Patient-Specific Semi-Supervised Learning for Postoperative Brain Tumor Segmentation

In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor segmentation has been rarely approached so far. We present a fully-automatic segmentation method using multimodal magnetic resonance image data and patient-specific semi-supervised learning. The idea behind our semi-supervised approach is to effectively fuse information from both pre- and postoperative image data of the same patient to improve segmentation of the postoperative image. We pose image segmentation as a classification problem and solve it by adopting a semi-supervised decision forest. The method is evaluated on a cohort of 10 high-grade glioma patients, with segmentation performance and computation time comparable or superior to a state-of-the-art brain tumor segmentation method. Moreover, our results confirm that the inclusion of preoperative MR images lead to a better performance regarding postoperative brain tumor segmentation.

Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

Sparse computation for large-scale binary classification

Well-known data mining algorithms rely on inputs in the form of pairwise similarities between objects. For large datasets it is computationally impossible to perform all pairwise comparisons. We therefore propose a novel approach that uses approximate Principal Component Analysis to efficiently identify groups of similar objects. The effectiveness of the approach is demonstrated in the context of binary classification using the supervised normalized cut as a classifier. For large datasets from the UCI repository, the approach significantly improves run times with minimal loss in accuracy.

Synthesis of Semi-Natural Grassland Vegetation of a Biogeographically Heterogeneous Area: Mesophilous Species-Rich Meadows in Switzerland

For a hundred years semi-natural species-rich meadow vegetation has been described from various areas of Switzerland. The first description dates from 1892 by Stebler and Schröter. In the present study, relevés of 65 semi-natural mesophilous meadow associations and communities reported by 26 authors, which were collected throughout the century, are summarized. An increasing number of descriptions dating from the 1980s and 1990s is included. A numerical classification of these 65 types resulted in four main groups of meadow-types. When compared with the existing literature of alliances a high correlation is found with the Polygono-Trisetion Br.-Bl. et R. Tx. ex Marshall 1947, the Arrhenatherion W. Koch 1926, the Agrostio-Festucion Puscaru et al. 1956, the Mesobromion Br.-Bl. et Moor 1938 em. Oberdorfer 1957, and with the Chrysopogonetum W. Koch 1943. The Agrostio-Festucion is characteristic for the montane belt in southern Switzerland and was until recently poorly known. This alliance is discussed in detail. Some classifications of meadow types by the original authors had to be rearranged for the present purpose. The present classification coincides well with the one Stebler and Schröter gave in 1892. Today, after a century of intensive changes in land use, their four main types are still valid.