215 citations · 505 across the 26 of their papers we have counts for
27 papers
Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants
Vaishnav Negi, Lev Sorokin, Soroosh Tayebi Arasteh +1
In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. Ensuring their reliability is…
FRAME: Separating sampling variation from performance disparities in medical image analysis
Mahshad Lotfinia, Daniel Truhn, Andreas Maier +1
Fairness audits of medical imaging models commonly report the largest performance difference between demographic subgroups and treat any positive value as evidence of bias. Yet a p…
CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging
Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn
In medical imaging, one frozen foundation encoder is often reused for many tasks. The encoder is usually chosen by the area under the receiver operating characteristic curve (AUROC…
Medical foundation models converge less under label supervision
Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia +4
Diagnostic classifiers and imaging biomarkers are fitted on the embeddings of medical foundation models. These models are replaced as new versions appear. This practice assumes tha…
The strength of clinical evidence is recoverable from language model representations but not from their stated grades
Soroosh Tayebi Arasteh
Large language models (LLMs) increasingly summarize clinical evidence, where a claim's weight depends on how strongly it is supported. Yet these models convey confidence poorly, an…
Vision-language models for chest radiography do not always need the image
Mahshad Lotfinia, Sebastian Ziegelmayer, Lisa Adams +4
Vision-language models that answer questions about chest radiographs are evaluated by their accuracy on labels derived from radiology reports. High benchmark accuracy is often inte…
Selective Linkage Precision for Released Medical Vision-Language Models
Soroosh Tayebi Arasteh, Mahshad Lotfinia, Sven Nebelung +1
Hospitals may release de-identified chest radiographs while restricting access to their reports. An attacker who already has reports from the same population and their metadata can…
Safety and accuracy follow different scaling laws in clinical large language models
Sebastian Wind, Tri-Thien Nguyen, Jeta Sopa +9
Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies…
Differential privacy representation geometry for medical image analysis
Soroosh Tayebi Arasteh, Marziyeh Mohammadi, Sven Nebelung +1
Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility loss unclear. We…
Automated grounding verification of AI statements about chest radiographs
Soroosh Tayebi Arasteh, Mehdi Joodaki, Mahshad Lotfinia +4
A grounding verifier checks a statement about a patient's image against the radiology report and the cited evidence. The state-of-the-art methods for testing these verifiers remove…
Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering
Mina Farajiamiri, Jeta Sopa, Saba Afza +9
Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. Thes…
The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis
Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia +7
Differential privacy limits how much each training image can influence a medical imaging model but lowers its diagnostic accuracy. Pretrained weights reduce this loss. It is unknow…
Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Soroosh Tayebi Arasteh, Mina Shaigan, Christiane Kuhl +3
Self-supervised learning (SSL) has improved visual representation learning, but its value in chest radiography remains uncertain. DINOv3 extends earlier SSL models through Gram-anc…
Perceptual implications of automatic anonymization in pathological speech
Soroosh Tayebi Arasteh, Saba Afza, Tri-Thien Nguyen +11
Automatic anonymization is increasingly used to enable ethical sharing of clinical speech, yet its perceptual and clinical consequences remain undercharacterized. We present a huma…
Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations
Mahshad Lotfinia, Arash Tayebiarasteh, Samaneh Samiei +2
Reliable artificial intelligence (AI) models for medical image analysis often depend on large and diverse labeled datasets. Federated learning (FL) offers a decentralized and priva…
Large Language Models Streamline Automated Machine Learning for Clinical Studies
Soroosh Tayebi Arasteh, Tianyu Han, Mahshad Lotfinia +4
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 da…
Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
Soroosh Tayebi Arasteh, Leo Misera, Jakob Nikolas Kather +2
Pre-training datasets, like ImageNet, have become the gold standard in medical image analysis. However, the emergence of self-supervised learning (SSL), which leverages unlabeled d…
Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy
Soroosh Tayebi Arasteh, Mahshad Lotfinia, Teresa Nolte +6
Developing robust and effective artificial intelligence (AI) models in medicine requires access to large amounts of patient data. The use of AI models solely trained on large multi…
Federated learning for secure development of AI models for Parkinson's disease detection using speech from different languages
Soroosh Tayebi Arasteh, Cristian David Rios-Urrego, Elmar Noeth +4
Parkinson's disease (PD) is a neurological disorder impacting a person's speech. Among automatic PD assessment methods, deep learning models have gained particular interest. Recent…
Fibroglandular Tissue Segmentation in Breast MRI using Vision Transformers -- A multi-institutional evaluation
Gustav Müller-Franzes, Fritz Müller-Franzes, Luisa Huck +9
Accurate and automatic segmentation of fibroglandular tissue in breast MRI screening is essential for the quantification of breast density and background parenchymal enhancement. I…
Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
Soroosh Tayebi Arasteh, Alexander Ziller, Christiane Kuhl +6
Artificial intelligence (AI) models are increasingly used in the medical domain. However, as medical data is highly sensitive, special precautions to ensure its protection are requ…
Medical Diagnosis with Large Scale Multimodal Transformers: Leveraging Diverse Data for More Accurate Diagnosis
Firas Khader, Gustav Mueller-Franzes, Tianci Wang +9
Multimodal deep learning has been used to predict clinical endpoints and diagnoses from clinical routine data. However, these models suffer from scaling issues: they have to learn…
Diffusion Probabilistic Models beat GANs on Medical Images
Gustav Müller-Franzes, Jan Moritz Niehues, Firas Khader +8
The success of Deep Learning applications critically depends on the quality and scale of the underlying training data. Generative adversarial networks (GANs) can generate arbitrary…
Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation
Firas Khader, Gustav Mueller-Franzes, Soroosh Tayebi Arasteh +12
Recent advances in computer vision have shown promising results in image generation. Diffusion probabilistic models in particular have generated realistic images from textual input…