Zobrazeno 1 - 10
of 577
pro vyhledávání: '"Han Tianyu"'
Autor:
Müller-Franzes, Gustav, Khader, Firas, Siepmann, Robert, Han, Tianyu, Kather, Jakob Nikolas, Nebelung, Sven, Truhn, Daniel
MRI and CT are essential clinical cross-sectional imaging techniques for diagnosing complex conditions. However, large 3D datasets with annotations for deep learning are scarce. While methods like DINOv2 are encouraging for 2D image analysis, these m
Externí odkaz:
http://arxiv.org/abs/2411.15802
Autor:
Dorfner, Felix J., Dada, Amin, Busch, Felix, Makowski, Marcus R., Han, Tianyu, Truhn, Daniel, Kleesiek, Jens, Sushil, Madhumita, Lammert, Jacqueline, Adams, Lisa C., Bressem, Keno K.
Large language models (LLMs) have shown potential in biomedical applications, leading to efforts to fine-tune them on domain-specific data. However, the effectiveness of this approach remains unclear. This study evaluates the performance of biomedica
Externí odkaz:
http://arxiv.org/abs/2408.13833
Autor:
Han, Tianyu, Wang, Bo
Publikováno v:
IEEE Control Systems Letters, vol. 8, pp. 2469-2474, 2024
We present a safety-critical controller for the problem of stabilization for force-controlled nonholonomic mobile robots. The proposed control law is based on the constructions of control Lyapunov functions (CLFs) and control barrier functions (CBFs)
Externí odkaz:
http://arxiv.org/abs/2408.10941
Denoising diffusion models offer a promising approach to accelerating magnetic resonance imaging (MRI) and producing diagnostic-level images in an unsupervised manner. However, our study demonstrates that even tiny worst-case potential perturbations
Externí odkaz:
http://arxiv.org/abs/2406.16983
Autor:
Khader, Firas, Nahhas, Omar S. M. El, Han, Tianyu, Müller-Franzes, Gustav, Nebelung, Sven, Kather, Jakob Nikolas, Truhn, Daniel
The Transformer model has been pivotal in advancing fields such as natural language processing, speech recognition, and computer vision. However, a critical limitation of this model is its quadratic computational and memory complexity relative to the
Externí odkaz:
http://arxiv.org/abs/2406.01314
Autor:
Adams, Lisa, Busch, Felix, Han, Tianyu, Excoffier, Jean-Baptiste, Ortala, Matthieu, Löser, Alexander, Aerts, Hugo JWL., Kather, Jakob Nikolas, Truhn, Daniel, Bressem, Keno
Background: Recent advancements in large language models (LLMs) offer potential benefits in healthcare, particularly in processing extensive patient records. However, existing benchmarks do not fully assess LLMs' capability in handling real-world, le
Externí odkaz:
http://arxiv.org/abs/2401.14490
Publikováno v:
J Med Internet Res 2024;26:e54948
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.
Externí odkaz:
http://arxiv.org/abs/2311.14777
Autor:
Han, Tianyu, Žigutytė, Laura, Huck, Luisa, Huppertz, Marc, Siepmann, Robert, Gandelsman, Yossi, Blüthgen, Christian, Khader, Firas, Kuhl, Christiane, Nebelung, Sven, Kather, Jakob, Truhn, Daniel
Detecting misleading patterns in automated diagnostic assistance systems, such as those powered by Artificial Intelligence, is critical to ensuring their reliability, particularly in healthcare. Current techniques for evaluating deep learning models
Externí odkaz:
http://arxiv.org/abs/2309.17123
Autor:
Han, Tianyu, Nebelung, Sven, Khader, Firas, Wang, Tianci, Mueller-Franzes, Gustav, Kuhl, Christiane, Försch, Sebastian, Kleesiek, Jens, Haarburger, Christoph, Bressem, Keno K., Kather, Jakob Nikolas, Truhn, Daniel
Large language models (LLMs) have broad medical knowledge and can reason about medical information across many domains, holding promising potential for diverse medical applications in the near future. In this study, we demonstrate a concerning vulner
Externí odkaz:
http://arxiv.org/abs/2309.17007
Autor:
Arasteh, Soroosh Tayebi, Han, Tianyu, Lotfinia, Mahshad, Kuhl, Christiane, Kather, Jakob Nikolas, Truhn, Daniel, Nebelung, Sven
Publikováno v:
Nat Commun 15, 1603 (2024)
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. We investigated the potential of the ChatGPT Advanced Dat
Externí odkaz:
http://arxiv.org/abs/2308.14120