AutoTT: Automated Detection and Analysis of T-Tubule Architecture in Cardiomyocytes

Cardiac transverse (T)-tubules provide a specialized structure for synchronization and stabilization of sarcoplasmic reticulum Ca2+ release in healthy cardiomyocytes. The application of laser scanning confocal microscopy and the use of fluorescent lipophilic membrane dyes have boosted the discoveries that T-tubule remodeling is a significant factor contributing to cardiac contractile dysfunction. However, the analysis and quantification of the remodeling of T-tubules have been a challenge and remain inconsistent among different research laboratories. Fast Fourier transformation (FFT) is the major analysis method applied to calculate the spatial frequency spectrum, which is used to represent the regularity of T-tubule systems. However, this approach is flawed because the density of T-tubules as well as non-T-tubule signals in the images influence the spectrum power generated by FFT. Preprocessing of images and topological architecture extracting is necessary to remove non-T-tubule noise from the analysis. In addition, manual analysis of images is time consuming and prone to errors and investigator bias. Therefore, we developed AutoTT, an automated analysis program that incorporates image processing, morphological feature extraction, and FFT analysis of spectrum power. The underlying algorithm is implemented in MATLAB (The Math Works, Natick, MA). The program outputs the densities of transversely oriented T-tubules and longitudinally oriented T-tubules, power spectrum of the overall T-tubule systems, and averaged spacing of T-tubules. We also combined the density and regularity of T-tubules to give an index of T-tubule integrity (TTint), which provides a global evaluation of T-tubule alterations. In summary, AutoTT provides a reliable, easy to use, and fast approach for analyzing myocyte T-tubules. This program can also be applied to measure the density and integrity of other cellular structures.