Search

Your search keyword '"Attenberger, Ulrike"' showing total 1,018 results
Start Over Author "Attenberger, Ulrike"
1,018 results on '"Attenberger, Ulrike"'

1. Informed Deep Abstaining Classifier: Investigating noise-robust training for diagnostic decision support systems

Author

Schneider, Helen, Nowak, Sebastian, Parikh, Aditya, Layer, Yannik C., Theis, Maike, Block, Wolfgang, Sprinkart, Alois M., Attenberger, Ulrike, and Sifa, Rafet

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Image-based diagnostic decision support systems (DDSS) utilizing deep learning have the potential to optimize clinical workflows. However, developing DDSS requires extensive datasets with expert annotations and is therefore costly. Leveraging report contents from radiological data bases with Natural Language Processing to annotate the corresponding image data promises to replace labor-intensive manual annotation. As mining "real world" databases can introduce label noise, noise-robust training losses are of great interest. However, current noise-robust losses do not consider noise estimations that can for example be derived based on the performance of the automatic label generator used. In this study, we expand the noise-robust Deep Abstaining Classifier (DAC) loss to an Informed Deep Abstaining Classifier (IDAC) loss by incorporating noise level estimations during training. Our findings demonstrate that IDAC enhances the noise robustness compared to DAC and several state-of-the-art loss functions. The results are obtained on various simulated noise levels using a public chest X-ray data set. These findings are reproduced on an in-house noisy data set, where labels were extracted from the clinical systems of the University Hospital Bonn by a text-based transformer. The IDAC can therefore be a valuable tool for researchers, companies or clinics aiming to develop accurate and reliable DDSS from routine clinical data., Comment: This preprint has no post-submission improvements or corrections. The Version of Record of this contribution is published in the Neural Information Processing, ICONIP 2024 Proceedings

Published
2024

7. Efficient 3D affinely equivariant CNNs with adaptive fusion of augmented spherical Fourier-Bessel bases

Author

Zhao, Wenzhao, Albert, Steffen, Wichtmann, Barbara D., Maurer, Angelika, Attenberger, Ulrike, Zöllner, Frank G., and Hesser, Jürgen

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction. However, these networks, which rely on parameter sharing and discrete transformation groups, often underperform in modern deep neural network architectures for processing volumetric images, such as the common 3D medical images. To address these limitations, this paper presents an efficient non-parameter-sharing continuous 3D affine group equivariant neural network for volumetric images. This network uses an adaptive aggregation of Monte Carlo augmented spherical Fourier-Bessel filter bases to improve the efficiency and flexibility of 3D group equivariant CNNs for volumetric data. Unlike existing methods that focus only on angular orthogonality in filter bases, the introduced spherical Bessel Fourier filter base incorporates both angular and radial orthogonality to improve feature extraction. Experiments on four medical image segmentation datasets show that the proposed methods achieve better affine group equivariance and superior segmentation accuracy than existing 3D group equivariant convolutional neural network layers, significantly improving the training stability and data efficiency of conventional CNN layers (at 0.05 significance level). The code is available at https://github.com/ZhaoWenzhao/WMCSFB.

Published
2024

18. Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network

Author

Zhao, Wenzhao, Wichtmann, Barbara D., Albert, Steffen, Maurer, Angelika, Zöllner, Frank G., Attenberger, Ulrike, and Hesser, Jürgen

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Group-equivariant convolutional neural networks (G-CNN) heavily rely on parameter sharing to increase CNN's data efficiency and performance. However, the parameter-sharing strategy greatly increases the computational burden for each added parameter, which hampers its application to deep neural network models. In this paper, we address these problems by proposing a non-parameter-sharing approach for group equivariant neural networks. The proposed methods adaptively aggregate a diverse range of filters by a weighted sum of stochastically augmented decomposed filters. We give theoretical proof about how the continuous group convolution can be approximated by our methods. Our method applies to both continuous and discrete groups, where the augmentation is implemented using Monte Carlo sampling and bootstrap resampling, respectively. We demonstrate that our methods serve as an efficient extension of standard CNN. Experiments on group equivariance tests show how our methods can achieve superior performance to parameter-sharing group equivariant networks. Experiments on image classification and image denoising tasks show that in certain scenarios, with a suitable set of filter bases, our method helps improve the performance of standard CNNs and build efficient lightweight image denoising networks. The code will be available at https://github.com/ZhaoWenzhao/MCG_CNN.

Published
2023

21. Improving Chest X-Ray Classification by RNN-based Patient Monitoring

Author

Biesner, David, Schneider, Helen, Wulff, Benjamin, Attenberger, Ulrike, and Sifa, Rafet

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition
Abstract

Chest X-Ray imaging is one of the most common radiological tools for detection of various pathologies related to the chest area and lung function. In a clinical setting, automated assessment of chest radiographs has the potential of assisting physicians in their decision making process and optimize clinical workflows, for example by prioritizing emergency patients. Most work analyzing the potential of machine learning models to classify chest X-ray images focuses on vision methods processing and predicting pathologies for one image at a time. However, many patients undergo such a procedure multiple times during course of a treatment or during a single hospital stay. The patient history, that is previous images and especially the corresponding diagnosis contain useful information that can aid a classification system in its prediction. In this study, we analyze how information about diagnosis can improve CNN-based image classification models by constructing a novel dataset from the well studied CheXpert dataset of chest X-rays. We show that a model trained on additional patient history information outperforms a model trained without the information by a significant margin. We provide code to replicate the dataset creation and model training., Comment: To be published in proceedings of IEEE International Conference on Machine Learning Applications IEEE ICMLA 2022

Published
2022

31. Symmetry-Aware Siamese Network: Exploiting Pathological Asymmetry for Chest X-Ray Analysis

Author

Schneider, Helen, Yildiz, Elif Cansu, Biesner, David, Layer, Yannik C., Wulff, Benjamin, Nowak, Sebastian, Theis, Maike, Sprinkart, Alois M., Attenberger, Ulrike I., Sifa, Rafet, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Iliadis, Lazaros, editor, Papaleonidas, Antonios, editor, Angelov, Plamen, editor, and Jayne, Chrisina, editor

Published
2023
Full Text
View/download PDF

36. How Controlled is the Expansion of VIATORR CX?

Author

Dell, Tatjana, Menne, Matthias, Wagenpfeil, Julia, Praktiknjo, Michael, Jansen, Christian, Isaak, Alexander, Mesropyan, Narine, Steinseifer, Ulrich, Attenberger, Ulrike, Luetkens, Julian, Meyer, Carsten, and Kuetting, Daniel

Published
2023
Full Text
View/download PDF

45. Women in radiology: gender diversity is not a metric—it is a tool for excellence

Author

Kubik-Huch, Rahel A, Vilgrain, Valérie, Krestin, Gabriel P, Reiser, Maximilian F, Attenberger, Ulrike I, Muellner, Ada U, Hess, Christopher P, and Hricak, Hedvig

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Behavioral and Social Science, Basic Behavioral and Social Science, Gender Equality, Female, Humans, Leadership, Physicians, Women, Radiologists, Radiology, Workforce, Mentoring, Nuclear Medicine & Medical Imaging, Clinical sciences
Abstract

Women in Focus: Be Inspired was a unique programme held at the 2019 European Congress of Radiology that was structured to address a range of topics related to gender and healthcare, including leadership, mentoring and the generational progression of women in medicine. In most countries, women constitute substantially fewer than half of radiologists in academia or private practice despite frequently accounting for at least half of medical school enrolees. Furthermore, the proportion of women decreases at higher academic ranks and levels of leadership, a phenomenon which has been referred to as a "leaky pipeline". Gender diversity in the radiologic workplace, including in academic and leadership positions, is important for the present and future success of the field. It is a tool for excellence that helps to optimize patient care and research; moreover, it is essential to overcome the current shortage of radiologists. This article reviews the current state of gender diversity in academic and leadership positions in radiology internationally and explores a wide range of potential reasons for gender disparities, including the lack of role models and mentorship, unconscious bias and generational changes in attitudes about the desirability of leadership positions. Strategies for both individuals and institutions to proactively increase the representation of women in academic and leadership positions are suggested. KEY POINTS: • Gender-diverse teams perform better. Thus, gender diversity throughout the radiologic workplace, including in leadership positions, is important for the current and future success of the field. • Though women now make up roughly half of medical students, they remain underrepresented among radiology trainees, faculty and leaders. • Factors leading to the gender gap in academia and leadership positions in Radiology include a lack of role models and mentors, unconscious biases, other societal barriers and generational changes.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results