Abstract.Recently there is much interest in moving objects databases, and data models and query languages have been proposed offering data types such as moving point and moving region together with suitable operations. In contrast to most earlier work on spatio-temporal databases, a moving region can change its shape and extent not only in discrete steps, but continuously. Examples of such moving regions are oil spills, forest fires, hurricanes, schools of fish, spreads of diseases, or armies, to name but a few.Whereas the database will contain a "temporally complete" representation of a moving region in the sense that for any instant of time the current extent and shape can be retrieved, the original information about the object moving around in the real world will most likely be a series of observations ("snapshots"). We consider the problem of constructing the complete moving region representation from a series of snapshots. We assume a model where a region is represented as a set of polygons with polygonal holes. A moving region is represented as a set of slices with disjoint time intervals, such that within each slice it is a region whose vertices move linearly with time. Snapshots are also given as sets of polygons with polygonal holes. We develop algorithms to interpolate between two snapshots, going from simple convex polygons to arbitrary polygons. The implementation is available on the Web.

No abstract

The most common type of bladder cancer is urothelial carcinoma, which is among the cancer types with the highest recurrence rate and lifetime treatment cost per patient. Diagnosed patients are stratified into risk groups, mainly based on grade and stage. However, it is well known that correct grading of bladder cancer suffers from intra-and interobserver variability and inconsistent reproducibility between pathologists, potentially leading to under-or overtreatment of the patients. The economic burden, unnecessary patient suffering, and additional load on the health care system illustrate the importance of developing new tools to aid pathologists. We propose a pipeline, called TRI grade , that will identify diagnostic relevant regions in the whole-slide image (WSI) and collectively predict the grade of the current WSI. The system consists of two main models, trained on weak slide-level grade labels. First, a WSI is segmented into the different tissue classes (urothelium, stroma, muscle, blood, damaged tissue, and background). Next, tiles are extracted from the diagnostic relevant urothelium tissue from three magnification levels (25x, 100x, and 400x) and processed sequentially by a convolutional neural network (CNN) based model. Ten models were trained for the slide-level grading experiment, where the best model achieved an F1-score of 0.90 on a test set consisting of 50 WSIs. The best model was further evaluated on a smaller segmentation test set, consisting of 14 WSIs where low-and high-grade regions were annotated by a pathologist. The TRI grade pipeline achieved an average F1-score of 0.91 for both the low-grade and high-grade classes.INDEX TERMS Automated cancer grading, bladder cancer, convolutional neural networks, multiscale classification, urothelial carcinoma, weakly labelled data, whole-slide image.

No abstract

No abstract