Jan Luts

Bio: Jan Luts is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Support vector machine & Semiparametric regression. The author has an hindex of 18, co-authored 45 publications receiving 1369 citations. Previous affiliations of Jan Luts include University of Technology, Sydney & The Catholic University of America.

Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy.

Abstract: Justification Automatic brain tumor classification by MRS has been under development for more than a decade. Nonetheless, to our knowledge, there are no published evaluations of predictive models with unseen cases that are subsequently acquired in different centers. The multicenter eTUMOUR project (2004–2009), which builds upon previous expertise from the INTERPRET project (2000–2002) has allowed such an evaluation to take place.

Clinical implications of intra- and interobserver reproducibility of transvaginal sonographic measurement of gestational sac and crown-rump length at 6-9 weeks' gestation.

Abstract: Objectives To assess intra- and interobserver agreement of routinely performed measurements – crown–rump length (CRL) and mean gestational sac diameter (MSD) – for assessing the likelihood of miscarriage in the first trimester of pregnancy using transvaginal sonography. Methods A cross-sectional study of CRL and gestational sac measurements in first-trimester pregnancies was conducted in a fetal medicine referral center with a predominantly Caucasian population. Gestational age ranged from 6 to 9 weeks. All patients underwent a transvaginal ultrasound examination using a highresolution ultrasound machine. Two measurements of CRL and measurements of three diameters of the gestational sac were obtained by two observers. Agreement within and between observers for CRL and between observers for MSD was analyzed using 95% prediction intervals, Bland–Altman plots with 95% limits of agreement and the intraclass correlation coefficient (ICC). Results In total 54 patients were included in the study, with measurements obtained by both observers in 44 of these. Intra- and interobserver ICCs were high for CRL measurements, with values of 0.992 and 0.993 for intraobserver agreement and 0.993 for interobserver agreement. For the MSD, the interobserver ICC was 0.952. Limits of agreement were ± 8.91 and ± 11.37% for intraobserver agreement of CRL and ± 14.64% for interobserver agreement of CRL. For MSD, the interobserver limits of agreement were ± 18.78%. For an MSD measurement of 20 mm by the first observer, the prediction interval for the second observer was 16.8–24.5 mm. For a CRL measurement of 6 mm, the prediction interval for the second observer was 5.4–6.7 mm. Conclusion For dating purposes, there is reasonable reproducibility of CRL measurements using transvaginal ultrasonography at 6–9 weeks’ gestation. When diagnosing miscarriage based on measurements of CRL care must be taken for values close to any decision boundary. The higher interobserver variability that we observed for MSD has implications for the diagnosis of miscarriage based on this measurement in the absence of a visible embryo or yolk sac. Copyright  2011 ISUOG. Published by John Wiley & Sons, Ltd.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Variational Inference: A Review for Statisticians

Abstract: One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation involving the posterior density. In this article, we review variational inference (VI), a method from machine learning that approximates probability densities through optimization. VI has been used in many applications and tends to be faster than classical methods, such as Markov chain Monte Carlo sampling. The idea behind VI is to first posit a family of densities and then to find a member of that family which is close to the target density. Closeness is measured by Kullback–Leibler divergence. We review the ideas behind mean-field variational inference, discuss the special case of VI applied to exponential family models, present a full example with a Bayesian mixture of Gaussians, and derive a variant that uses stochastic optimization to scale up to massive data...

Variational Inference: A Review for Statisticians

Abstract: One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation involving the posterior density. In this paper, we review variational inference (VI), a method from machine learning that approximates probability densities through optimization. VI has been used in many applications and tends to be faster than classical methods, such as Markov chain Monte Carlo sampling. The idea behind VI is to first posit a family of densities and then to find the member of that family which is close to the target. Closeness is measured by Kullback-Leibler divergence. We review the ideas behind mean-field variational inference, discuss the special case of VI applied to exponential family models, present a full example with a Bayesian mixture of Gaussians, and derive a variant that uses stochastic optimization to scale up to massive data. We discuss modern research in VI and highlight important open problems. VI is powerful, but it is not yet well understood. Our hope in writing this paper is to catalyze statistical research on this class of algorithms.