Learning-based ventricle detection from cardiac MR and CT images

The authors describe a technique that is reliable, adaptive, and versatile to solve the problem of region detection for a relatively wide class of medical images. Learning is essential in approaching this objective. In order to fully use the properties of the medical images and obtain a high efficiency, the authors compute a binary visual attention map which contains the region of interest as well as other things. Motivated by the analytical result of their em Bell image intensity model, they define critical points in the histogram of the intensity distribution and use them as candidates for threshold which in turn is used to obtain the attention map. The learning takes places in two stages: (i) learning for automatic selection of threshold values; (ii) learning for automatic selection of the region of interest from candidate regions in the attention map. The result from the second stage is evaluated based on a learned cost measure and the outcome is fed back to the first stage when necessary. This feedback enhances the reliability of the entire system. Experiments have been conducted to approximately locate the endocardium boundaries of the left and right ventricles from gradient-echo MR images. Cardiac CT images have also be used for testing