Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Öttl, Mathias"'
Recent advances in computer-aided diagnosis for histopathology have been largely driven by the use of deep learning models for automated image analysis. While these networks can perform on par with medical experts, their performance can be impeded by
Externí odkaz:
http://arxiv.org/abs/2409.09797
Autor:
Qiu, Jingna, Aubreville, Marc, Wilm, Frauke, Öttl, Mathias, Utz, Jonas, Schlereth, Maja, Breininger, Katharina
Acquiring annotations for whole slide images (WSIs)-based deep learning tasks, such as creating tissue segmentation masks or detecting mitotic figures, is a laborious process due to the extensive image size and the significant manual work involved in
Externí odkaz:
http://arxiv.org/abs/2407.06363
Autor:
Öttl, Mathias, Mei, Siyuan, Wilm, Frauke, Steenpass, Jana, Rübner, Matthias, Hartmann, Arndt, Beckmann, Matthias, Fasching, Peter, Maier, Andreas, Erber, Ramona, Breininger, Katharina
Denoising Diffusion Probabilistic models have become increasingly popular due to their ability to offer probabilistic modeling and generate diverse outputs. This versatility inspired their adaptation for image segmentation, where multiple predictions
Externí odkaz:
http://arxiv.org/abs/2403.14440
Autor:
Öttl, Mathias, Wilm, Frauke, Steenpass, Jana, Qiu, Jingna, Rübner, Matthias, Hartmann, Arndt, Beckmann, Matthias, Fasching, Peter, Maier, Andreas, Erber, Ramona, Kainz, Bernhard, Breininger, Katharina
Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for downstream tasks
Externí odkaz:
http://arxiv.org/abs/2403.14429
Autor:
Wilm, Frauke, Ammeling, Jonas, Öttl, Mathias, Fick, Rutger H. J., Aubreville, Marc, Breininger, Katharina
The U-net architecture has significantly impacted deep learning-based segmentation of medical images. Through the integration of long-range skip connections, it facilitated the preservation of high-resolution features. Out-of-distribution data can, h
Externí odkaz:
http://arxiv.org/abs/2402.08276
Autor:
Qiu, Jingna, Wilm, Frauke, Öttl, Mathias, Schlereth, Maja, Liu, Chang, Heimann, Tobias, Aubreville, Marc, Breininger, Katharina
The process of annotating histological gigapixel-sized whole slide images (WSIs) at the pixel level for the purpose of training a supervised segmentation model is time-consuming. Region-based active learning (AL) involves training the model on a limi
Externí odkaz:
http://arxiv.org/abs/2307.07168
Autor:
Wilm, Frauke, Fragoso, Marco, Bertram, Christof A., Stathonikos, Nikolas, Öttl, Mathias, Qiu, Jingna, Klopfleisch, Robert, Maier, Andreas, Breininger, Katharina, Aubreville, Marc
In histopathology, scanner-induced domain shifts are known to impede the performance of trained neural networks when tested on unseen data. Multi-domain pre-training or dedicated domain-generalization techniques can help to develop domain-agnostic al
Externí odkaz:
http://arxiv.org/abs/2301.04423
Autor:
Wilm, Frauke, Fragoso, Marco, Bertram, Christof A., Stathonikos, Nikolas, Öttl, Mathias, Qiu, Jingna, Klopfleisch, Robert, Maier, Andreas, Aubreville, Marc, Breininger, Katharina
Computer-aided systems in histopathology are often challenged by various sources of domain shift that impact the performance of these algorithms considerably. We investigated the potential of using self-supervised pre-training to overcome scanner-ind
Externí odkaz:
http://arxiv.org/abs/2211.16141
Autor:
Öttl, Mathias, Mönius, Jana, Rübner, Matthias, Geppert, Carol I., Qiu, Jingna, Wilm, Frauke, Hartmann, Arndt, Beckmann, Matthias W., Fasching, Peter A., Maier, Andreas, Erber, Ramona, Breininger, Katharina
Tumor segmentation in histopathology images is often complicated by its composition of different histological subtypes and class imbalance. Oversampling subtypes with low prevalence features is not a satisfactory solution since it eventually leads to
Externí odkaz:
http://arxiv.org/abs/2211.06150
Image annotation is one essential prior step to enable data-driven algorithms. In medical imaging, having large and reliably annotated data sets is crucial to recognize various diseases robustly. However, annotator performance varies immensely, thus
Externí odkaz:
http://arxiv.org/abs/2211.06146