Delineating trees in noisy 2D images and 3D image-stacks

Abstract

We present a novel approach to fully automated delineation of tree structures in noisy 2D images and 3D image stacks. Unlike earlier methods that rely mostly on local evidence, our method builds a set of candidate trees over many different subsets of points likely to belong to the final one and then chooses the best one according to a global objective function. Since we are not systematically trying to span all nodes, our algorithm is able to eliminate noise while retaining the right tree structure. Manually annotated dendrite micrographs and retinal scans are used to evaluate the performance of our method, which is shown to be able to reject noise while retaining the tree structure.

Reconstructing Geometrically Consistent Tree Structures from Noisy Images

“…In earlier work [1], we showed that robustness could be improved by exploiting the global tree topology early in the algorithm. However, this method suffers from the fact that the tree-growing algorithm it uses makes all its decisions based on local image evidence without regard to tree shape.…”

A Guided Tour of Selected Image Processing and Analysis Methods for Fluorescence and Electron Microscopy

“…With a set of points available to trace, graph based algorithms are then used with the seeds as nodes of the graph, to reconstruct the neuronal tree. Such semi-automatic algorithms [294]- [296] provide useful means for neural structure segmentation due to their speed and accuracy. However, it is argued that optimal seed point selection is difficult to automate and while human assisted methods can improve accuracy, such methods require significant technician labor.…”

Simultaneous correspondence and non-rigid 3D reconstruction of the coronary tree from single X-ray images

“…Note that this task is by itself an active area of research within medical imaging [4,7,20]. Yet, we design relatively simple solutions, partially based on the popular vessel enhancement filter proposed in [6], which although not being free of error, demonstrate the robustness of our algorithm for 3D non-rigid reconstruction.…”