Like the artist’s composite sketch that slowly reveals the face of a criminal suspect, the image on Xiaolei Huang’s computer screen is gradually zeroing in on America’s number-one killer – heart disease.
Lines in Huang’s image crisscross to form a netlike pattern called a polygon mesh. They intersect at three dimensional nodes called vertices.
Huang has used computer graphics to render a geometric model of three phases of the beating of an actual heart that was scanned, over time, by magnetic resonance imaging (MRI).
The heart may have its secrets, but the stress and strain that it undergoes as it pumps blood is not one of them, at least not to Huang, who is an assistant professor of computer science and engineering.
Huang writes software programs that enhance the detecting powers of MRI and other medical imaging techniques. Her programs can take 4-D medical images – with time as the fourth dimension – and extract from them the precise geometric shape and motion of the heart.
Huang then builds 4-D computer models that measure the natural changes, or deformations, in the heart’s structure as it expands and contracts.
These models will give cardiologists a clearer picture of the differences between the normal deformations that occur in healthy hearts and the abnormal deformations that occur in damaged and diseased hearts. They will also help physicians recognize different types of abnormal deformation and correspond them to various types of disease or damage.
“The clearer the picture we can obtain of the deformation in a normal heart,” says Huang, “the more quickly and reliably we can identify abnormalities in deformation that indicate a diseased or damaged heart. And if we obtain enough examples of different types of abnormalities, we can characterize the commonalities of these abnormalities.”
Tagging and tracking
The heart modeled on Huang’s computer screen was scanned by an MRI technique called SPAtial Modulation of Magnetization. SPAMM tags material points within the heart wall, which can be tracked over time to reveal the 3-D motion of the heart muscle.
The tags enable Huang to outline, or segment, the heart’s structures, including the boundaries separating heart and lungs, as well as those demarcating the heart’s outer wall, left and right ventricles and myocardium.
Huang then locates the vertices, manipulates her image and tracks the path of each vertex as the heart deforms. Based on the displacement of the vertices, she calculates the stress and strain imposed on the heart muscle.
“The model is no longer just a geometric model,” says Huang. “Now it has mechanical properties. This enables us to perform precise quantifications. We can partition the heart wall into sub-regions and follow each of these to determine whether the deformation that occurs is normal or not.”
Huang collaborates with computer scientists at Rutgers University and with Dr. Leon Axel, director of cardiac imaging at the New York University School of Medicine. She has a grant from the Lindback Foundation’s Minority Junior Faculty Award Program.
Huang says her model will enable diagnosticians to interpret medical images in a fraction of the time they now require.
“It takes hours for a human expert to interpret a sequence of images from one patient,” she says. “Our software tool can do segmentation and build a 4-D model in 26 seconds, while finding more instances of abnormal deformations and structures, especially very localized ones.”
Quantitative computer image analysis, says Huang, will not eliminate the need for human experts, but it will give technicians a valuable tool that automates the interpretation of medical scans.
“The tools of computer-aided diagnosis [CAD] are becoming more powerful, but they still don’t work as well as human analysts. They can, however, help technicians do their job faster, less subjectively and more reliably.”
In pursuit of hot spots
One of Huang’s software programs draws information from images acquired with Positron Emission Tomography (PET), a technique used in radiation oncology. PET produces a 3-D map of bright “hot spots” that represent areas of high energy activity in the body. These hot spots, however, can represent either normal sites like the heart or other organs, or abnormal sites such as tumors or inflammations.
Huang’s software automates the interpretation of PET scans by differentiating between normal and abnormal hot spots. Using segmentation, she identifies the precise boundaries of all hot spots in the PET scan and its accompanying CT scan. Using pattern recognition and computer vision, she identifies organs based on their shape and location. She “suppresses” these sites and then tracks the changes over time in abnormal hot spots.
“The precise boundaries of organs and tumors are very valuable,” says Huang. “Oncologists rely on them to make radiation treatment plans that protect normal organs by exposing them to as little radiation as possible while targeting tumors with high-intensity radiation.”
Because Huang’s software tools can do geometrical, statistical and mechanical modeling, her programs keep working when unforeseen obstacles are encountered.
“The main challenge with medical image computing is to do it robustly. Too often, when a software program encounters noise [slight variations in intensity, unwanted disturbance, energy or interference] or artifacts [ranging from dental fillings to distortions in tissue structure], it breaks down. Once this happens, it is difficult to recover information.
“Our model can be as complex or as simple as we want. We can attach to it as many properties as we want. It can represent geometry or it can be a statistical model. It can encode variations across patients and infer a statistical model from multiple people. Or it can have mechanical properties. All of this builds in robustness.”