MIT Researchers Build Machine Learning Model that Quickly Generates Brain Scan Templates to Aid Diagnosis

In many cases, analysis requires use of a common image template, called an “atlas,” that’s an average representation of a given patient population. Atlases serve as a reference for comparison, for example to identify clinically significant changes in brain structures over time. However, building a template is a time-consuming, laborious process, often taking days or weeks to generate, especially when using 3D brain scans. To save time, researchers often download publicly available atlases previously generated by research groups, although these fail to fully capture the diversity of individual datasets or specific subpopulations, such as those with new diseases or from young children. Ultimately, the atlas cannot be smoothly mapped onto outlier images, producing poor results.

The MIT researchers devised an automated machine-learning model that generates “conditional” atlases based on specific patient attributes, such as age, sex, and disease. By leveraging shared information from across an entire dataset, the model can also synthesize atlases from patient subpopulations that may be completely missing in the dataset. The researchers hope clinicians can use the model to build their own atlases quickly from their own, potentially small datasets.

“The world needs more atlases,” says first author Adrian Dalca, a former postdoc in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and now a faculty member in radiology at Harvard Medical School and Massachusetts General Hospital. “Atlases are central to many medical image analyses. This method can build a lot more of them and build conditional ones as well.”

Related Links:
Massachusetts Institute of Technology