Search Results for author: Daniel Truhn

Found 31 papers, 22 papers with code

Radiomic Feature Stability Analysis based on Probabilistic Segmentations

no code implementations13 Oct 2019 Christoph Haarburger, Justus Schock, Daniel Truhn, Philippe Weitz, Gustav Mueller-Franzes, Leon Weninger, Dorit Merhof

From these segmentations, we extract a high number of plausible feature vectors for each lung tumor and analyze feature variance with respect to the segmentations.

feature selection Segmentation

An Asymmetric Cycle-Consistency Loss for Dealing with Many-to-One Mappings in Image Translation: A Study on Thigh MR Scans

no code implementations23 Apr 2020 Michael Gadermayr, Maximilian Tschuchnig, Laxmi Gupta, Dorit Merhof, Nils Krämer, Daniel Truhn, Burkhard Gess

Generative adversarial networks using a cycle-consistency loss facilitate unpaired training of image-translation models and thereby exhibit a very high potential in manifold medical applications.

Translation

Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization

1 code implementation25 Nov 2020 Tianyu Han, Sven Nebelung, Federico Pedersoli, Markus Zimmermann, Maximilian Schulze-Hagen, Michael Ho, Christoph Haarburger, Fabian Kiessling, Christiane Kuhl, Volkmar Schulz, Daniel Truhn

Contrary to previous research on adversarially trained models, we found that the accuracy of such models was equal to standard models when sufficiently large datasets and dual batch norm training were used.

Decision Making

What Does DALL-E 2 Know About Radiology?

no code implementations27 Sep 2022 Lisa C. Adams, Felix Busch, Daniel Truhn, Marcus R. Makowski, Hugo JWL. Aerts, Keno K. Bressem

Generative models such as DALL-E 2 could represent a promising future tool for image generation, augmentation, and manipulation for artificial intelligence research in radiology provided that these models have sufficient medical domain knowledge.

Zero-Shot Text-to-Image Generation

Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation

1 code implementation7 Nov 2022 Firas Khader, Gustav Mueller-Franzes, Soroosh Tayebi Arasteh, Tianyu Han, Christoph Haarburger, Maximilian Schulze-Hagen, Philipp Schad, Sandy Engelhardt, Bettina Baessler, Sebastian Foersch, Johannes Stegmaier, Christiane Kuhl, Sven Nebelung, Jakob Nikolas Kather, Daniel Truhn

Furthermore, we demonstrate that synthetic images can be used in a self-supervised pre-training and improve the performance of breast segmentation models when data is scarce (dice score 0. 91 vs. 0. 95 without vs. with synthetic data).

Computed Tomography (CT) Denoising +3

MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data

no code implementations14 Apr 2023 Tianyu Han, Lisa C. Adams, Jens-Michalis Papaioannou, Paul Grundmann, Tom Oberhauser, Alexander Löser, Daniel Truhn, Keno K. Bressem

As large language models (LLMs) like OpenAI's GPT series continue to make strides, we witness the emergence of artificial intelligence applications in an ever-expanding range of fields.

Transformers for CT Reconstruction From Monoplanar and Biplanar Radiographs

no code implementations11 May 2023 Firas Khader, Gustav Müller-Franzes, Tianyu Han, Sven Nebelung, Christiane Kuhl, Johannes Stegmaier, Daniel Truhn

X-rays are widely available and even if the CT reconstructed from these radiographs is not a replacement of a complete CT in the diagnostic setting, it might serve to spare the patients from radiation where a CT is only acquired for rough measurements such as determining organ size.

Computed Tomography (CT)

Cascaded Cross-Attention Networks for Data-Efficient Whole-Slide Image Classification Using Transformers

no code implementations11 May 2023 Firas Khader, Jakob Nikolas Kather, Tianyu Han, Sven Nebelung, Christiane Kuhl, Johannes Stegmaier, Daniel Truhn

However, while the conventional transformer allows for a simultaneous processing of a large set of input tokens, the computational demand scales quadratically with the number of input tokens and thus quadratically with the number of image patches.

Image Classification whole slide images

Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy

1 code implementation10 Jun 2023 Soroosh Tayebi Arasteh, Mahshad Lotfinia, Teresa Nolte, Marwin Saehn, Peter Isfort, Christiane Kuhl, Sven Nebelung, Georgios Kaissis, Daniel Truhn

We specifically investigate the performance of models trained with DP as compared to models trained without DP on data from institutions that the model had not seen during its training (i. e., external validation) - the situation that is reflective of the clinical use of AI models.

Domain Generalization Fairness +4

Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images

2 code implementations15 Aug 2023 Soroosh Tayebi Arasteh, Leo Misera, Jakob Nikolas Kather, Daniel Truhn, Sven Nebelung

In this study, we explored if SSL for pre-training on non-medical images can be applied to chest radiographs and how it compares to supervised pre-training on non-medical images and on medical images.

Medical Diagnosis Medical Image Classification +1

Large Language Models Streamline Automated Machine Learning for Clinical Studies

1 code implementation27 Aug 2023 Soroosh Tayebi Arasteh, Tianyu Han, Mahshad Lotfinia, Christiane Kuhl, Jakob Nikolas Kather, Daniel Truhn, Sven Nebelung

A knowledge gap persists between machine learning (ML) developers (e. g., data scientists) and practitioners (e. g., clinicians), hampering the full utilization of ML for clinical data analysis.

Mind the Gap: Federated Learning Broadens Domain Generalization in Diagnostic AI Models

1 code implementation1 Oct 2023 Soroosh Tayebi Arasteh, Christiane Kuhl, Marwin-Jonathan Saehn, Peter Isfort, Daniel Truhn, Sven Nebelung

So far, the impact of training strategy, i. e., local versus collaborative, on the diagnostic on-domain and off-domain performance of AI models interpreting chest radiographs has not been assessed.

Domain Generalization Federated Learning +2

A Good Feature Extractor Is All You Need for Weakly Supervised Pathology Slide Classification

1 code implementation20 Nov 2023 Georg Wölflein, Dyke Ferber, Asier Rabasco Meneghetti, Omar S. M. El Nahhas, Daniel Truhn, Zunamys I. Carrero, David J. Harrison, Ognjen Arandjelović, Jakob N. Kather

We question this belief in the context of weakly supervised whole slide image classification, motivated by the emergence of powerful feature extractors trained using self-supervised learning on diverse pathology datasets.

Benchmarking Image Classification +2

From Text to Image: Exploring GPT-4Vision's Potential in Advanced Radiological Analysis across Subspecialties

no code implementations24 Nov 2023 Felix Busch, Tianyu Han, Marcus Makowski, Daniel Truhn, Keno Bressem, Lisa Adams

The study evaluates and compares GPT-4 and GPT-4Vision for radiological tasks, suggesting GPT-4Vision may recognize radiological features from images, thereby enhancing its diagnostic potential over text-based descriptions.

LongHealth: A Question Answering Benchmark with Long Clinical Documents

1 code implementation25 Jan 2024 Lisa Adams, Felix Busch, Tianyu Han, Jean-Baptiste Excoffier, Matthieu Ortala, Alexander Löser, Hugo JWL. Aerts, Jakob Nikolas Kather, Daniel Truhn, Keno Bressem

However, all models struggled significantly in tasks requiring the identification of missing information, highlighting a critical area for improvement in clinical data interpretation.

Information Retrieval Multiple-choice +2

Cannot find the paper you are looking for? You can Submit a new open access paper.