Daniel Scholz

Aswathi Varma, Suprosanna Shit, Chinmay Prabhakar et al.

Vision Transformers (ViTs) have emerged as the state-of-the-art architecture in representation learning, leveraging self-attention mechanisms to excel in various tasks. ViTs split images into fixed-size patches, constraining them to a predefined size and necessitating pre-processing steps like resizing, padding, or cropping. This poses challenges in medical imaging, particularly with irregularly shaped structures like tumors. A fixed bounding box crop size produces input images with highly variable foreground-to-background ratios. Resizing medical images can degrade information and introduce artefacts, impacting diagnosis. Hence, tailoring variable-sized crops to regions of interest can enhance feature representation capabilities. Moreover, large images are computationally expensive, and smaller sizes risk information loss, presenting a computation-accuracy tradeoff. We propose VariViT, an improved ViT model crafted to handle variable image sizes while maintaining a consistent patch size. VariViT employs a novel positional embedding resizing scheme for a variable number of patches. We also implement a new batching strategy within VariViT to reduce computational complexity, resulting in faster training and inference times. In our evaluations on two 3D brain MRI datasets, VariViT surpasses vanilla ViTs and ResNet in glioma genotype prediction and brain tumor classification. It achieves F1-scores of 75.5% and 76.3%, respectively, learning more discriminative features. Our proposed batching strategy reduces computation time by up to 30% compared to conventional architectures. These findings underscore the efficacy of VariViT in image representation learning. Our code can be found here: https://github.com/Aswathi-Varma/varivit

Daniel Scholz, Benedikt Wiestler, Daniel Rueckert et al.

Image synthesis is increasingly being adopted in medical image processing, for example for data augmentation or inter-modality image translation. In these critical applications, the generated images must fulfill a high standard of biological correctness. A particular requirement for these images is global consistency, i.e an image being overall coherent and structured so that all parts of the image fit together in a realistic and meaningful way. Yet, established image quality metrics do not explicitly quantify this property of synthetic images. In this work, we introduce two metrics that can measure the global consistency of synthetic images on a per-image basis. To measure the global consistency, we presume that a realistic image exhibits consistent properties, e.g., a person's body fat in a whole-body MRI, throughout the depicted object or scene. Hence, we quantify global consistency by predicting and comparing explicit attributes of images on patches using supervised trained neural networks. Next, we adapt this strategy to an unlabeled setting by measuring the similarity of implicit image features predicted by a self-supervised trained network. Our results demonstrate that predicting explicit attributes of synthetic images on patches can distinguish globally consistent from inconsistent images. Implicit representations of images are less sensitive to assess global consistency but are still serviceable when labeled data is unavailable. Compared to established metrics, such as the FID, our method can explicitly measure global consistency on a per-image basis, enabling a dedicated analysis of the biological plausibility of single synthetic images.

Ayhan Can Erdur, Daniel Scholz, Jiazhen Pan et al.

State-of-the-art large language models (LLMs) show high performance in general visual question answering. However, a fundamental limitation remains: current architectures lack the native 3D spatial reasoning required for direct analysis of volumetric medical imaging, such as CT or MRI. Emerging agentic AI offers a new solution, eliminating the need for intrinsic 3D processing by enabling LLMs to orchestrate and leverage specialized external tools. Yet, the feasibility of such agentic frameworks in complex, multi-step radiological workflows remains underexplored. In this work, we present a training-free agentic pipeline for automated brain MRI analysis. Validating our methodology on several LLMs (GPT-5.1, Gemini 3 Pro, Claude Sonnet 4.5) with off-the-shelf domain-specific tools, our system autonomously executes complex end-to-end workflows, including preprocessing (skull stripping, registration), pathology segmentation (glioma, meningioma, metastases), and volumetric analysis. We evaluate our framework across increasingly complex radiological tasks, from single-scan segmentation and volumetric reporting to longitudinal response assessment requiring multi-timepoint comparisons. We analyze the impact of architectural design by comparing single-agent models against multi-agent "domain-expert" collaborations. Finally, to support rigorous evaluation of future agentic systems, we introduce and release a benchmark dataset of image-prompt-answer tuples derived from public BraTS data. Our results demonstrate that agentic AI can solve highly neuro-radiological image analysis tasks through tool use without the need for training or fine-tuning.

Ayhan Can Erdur, Daniel Scholz, Josef A. Buchner et al.

Brain metastases (BMs) are the most frequently occurring brain tumors. The treatment of patients having multiple BMs with stereo tactic radiosurgery necessitates accurate localization of the metastases. Neural networks can assist in this time-consuming and costly task that is typically performed by human experts. Particularly challenging is the detection of small lesions since they are often underrepresented in exist ing approaches. Yet, lesion detection is equally important for all sizes. In this work, we develop an ensemble of neural networks explicitly fo cused on detecting and segmenting small BMs. To accomplish this task, we trained several neural networks focusing on individual aspects of the BM segmentation problem: We use blob loss that specifically addresses the imbalance of lesion instances in terms of size and texture and is, therefore, not biased towards larger lesions. In addition, a model using a subtraction sequence between the T1 and T1 contrast-enhanced sequence focuses on low-contrast lesions. Furthermore, we train additional models only on small lesions. Our experiments demonstrate the utility of the ad ditional blob loss and the subtraction sequence. However, including the specialized small lesion models in the ensemble deteriorates segmentation results. We also find domain-knowledge-inspired postprocessing steps to drastically increase our performance in most experiments. Our approach enables us to submit a competitive challenge entry to the ASNR-MICCAI BraTS Brain Metastasis Challenge 2023.

Ayhan Can Erdur, Christian Beischl, Daniel Scholz et al.

Missing input sequences are common in medical imaging data, posing a challenge for deep learning models reliant on complete input data. In this work, inspired by MultiMAE [2], we develop a masked autoencoder (MAE) paradigm for multi-modal, multi-task learning in 3D medical imaging with brain MRIs. Our method treats each MRI sequence as a separate input modality, leveraging a late-fusion-style transformer encoder to integrate multi-sequence information (multi-modal) and individual decoder streams for each modality for multi-task reconstruction. This pretraining strategy guides the model to learn rich representations per modality while also equipping it to handle missing inputs through cross-sequence reasoning. The result is a flexible and generalizable encoder for brain MRIs that infers missing sequences from available inputs and can be adapted to various downstream applications. We demonstrate the performance and robustness of our method against an MAE-ViT baseline in downstream segmentation and classification tasks, showing absolute improvement of $10.1$ overall Dice score and $0.46$ MCC over the baselines with missing input sequences. Our experiments demonstrate the strength of this pretraining strategy. The implementation is made available.

Daniel Scholz, Ayhan Can Erdur, Viktoria Ehm et al.

Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness for multi-modal imaging tasks that are common in many medical fields, such as neurology and oncology. While supervised models perform well in this setting, they fail to leverage unlabeled datasets and struggle with missing modalities, a frequent challenge in clinical settings. To bridge these gaps, we introduce MM-DINOv2, a novel and efficient framework that adapts the pre-trained vision foundation model DINOv2 for multi-modal medical imaging. Our approach incorporates multi-modal patch embeddings, enabling vision foundation models to effectively process multi-modal imaging data. To address missing modalities, we employ full-modality masking, which encourages the model to learn robust cross-modality relationships. Furthermore, we leverage semi-supervised learning to harness large unlabeled datasets, enhancing both the accuracy and reliability of medical predictions. Applied to glioma subtype classification from multi-sequence brain MRI, our method achieves a Matthews Correlation Coefficient (MCC) of 0.6 on an external test set, surpassing state-of-the-art supervised approaches by +11.1%. Our work establishes a scalable and robust solution for multi-modal medical imaging tasks, leveraging powerful vision foundation models pre-trained on natural images while addressing real-world clinical challenges such as missing data and limited annotations.

Daniel Scholz, Ayhan Can Erdur, Robbie Holland et al.

Magnetic resonance imaging (MRI) is an invaluable tool for clinical and research applications. Yet, variations in scanners and acquisition parameters cause inconsistencies in image contrast, hindering data comparability and reproducibility across datasets and clinical studies. Existing scanner harmonization methods, designed to address this challenge, face limitations, such as requiring traveling subjects or struggling to generalize to unseen domains. We propose a novel approach using a conditioned diffusion autoencoder with a contrastive loss and domain-agnostic contrast augmentation to harmonize MR images across scanners while preserving subject-specific anatomy. Our method enables brain MRI synthesis from a single reference image. It outperforms baseline techniques, achieving a +7% PSNR improvement on a traveling subjects dataset and +18% improvement on age regression in unseen. Our model provides robust, effective harmonization of brain MRIs to target scanners without requiring fine-tuning. This advancement promises to enhance comparability, reproducibility, and generalizability in multi-site and longitudinal clinical studies, ultimately contributing to improved healthcare outcomes.