#Justin Mikhail Solomon | Explore Tumblr posts and blogs

dorcasrempel · 5 years ago

Text

Using algorithms to build a map of the placenta

The placenta is one of the most vital organs when a woman is pregnant. If it’s not working correctly, the consequences can be dire: Children may experience stunted growth and neurological disorders, and their mothers are at increased risk of blood conditions like preeclampsia, which can impair kidney and liver function.

Unfortunately, assessing placental health is difficult because of the limited information that can be gleaned from imaging. Traditional ultrasounds are cheap, portable, and easy to perform, but they can’t always capture enough detail. This has spurred researchers to explore the potential of magnetic resonance imaging (MRI). Even with MRIs, though, the curved surface of the uterus makes images difficult to interpret.

This problem got the attention of a team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), who wondered whether the placenta’s scrunched shape could be flattened out using some fancy geometry.

Next month they’re publishing a paper showing that it can. Their new algorithm unfolds images from MRI scans to better visualize the organ. For example, their images more clearly show the “cotyledons,” circular structures that allow for the exchange of nutrients between the mother and her developing child or children. Being able to visualize such structures could allow doctors to diagnose and treat placental issues much earlier in the pregnancy.

“The idea is to unfold the image of the placenta while it’s in the body, so that it looks similar to how doctors are used to seeing it after delivery,” says PhD student Mazdak Abulnaga, lead author of the new paper with MIT professors Justin Solomon and Polina Golland. “While this is just a first step, we think an approach like this has the potential to become a standard imaging method for radiologists.”

Golland says that the algorithm could also be used in clinical research to find specific biomarkers associated with poor placental health. Such research could help radiologists save time and more accurately locate problem areas without having to examine many different slices of the placenta.

Chris Kroenke, an associate professor at Oregon Health and Science University, says that the project opens up many new possibilities for monitoring placental health.

“The biological processes that underlie cotyledon patterning are not completely understood, nor is it known whether a standard pattern should be expected for a given population,” says Kroenke, who was not involved in the paper. “The tools provided by this work will certainly aid researchers to address these questions in the future.”

Abulnaga, Solomon, and Golland co-wrote the paper with former CSAIL postdoc Mikhail Bessemeltsev and their collaborators, Esra Abaci Turk and P. Ellen Grant of Boston Children’s Hospital (BCH). Grant is the director of BCH’s Fetal-Neonatal Neuroimaging and Development Science Center, and a professor of radiology and pediatrics at Harvard Medical School. The team also worked closely with collaborators at Massachusetts General Hospital (MGH) and MIT Professor Elfar Adalsteinsson.

The paper will be presented Oct. 14 in Shenzhen, China, at the International Conference on Medical Image Computing and Computer-Assisted Intervention.

The team’s algorithm first models the placenta’s shape by subdividing it into thousands of tiny pyramids, or tetrahedra. This serves an efficient representation for computers to perform operations to manipulate the shape. The algorithm then arranges those pyramids into a template that resembles the flattened shape that a placenta holds once it’s out of the body. (The algorithm does this by essentially moving the corners of the pyramids on the surface of the placenta to match the two parallel planes of the template and letting the rest fill the new shape.)

The model has to make a tradeoff between the pyramids matching the shape of the template and minimizing the amount of distortion. The team showed the system can ultimately achieve accuracy at the scale of less than one voxel (a 3-D pixel).

The project is far from the first aimed at improving medical imaging by actually manipulating said images. There have been recent efforts to unfold scans of ribs, and researchers have also spent many years developing ways to flatten images of the brain’s cerebral cortex to better visualize areas between the folds.

Meanwhile, work involving the womb is much newer. Previous approaches to this problem focused on flattening different layers of the placenta separately. The team says that they feel that the new volumetric method results in more consistency and less distortion because it maps the whole 3-D placenta at once, enabling it to more closely model the physical unfolding process.

“The team’s work provides a very elegant tool to address the issue of the placenta’s irregular shape being difficult to image,” says Kroenke.

As a next step, the team hopes to work with MGH and BCH to directly compare in-utero images with ones of the same placentas post-birth. Because the placenta loses fluid and changes shape during the birth process, this will require using a special chamber designed by MGH and BCH where researchers can put the placenta directly after the birth.

The source code for the project is available on github. The work was supported in part by the National Institute of Child Health and Human Development, the National Institute of Biomedical Imaging and Bioengineering, the National Science Foundation, the U.S. Air Force, and the Natural Sciences and Engineering Research Council of Canada.

Using algorithms to build a map of the placenta syndicated from https://osmowaterfilters.blogspot.com/

0 notes

dorcasrempel · 6 years ago

Text

Smoothing out sketches’ rough edges

Artists may soon have at their disposal a new MIT-developed tool that could help them create digital characters, logos, and other graphics more quickly and easily.

Many digital artists rely on image vectorization, a technique that converts a pixel-based image into an image comprising groupings of clearly defined shapes. In this technique, points in the image are connected by lines or curves to construct the shapes. Among other perks, vectorized images maintain the same resolution when either enlarged or shrunk down.

To vectorize an image, artists often have to hand-trace each stroke using specialized software, such as Adobe Illustrator, which is laborious. Another option is using automated vectorization tools in those software packages. Often, however, these tools lead to numerous tracing errors that take more time to rectify by hand. The main culprit: mismatches at intersections where curves and lines meet.

In a paper being published in the journal ACM Transactions on Graphics, MIT researchers detail a new automated vectorization algorithm that traces intersections without error, greatly reducing the need for manual revision. Powering the tool is a modified version of a new mathematical technique in the computer-graphics community, called “frame fields,” used to guide tracing of paths around curves, sharp corners, and messy parts of drawings where many lines intersect.

The tool could save digital artists significant time and frustration. “A rough estimate is that it could save 20 to 30 minutes from automated tools, which is substantial when you think about animators who work with multiple sketches,” says first author Mikhail Bessmeltsev, a former Computer Science and Artificial Intelligence Laboratory (CSAIL) postdoc associate who is now an assistant professor at the University of Montreal. “The hope is to make automated vectorization tools more practical for artists who care about the quality of their work.”

Co-author on the paper is Justin Solomon, an assistant professor in CSAIL and in the Department of Electrical Engineering and Computer Science, and a principal investigator in the Geometric Data Processing Group.

Guiding the lines

Many modern tools used to model 3-D shapes directly from artist sketches, including Bessmeltsev’s previous research projects, require vectorizing the drawings first. Automated vectorization “never worked for me, so I got frustrated,” he says. Those tools, he says, are fine for rough alignments but aren’t designed for precision: “Imagine you’re an animator and you drew a couple frames of animation. They’re pretty clean sketches, and you want to edit or color them on a computer. For that, you really care how well your vectorization aligns with your pencil drawing.”

Many errors, he noted, come from misalignment between the original and vectorized image at junctions where two curves meet — in a type of “X” junction — and where one line ends at another — in a “T” junction. Previous research and software used models incapable of aligning the curves at those junctions, so Bessmeltsev and Solomon took on the task.

The key innovation came from using frame fields to guide tracing. Frame fields assign two directions to each point of a 2-D or 3-D shape. These directions overlay a basic structure, or topology, that can guide geometric tasks in computer graphics. Frame fields have been used, for instance, to restore destroyed historical documents and to convert triangle meshes — networks of triangles covering a 3-D shape — into quadrangle meshes — grids of four-sided shapes. Quad meshes are commonly used to create computer-generated characters in movies and video games, and for computer-aided design (CAD) for better real-world design and simulation.

Bessmeltsev, for the first time, applied frame fields to image vectorization. His frame fields assign two directions to every dark pixel on an image. This keeps track of the tangent directions — where a curve meets a line — of nearby drawn curves. That means, at every intersection of a drawing, the two directions of the frame field align with the directions of the intersecting curves. This drastically reduces the roughness, or noise, surrounding intersections, which usually makes them difficult to trace.

“At a junction, all you have to do is follow one direction of the frame field and you get a smooth curve. You do that for every junction, and all junctions will then be aligned properly,” Bessmeltsev says.

Cleaner vectorization

When given an input of a pixeled raster 2-D drawing with one color per pixel, the tool assigns each dark pixel a cross that indicates two directions. Starting at some pixel, it first chooses a direction to trace. Then, it traces the vector path along the pixels, following the directions. After tracing, the tool creates a graph capturing connections between the solid strokes in the drawn image. Using this graph, the tool matches the necessary lines and curves to those strokes and automatically vectorizes the image.

In their paper, the researchers demonstrated their tool on various sketches, such as cartoon animals, people, and plants. The tool cleanly vectorized all intersections that were traced incorrectly using traditional tools. With traditional tools, for instance, lines around facial features, such as eyes and teeth, didn’t stop where the original lines did or ran through other lines.

One example in the paper shows pixels making up two slightly curved lines leading to the tip of a hat worn by a cartoon elephant. There’s a sharp corner where the two lines meet. Each dark pixel contains a cross that’s straight or slightly slanted, depending on the curvature of the line. Using those cross directions, the traced line could easily follow as it swooped around the sharp turn.

“Many artists still enjoy and prefer to work with real media (for example, pen, pencil, and paper). … The problem is that the scanning of such content into the computer often results in a severe loss of information,” says Nathan Carr, a principal researcher in computer graphics at Adobe Systems Inc., who was not involved in the research. “[The MIT] work relies on a mathematical construct known as ‘frame fields,’ to clean up and disambiguate scanned sketches to gain back this loss of information. It’s a great application of using mathematics to facilitate the artistic workflow in a clean well-formed manner. In summary, this work is important, as it aids in the ability for artists to transition between the physical and digital realms.”

Next, the researchers plan to augment the tool with a temporal-coherence technique, which extracts key information from adjacent animation frames. The idea would be to vectorize the frames simultaneously, using information from one to adjust the line tracing on the next, and vice versa. “Knowing the sketches don’t change much between the frames, the tool could improve the vectorization by looking at both at the same time,” Bessmeltsev says.

Smoothing out sketches’ rough edges syndicated from https://osmowaterfilters.blogspot.com/

0 notes