We present ilastik, an easy-to-use interactive tool that brings machine-learning-based (bio)image analysis to end users without substantial computational expertise. It contains pre-defined workflows for image segmentation, object classification, counting and tracking. Users adapt the workflows to the problem at hand by interactively providing sparse training annotations for a nonlinear classifier. ilastik can process data in up to five dimensions (3D, time and number of channels). Its computational back end runs operations on-demand wherever possible, allowing for interactive prediction on data larger than RAM. Once the classifiers are trained, ilastik workflows can be applied to new data from the command line without further user interaction. We describe all ilastik workflows in detail, including three case studies and a discussion on the expected performance. machine learning | image analysis | software

No abstract

Recently, unsupervised image segmentation has become increasingly popular. Starting from a superpixel segmentation, an edge-weighted region adjacency graph is constructed. Amongst all segmentations of the graph, the one which best conforms to the given image evidence, as measured by the sum of cut edge weights, is chosen.Since this problem is NP-hard, we propose a new approximate solver based on the move-making paradigm: first, the graph is recursively partitioned into small regions (cut phase). Then, for any two adjacent regions, we consider alternative cuts of these two regions defining possible moves (glue & cut phase). For planar problems, the optimal move can be found, whereas for non-planar problems, efficient approximations exist.We evaluate our algorithm on published and new benchmark datasets, which we make available here. The proposed algorithm finds segmentations that, as measured by a loss function, are as close to the ground-truth as the global optimum found by exact solvers. It does so significantly faster then existing approximate methods, which is important for large-scale problems.

No abstract

Percutaneous radiofrequency ablation (RFA) is becoming a standard minimally invasive clinical procedure for the treatment of liver tumors. However, planning the applicator placement such that the malignant tissue is completely destroyed, is a demanding task that requires considerable experience. In this work, we present a fast GPU-based real-time approximation of the ablation zone incorporating the cooling effect of liver vessels. Weighted distance fields of varying RF applicator types are derived from complex numerical simulations to allow a fast estimation of the ablation zone. Furthermore, the heat-sink effect of the cooling blood flow close to the applicator's electrode is estimated by means of a preprocessed thermal equilibrium representation of the liver parenchyma and blood vessels. Utilizing the graphics card, the weighted distance field incorporating the cooling blood flow is calculated using a modular shader framework, which facilitates the real-time visualization of the ablation zone in projected slice views and in volume rendering. The proposed methods are integrated in our software assistant prototype for planning RFA therapy. The software allows the physician to interactively place virtual RF applicator models. The real-time visualization of the corresponding approximated ablation zone facilitates interactive evaluation of the tumor coverage in order to optimize the applicator's placement such that all cancer cells are destroyed by the ablation.