Výsledky vyhledávání - "Hägele, Miriam"

Report

DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology

Autor: Aversa, Marco, Nobis, Gabriel, Hägele, Miriam, Standvoss, Kai, Chirica, Mihaela, Murray-Smith, Roderick, Alaa, Ahmed, Ruff, Lukas, Ivanova, Daniela, Samek, Wojciech, Klauschen, Frederick, Sanguinetti, Bruno, Oala, Luis

We present DiffInfinite, a hierarchical diffusion model that generates arbitrarily large histological images while preserving long-range correlation structural information. Our approach first generates synthetic segmentation masks, subsequently used

Externí odkaz: http://arxiv.org/abs/2306.13384

Zobrazit plný text záznamu

Report

Leveraging weak complementary labels to improve semantic segmentation of hepatocellular carcinoma and cholangiocarcinoma in H&E-stained slides

Autor: Hägele, Miriam, Eschrich, Johannes, Ruff, Lukas, Alber, Maximilian, Schallenberg, Simon, Guillot, Adrien, Roderburg, Christoph, Tacke, Frank, Klauschen, Frederick

In this paper, we present a deep learning segmentation approach to classify and quantify the two most prevalent primary liver cancers - hepatocellular carcinoma and intrahepatic cholangiocarcinoma - from hematoxylin and eosin (H&E) stained whole slid

Externí odkaz: http://arxiv.org/abs/2302.01813

Zobrazit plný text záznamu

Report

On the identification of the riskiest directional components from multivariate heavy-tailed data

Autor: Hägele, Miriam, Lehtomaa, Jaakko

Publikováno v: Risks 2023, 11, 130

In univariate data, there exist standard procedures for identifying dominating features that produce the largest observations. However, in the multivariate setting, the situation is quite different. This paper aims to provide tools and algorithms for

Externí odkaz: http://arxiv.org/abs/2112.05759

Zobrazit plný text záznamu

Report

Large deviations for a class of multivariate heavy-tailed risk processes used in insurance and finance

Autor: Hägele, Miriam, Lehtomaa, Jaakko

Publikováno v: J. Risk Financial Manag.2021,14, 202

Modern risk modelling approaches deal with vectors of multiple components. The components could be, for example, returns of financial instruments or losses within an insurance portfolio concerning different lines of business. One of the main problems

Externí odkaz: http://arxiv.org/abs/2103.11707

Zobrazit plný text záznamu

Report

Precise asymptotics of ruin probabilities for a class of multivariate heavy-tailed distributions

Autor: Hägele, Miriam

Publikováno v: Statistics & Probability Letters Volume 166, November 2020, 108871

This article studies asymptotic approximations of ruin probabilities of multivariate random walks with heavy-tailed increments. Under our assumptions, the distributions of the increments are closely connected to multivariate subexponentiality and adm

Externí odkaz: http://arxiv.org/abs/2005.12637

Zobrazit plný text záznamu

Report

Resolving challenges in deep learning-based analyses of histopathological images using explanation methods

Autor: Hägele, Miriam, Seegerer, Philipp, Lapuschkin, Sebastian, Bockmayr, Michael, Samek, Wojciech, Klauschen, Frederick, Müller, Klaus-Robert, Binder, Alexander

Publikováno v: Sci Rep 10, 6423 (2020)

Deep learning has recently gained popularity in digital pathology due to its high prediction quality. However, the medical domain requires explanation and insight for a better understanding beyond standard quantitative performance evaluation. Recentl

Externí odkaz: http://arxiv.org/abs/1908.06943

Zobrazit plný text záznamu

Report

iNNvestigate neural networks!

Autor: Alber, Maximilian, Lapuschkin, Sebastian, Seegerer, Philipp, Hägele, Miriam, Schütt, Kristof T., Montavon, Grégoire, Samek, Wojciech, Müller, Klaus-Robert, Dähne, Sven, Kindermans, Pieter-Jan

In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specialists can understand and analy

Externí odkaz: http://arxiv.org/abs/1808.04260

Zobrazit plný text záznamu

Report

Towards computational fluorescence microscopy: Machine learning-based integrated prediction of morphological and molecular tumor profiles

Autor: Binder, Alexander, Bockmayr, Michael, Hägele, Miriam, Wienert, Stephan, Heim, Daniel, Hellweg, Katharina, Stenzinger, Albrecht, Parlow, Laura, Budczies, Jan, Goeppert, Benjamin, Treue, Denise, Kotani, Manato, Ishii, Masaru, Dietel, Manfred, Hocke, Andreas, Denkert, Carsten, Müller, Klaus-Robert, Klauschen, Frederick

Recent advances in cancer research largely rely on new developments in microscopic or molecular profiling techniques offering high level of detail with respect to either spatial or molecular features, but usually not both. Here, we present a novel ma

Externí odkaz: http://arxiv.org/abs/1805.11178

Zobrazit plný text záznamu