RATS: Rapid Automatic Tissue Segmentation in rodent brain MRI

RATS is a rapid, robust and highly accurate algorithm for the skull-stripping of the rodent brain from MRI data. To download RATS, please go to the downloads page. For questions on using the software, please visit the FAQ page.

rats-pipeline.jpeg

The RATS algorithm consists of two stages. First, a mathematical morphology pipeline is used to create a rough segmentation. This is used for building a graph for a LOGISMOS-based approach for final segmentation. 

rats-olfBulbGraph.jpeg

Evaluation on T1-weighted rat brain MRI (left) and T2-weighted mouse brain MRI (right) show that RATS is significantly more accurate than existing methods such as pulse-coupled neural networks (PCNN) and atlas-based tissue classifiers. RATS is also significantly faster than these alternative methods, with a run time under 2 minutes.

rats-rat3d.jpeg

For additional details, please refer to:

  • Oguz I, Zhang H, Rumple A, Sonka M. RATS: Rapid Automatic Tissue Segmentation in rodent brain MRI. Journal of neuroscience methods (2014) vol. 221 pp. 175 - 182. (link)

  • Yin Y, Zhang X, Williams R, Wu X, Anderson D, Sonka M. LOGISMOS - Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces: cartilage segmentation in the knee joint. IEEE Transactions on Medical Imaging (2010) vol. 29 (12) pp. 2023-37. (link)

Development was supported, in part, by NIH-NIBIB R01-EB044640.