Maaß, Peter
Lade...
10 Ergebnisse
Gerade angezeigt 1 - 10 von 10
- Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Deep learning detection of melanoma metastases in lymph nodes.(Elsevier, 2023-07); ; Background: In melanoma patients, surgical excision of the first draining lymph node, the sentinel lymph node (SLN), is a routine procedure to evaluate lymphogenic metastases. Metastasis detection by histopathological analysis assesses multiple tissue levels with hematoxylin and eosin and immunohistochemically stained glass slides. Considering the amount of tissue to analyze, the detection of metastasis can be highly time-consuming for pathologists. The application of artificial intelligence in the clinical routine has constantly increased over the past few years. Methods: In this multi-center study, a deep learning method was established on histological tissue sections of sentinel lymph nodes collected from the clinical routine. The algorithm was trained to highlight potential melanoma metastases for further review by pathologists, without relying on supplementary immunohistochemical stainings (e.g. anti-S100, anti-MelanA). Results: The established method was able to detect the existence of metastasis on individual tissue cuts with an area under the curve of 0.9630 and 0.9856 respectively on two test cohorts from different laboratories. The method was able to accurately identify tumour deposits>0.1 mm and, by automatic tumour diameter measurement, classify these into 0.1 mm to -1.0 mm and>1.0 mm groups, thus identifying and classifying metastasis currently relevant for assessing prognosis and stratifying treatment. Conclusions: Our results demonstrate that AI-based SLN melanoma metastasis detection has great potential and could become a routinely applied aid for pathologists. Our current study focused on assessing established parameters; however, larger future AI-based studies could identify novel biomarkers potentially further improving SLN-based prognostic and therapeutic predictions for affected patients.Wissenschaftlicher ArtikelBand:18849 56 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, A Deep Prior Approach to Magnetic Particle ImagingMagnetic particle imaging (MPI) is a tracer-based imaging modality with an increasing number of potential medical applications exploiting the nonlinear magnetization behavior of magnetic nanoparticles. The image reconstruction is obtained by solving an ill-posed inverse problem requiring regularization. The number of data-driven machine learning techniques applying to inverse problems is continuously increasing. While more classical regularization techniques, e.g., variational methods, are commonly used in MPI, we focus on a novel deep image prior (DIP) approach. Initially developed for image processing tasks, it has been shown to be applicable to inverse problems. In this work, we investigate the DIP approach in the context of MPI. Its behavior is illustrated and compared to standard reconstruction methods on a 2D phantom data set obtained from the Bruker preclinical MPI system.Konferenzbeitrag46 46 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Mathematical aspects of catalyst positioning in lithium/air batteries(IOP Publishing, 2020-02-25); ; ; In this paper we investigate a system of partial differential equations describing the clogging process of non-aqueous lithium/air batteries. The main aim is to optimize the positioning of catalysts on the surface of the pore of the battery in order to maximize the efficiency of the battery. To this end we analyze the parameter-to-state map which maps the initial catalyst positions cat0(x) to the diminishing radius of the pore until clogging. We obtain results on the continuity and Fréchet differentiability of the parameter-to-state map and we obtain the related sensitivity system. The paper also includes numerical experiments, which compare a greedy approach to catalyst positioning with results obtained by an analytic optimisation procedure.Wissenschaftlicher ArtikelBand:36Heft:423 21 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, A generalized conditional gradient method and its connection to an iterative shrinkage methodThis article combines techniques from two fields of applied mathematics: optimization theory and inverse problems. We investigate a generalized conditional gradient method and its connection to an iterative shrinkage method, which has been recently proposed for solving inverse problems. The iterative shrinkage method aims at the solution of non-quadratic minimization problems where the solution is expected to have a sparse representation in a known basis. We show that it can be interpreted as a generalized conditional gradient method. We prove the convergence of this generalized method for general class of functionals, which includes non-convex functionals. This also gives a deeper understanding of the iterative shrinkage method.Wissenschaftlicher ArtikelBand:42174 321 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Joint super-resolution image reconstruction and parameter identification in imaging operator: analysis of bilinear operator equations, numerical solution, and application to magnetic particle imagingOne important property of imaging modalities and related applications is the resolution of image reconstructions which relies on various factors such as instrumentation or data processing. Restrictions in resolution can have manifold origins, e.g., limited resolution of available data, noise level in the data, and/or inexact model operators. In this work we investigate a novel data processing approach suited for inexact model operators. Here, two different information sources, high-dimensional model information and high-quality measurement on a lower resolution, are comprised in a hybrid approach. The joint reconstruction of a high resolution image and parameters of the imaging operator are obtained by minimizing a Tikhonov-type functional. The hybrid approach is analyzed for bilinear operator equations with respect to stability, convergence, and convergence rates. We further derive an algorithmic solution exploiting an algebraic reconstruction technique. The study is complemented by numerical results ranging from an academic test case to image reconstruction in magnetic particle imaging.Wissenschaftlicher ArtikelBand:36Heft:1229 24 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Cross-Normalization of MALDI Mass Spectrometry Imaging Data Improves Site-to-Site Reproducibility(Elsevier, 2021-07-23); ; 18 24 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Applying an artificial intelligence deep learning approach to routine dermatopathological diagnosis of basal cell carcinoma.(Wiley, 2023-10-09); ; 51 40 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Singular Values for ReLU LayersDespite their prevalence in neural networks, we still lack a thorough theoretical characterization of rectified linear unit (ReLU) layers. This article aims to further our understanding of ReLU layers by studying how the activation function ReLU interacts with the linear component of the layer and what role this interaction plays in the success of the neural network in achieving its intended task. To this end, we introduce two new tools: ReLU singular values of operators and the Gaussian mean width of operators. By presenting, on the one hand, theoretical justifications, results, and interpretations of these two concepts and, on the other hand, numerical experiments and results of the ReLU singular values and the Gaussian mean width being applied to trained neural networks, we hope to give a comprehensive, singular-value-centric view of ReLU layers. We find that ReLU singular values and the Gaussian mean width do not only enable theoretical insights but also provide one with metrics that seem promising for practical applications. In particular, these measures can be used to distinguish correctly and incorrectly classified data as it traverses the network. We conclude by introducing two tools based on our findings: double layers and harmonic pruning.Wissenschaftlicher ArtikelBand:31Heft:937 36 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, DL4TO : A Deep Learning Library for Sample-Efficient Topology OptimizationWe present and publish the DL4TO software library – a Python library for three-dimensional topology optimization. The framework is based on PyTorch and allows easy integration with neural networks. The library fills a critical void in the current research toolkit on the intersection of deep learning and topology optimization. We present the structure of the library’s main components and how it enabled the incorporation of physics concepts into deep learning models.Konferenzbeitrag37 57 - Some of the metrics are blocked by yourconsent settings
Item-typ:Veröffentlichung, Trend-specific clustering for micro mass production of linked parts(Elsevier Science, 2018-07-10); ; ; ; In micro production, small tolerances, as well as size effects increase the requirement for a fast, precise, and reliable methodology that enhances the output of assemblies. In contrast to conventional approaches, a widening of the tolerance field enables an overall improvement of the output of a process chain while assuring functionality of parts. Therefore, the consideration of trends for building sections is essential for increasing the outcome by identifying sections that can be matched. This paper presents the Linked Parts Clustering Algorithm for the identification of trend-specific clusters in linked parts and demonstrates the area of application.Wissenschaftlicher ArtikelBand:67Heft:1112 117