc at Massachusetts General Hospital and CSAIL; Amy Zhao, a graduate student in CSAIL; Mert R. Sabuncu, a former CSAIL postdoc and now a professor at Cornell University; and John Guttag, the Dugald C. Jackson Professor in Electrical Engineering at MIT.

Retaining information

MRI scans are basically hundreds of stacked 2-D images that form massive 3-D images, called "volumes," containing a million or more 3-D pixels, called "voxels." Therefore, it's very time-consuming to align all voxels in the first volume with those in the second. Moreover, scans can come from different machines and have different spatial orientations, meaning matching voxels is even more computationally complex.

"You have two different images of two different brains, put them on top of each other, and you start wiggling one until one fits the other. Mathematically, this optimization procedure takes a long time," says Dalca, senior author on the CVPR paper and lead author on the MICCAI paper.

This process becomes particularly slow when analyzing scans from large populations. Neuroscientists analyzing variations in brain structures across hundreds of patients with a particular disease or condition, for instance, could potentially take hundreds of hours.

That's because those algorithms have one major flaw: They never learn. After each registration, they dismiss all data pertaining to voxel location. "Essentially, they start from scratch given a new pair of images," Balakrishnan says. "After 100 registrations, you should have learned something from the alignment. That's what we leverage."

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.

In the CVPR paper, the researchers trained their algorithm on 7,000 publicly available MRI brain scans and then tested it on 250 additional scans.

During training, brain scans were fed into the algorithm in pairs. Using a CNN and modified computation layer called a spatial transformer, the method captures similarities of voxels in one MRI scan with voxels in the other scan. In doing so, the algorithm learns information about groups of voxels -- such as anatomical shapes common to both scans -- which it uses to calculate optimized parameters that can be applied to any scan pair.

When fed two new scans, a simple mathematical "function" uses those optimized parameters to rapidly calculate the exact alignment of every voxel in both scans. In short, the algorithm's CNN component gains all necessary information during training so that, during each new registration, the entire registration can be executed using one, easily computable function evaluation.

The researchers found their algorithm could accurately register all of their 250 test brain scans -- those registered after the training set -- within two minutes using a traditional central processing unit, and in under one second using a graphics processing unit.

Importantly, the algorithm is "unsupervised," meaning it doesn't require additional information beyond image data. Some registration algorithms incorporate CNN models but require a "ground truth," meaning another traditional algorithm is first run to compute accurate registrations. The researchers' algorithm maintains its accuracy without that data.

The MICCAI paper develops a refined VoxelMorph algorithm that "says how sure we are about each registration," Balakrishnan says. It also guarantees the registration "smoothness," meaning it doesn't produce folds, holes, or general distortions in the composite image. The paper presents a mathematical model that validates the algorithm's accuracy using something called a Dice score, a standard metric to evaluate the accuracy of overlapped images. Across 17 brain regions, the refined VoxelMorph algorithm scored the same accuracy as a commonly used state-of-the-art registration algorithm, while providing runtime and methodological improvements.

Beyond brain scans

The speedy algorithm has a wide range of potential applications in addition to analyzing brain scans, the researchers say. MIT colleagues, for instance, are currently running the algorithm on lung images.

The algorithm could also pave the way for image registration during operations. Various scans of different qualities and speeds are currently used before or during some surgeries. But those images are not registered until after the operation. When resecting a brain tumor, for instance, surgeons sometimes scan a patient's brain before and after surgery to see if they've removed all the tumor. If any bit remains, they're back in the operating room.

With the new algorithm, Dalca says, surgeons could potentially register scans in near real-time, getting a much clearer picture on their progress. "Today, they can't really overlap the images during surgery, because it will take two hours, and the surgery is ongoing" he says. "However, if it only takes a second, you can imagine that it could be feasible."
-end-
Additional background

ARCHIVE: New technique makes brain scans better http://news.mit.edu/2017/new-technique-makes-brain-scans-better-0621

ARCHIVE: Using machine learning to improve patient care http://news.mit.edu/2017/using-machine-learning-improve-patient-care-0821

ARCHIVE: Making sense of medical sensors http://news.mit.edu/2013/making-sense-of-medical-sensors-0419

Massachusetts Institute of Technology

Related Brain Tumor Articles:

New target found to attack an incurable brain tumor in children
Research shows that a tumor suppressor gene p16 is turned off by a histone mutation (H3.3K27M), which is found in up to 70 percent of childhood brain tumors called diffuse intrinsic pontine glioma (DIPG).
Treatment of malignant brain tumor in children gets closer
Researchers at the University of Copenhagen have identified important mechanisms underlying how a special type of malignant brain tumor arises in children.
Molecule stops fatal pediatric brain tumor
Northwestern Medicine scientists have found a molecule that stops the growth of an aggressive pediatric brain tumor.
Tumor-seeking salmonella treats brain tumors
Genetic tweaks to salmonella turn the bacteria into cancer-seeking missiles that produce self-destruct orders deep within tumors.
Molecular signature for aggressive brain tumor uncovered
Researchers from Brigham and Women's Hospital, in collaboration with colleagues at Massachusetts General Hospital, have identified genetic mutations that can distinguish aggressive rhabdoid meningiomas from more benign forms using routine laboratory tests.
Brain tumor characteristics could help predict survival in people over 70
Characteristics like seizures, location of the tumour, and pressure in the brain, give insight into length of survival and treatment options for brain tumour patients over the age of 70, according to new research* presented at the National Cancer Research Institute's (NCRI) Cancer Conference in Liverpool.
Key mechanism identified in brain tumor growth
A gene known as OSMR plays a key role in driving the growth of glioblastoma tumors, according to a new study led by a McGill University researcher and published in the journal Nature Neuroscience.
Laser treatment may boost effectiveness of brain tumor drugs
The human brain has a remarkable defense system that filters bacteria and chemicals.
Genetic cause identified in rare pediatric brain tumor
Researchers found a way of differentiating angiocentric gliomas from other low-grade pediatric brain tumors and developed a pathological test that will help children avoid unnecessary and potentially damaging additional therapies.
New way to identify brain tumor aggressiveness
A comprehensive analysis of the molecular characteristics of gliomas -- the most common malignant brain tumor -- explains why some patients diagnosed with slow-growing (low-grade) tumors quickly succumb to the disease while others with more aggressive (high-grade) tumors survive for many years.

Related Brain Tumor Reading:

Best Science Podcasts 2019

We have hand picked the best science podcasts for 2019. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Setbacks
Failure can feel lonely and final. But can we learn from failure, even reframe it, to feel more like a temporary setback? This hour, TED speakers on changing a crushing defeat into a stepping stone. Guests include entrepreneur Leticia Gasca, psychology professor Alison Ledgerwood, astronomer Phil Plait, former professional athlete Charly Haversat, and UPS training manager Jon Bowers.
Now Playing: Science for the People

#524 The Human Network
What does a network of humans look like and how does it work? How does information spread? How do decisions and opinions spread? What gets distorted as it moves through the network and why? This week we dig into the ins and outs of human networks with Matthew Jackson, Professor of Economics at Stanford University and author of the book "The Human Network: How Your Social Position Determines Your Power, Beliefs, and Behaviours".