Van Den Bosch T.,University Hospitals uven |
Van Den Bosch T.,University Hospitals Leuven |
Van Schoubroeck D.,University Hospitals uven |
Van Calster B.,ESAT SCD |
Timmerman D.,University Hospitals uven
Journal of Obstetrics and Gynaecology | Year: 2012
We evaluated the implementation of a strict procedure for endometrium biopsy, including pre-sampling ultrasound examination and assessment of the tissue yield during sampling, in 257 consecutive women with abnormal bleeding. The tissue yield was assessed during sampling and scored from 1 to 4. The median endometrial thickness as measured by ultrasound was 5.0 mm, 5.1 mm, 10.0 mm and 18.7 mm for a tissue yield score of 1, 2, 3 and 4, respectively. The median endometrial thickness at ultrasound and the median tissue yield score was 18.3 mm and score 4 in the endometrial cancer cases, compared with 3.9 mm and score 1, and 14.8 mm and score 3 in the case of endometrial atrophy and hyperplasia, respectively; and 11.5 mm and score 2 in endometrial polyp cases. Overall, 12 cancers were diagnosed. No endometrial cancer was diagnosed during follow-up (median 447 days). A strict office endometrial biopsy procedure contributes to the diagnostic reliability for intracavitary pathology. © 2012 Informa UK, Ltd.
Welkenhuysen M.,Catholic University of Leuven |
Andrei A.,Bioelectronics Systems Group |
Ameye L.,ESAT SCD |
Eberle W.,Bioelectronics Systems Group |
And 2 more authors.
IEEE Transactions on Biomedical Engineering | Year: 2011
In this study, the effect of insertion speed on long-term tissue response and insertion mechanics was investigated. A dummy silicon parylene-coated probe was used in this context and implanted in the rat brain at 10μm/s (n 6) or 100μm/s ( n 6) to a depth of 9mm. The insertion mechanics were assessed by the dimpling distance, and the force at the point of penetration, at the end of the insertion phase, and after a 3-min rest period in the brain. After 6 weeks, the tissue response was evaluated by estimating the amount of gliosis, inflammation, and neuronal cell loss with immunohistochemistry. No difference in dimpling, penetration force, or the force after a 3-min rest period in the brain was observed. However, the force at the end of the insertion phase was significantly higher when inserting the probes at 100μm/s compared to 10μm/s. Furthermore, an expected tissue response was seen with an increase of glial and microglial reactivity around the probe. This reaction was similar along the entire length of the probe. However, evidence for a neuronal kill zone was observed only in the most superficial part of the implant. In this region, the lesion size was also greatest. Comparison of the tissue response between insertion speeds showed no differences. © 2011 IEEE.
Bornigen D.,ESAT SCD |
Bornigen D.,Future Health |
Bornigen D.,Boston University |
Tranchevent L.-C.,ESAT SCD |
And 8 more authors.
Bioinformatics | Year: 2012
Motivation: Gene prioritization aims at identifying the most promising candidate genes among a large pool of candidates-so as to maximize the yield and biological relevance of further downstream validation experiments and functional studies. During the past few years, several gene prioritization tools have been defined, and some of them have been implemented and made available through freely available web tools. In this study, we aim at comparing the predictive performance of eight publicly available prioritization tools on novel data. We have performed an analysis in which 42 recently reported disease-gene associations from literature are used to benchmark these tools before the underlying databases are updated.Results: Cross-validation on retrospective data provides performance estimate likely to be overoptimistic because some of the data sources are contaminated with knowledge from disease-gene association. Our approach mimics a novel discovery more closely and thus provides more realistic performance estimates. There are, however, marked differences, and tools that rely on more advanced data integration schemes appear more powerful. © The Author 2012. Published by Oxford University Press. All rights reserved.
Mall R.,ESAT SCD |
Mehrkanoon S.,ESAT SCD |
Langone R.,ESAT SCD |
Suykens J.A.K.,ESAT SCD
Proceedings of the International Joint Conference on Neural Networks | Year: 2014
Kernel spectral clustering (KSC) solves a weighted kernel principal component analysis problem in a primal-dual optimization framework. It results in a clustering model using the dual solution of the problem. It has a powerful out-of-sample extension property leading to good clustering generalization w.r.t. the unseen data points. The out-of-sample extension property allows to build a sparse model on a small training set and introduces the first level of sparsity. The clustering dual model is expressed in terms of non-sparse kernel expansions where every point in the training set contributes. The goal is to find reduced set of training points which can best approximate the original solution. In this paper a second level of sparsity is introduced in order to reduce the time complexity of the computationally expensive out-of-sample extension. In this paper we investigate various penalty based reduced set techniques including the Group Lasso, L0, L1 L0 penalization and compare the amount of sparsity gained w.r.t. a previous L1 penalization technique. We observe that the optimal results in terms of sparsity corresponds to the Group Lasso penalization technique in majority of the cases. We showcase the effectiveness of the proposed approaches on several real world datasets and an image segmentation dataset. © 2014 IEEE.