Corresponding author der OTH Regensburg
Refine
Year of publication
- 2018 (4) (remove)
Document Type
- Article (4)
Language
- English (4)
Has Fulltext
- no (4) (remove)
Is part of the Bibliography
- no (4)
Keywords
Institute
- Fakultät Elektro- und Informationstechnik (2)
- Fakultät Informatik und Mathematik (2)
- Fakultät Maschinenbau (1)
- Labor Biofluidmechanik (1)
- Labor Intelligente Materialien und Strukturen (1)
- Mechatronics Research Unit (MRU) (1)
- Regensburg Center of Biomedical Engineering - RCBE (1)
- Regensburg Medical Image Computing (ReMIC) (1)
Begutachtungsstatus
- peer-reviewed (4)
It is shown that the critical exponent for the effective shear modulus of a composite medium where a compliant polymer matrix is filled with ferromagnetic particles may significantly depend on the external magnetic field. The physical consequence of this dependence is the critical behavior of the relative magnetorheological effect.
In this paper, we consider the reconstruction problem of photoacoustic tomography (PAT) with a flat observation surface. We develop a direct reconstruction method that employs regularization with wavelet sparsity constraints. To that end, we derive a wavelet-vaguelette decomposition (WVD) for the PAT forward operator and a corresponding explicit reconstruction formula in the case of exact data. In the case of noisy data, we combine the WVD reconstruction formula with soft-thresholding, which yields a spatially adaptive estimation method. We demonstrate that our method is statistically optimal for white random noise if the unknown function is assumed to lie in any Besov-ball. We present generalizations of this approach and, in particular, we discuss the combination of PAT-vaguelette soft-thresholding with a total variation (TV) prior. We also provide an efficient implementation of the PAT-vaguelette transform that leads to fast image reconstruction algorithms supported by numerical results.
Purpose
Age-related macular degeneration (AMD) is a common threat to vision. While classification of disease stages is critical to understanding disease risk and progression, several systems based on color fundus photographs are known. Most of these require in-depth and time-consuming analysis of fundus images. Herein, we present an automated computer-based classification algorithm.
Design Algorithm development for AMD classification based on a large collection of color fundus images. Validation is performed on a cross-sectional, population-based study.
Participants.
We included 120 656 manually graded color fundus images from 3654 Age-Related Eye Disease Study (AREDS) participants. AREDS participants were >55 years of age, and non-AMD sight-threatening diseases were excluded at recruitment. In addition, performance of our algorithm was evaluated in 5555 fundus images from the population-based Kooperative Gesundheitsforschung in der Region Augsburg (KORA; Cooperative Health Research in the Region of Augsburg) study.
Methods.
We defined 13 classes (9 AREDS steps, 3 late AMD stages, and 1 for ungradable images) and trained several convolution deep learning architectures. An ensemble of network architectures improved prediction accuracy. An independent dataset was used to evaluate the performance of our algorithm in a population-based study.
Main Outcome Measures.
κ Statistics and accuracy to evaluate the concordance between predicted and expert human grader classification.
Results.
A network ensemble of 6 different neural net architectures predicted the 13 classes in the AREDS test set with a quadratic weighted κ of 92% (95% confidence interval, 89%–92%) and an overall accuracy of 63.3%. In the independent KORA dataset, images wrongly classified as AMD were mainly the result of a macular reflex observed in young individuals. By restricting the KORA analysis to individuals >55 years of age and prior exclusion of other retinopathies, the weighted and unweighted κ increased to 50% and 63%, respectively. Importantly, the algorithm detected 84.2% of all fundus images with definite signs of early or late AMD. Overall, 94.3% of healthy fundus images were classified correctly.
Conclusions
Our deep learning algoritm revealed a weighted κ outperforming human graders in the AREDS study and is suitable to classify AMD fundus images in other datasets using individuals >55 years of age.
Objective:
Magneto-active Polymers (MAP) are smart materials whose mechanical characteristics, such as elastic and shear moduli, may be controllable by means of an externally applied magnetic field.
Methods:
Various additives may be used to influence the characteristics of the polymer matrix whilst a suspension of soft and/or hard magnetic particles determine the magnetic properties of the composite. Both pre-cure and post-cure magnetization is possible.
Results:
A range of control strategies have been investigated for evaluation of the system using fluids of differing kinematic viscosity.
Conclusion:
Depending on the degree of magnetic field homogeneity, magneto-deformation and magnetostriction contribute to MAP actuation. This paper presents a novel application in the form of a peristaltic MAP tube system, applicable to flow control and pumping of hemorheological fluids in blood circulatory systems for biomedical research purposes.