Research Group Peter Schüffler

The fifth edition of the WHO classification of brain tumors increasingly emphasizes the role of extensive genetic testing in the diagnosis of gliomas. In this context, computational pathology foundation models (FMs) present a promising approach for inferring molecular entities directly from conventional, H&E-stained histological images, potentially reducing the need for genetic analysis. We conducted a robust investigation into the ability of five established FMs to generate effective embeddings for downstream glioma classification using three datasets (TCGA, n=839 samples; EBRAINS, n=786 samples; TUM, n=250 samples) and state-of-the-art augmentation techniques. Our results demonstrate that FM embeddings enable competitive glioma classification performance, even with limited training data, achieving one-vs-rest AUC0.93 on all three datasets. However, we observed substantial differences between FMs in their downstream performance, susceptibility to perturbations, and consistency across multiple datasets. Dataset diversity and content of central nervous tissue were associated with improved generalization, while model and dataset size were not. Common to all FMs was a propensity to capture dataset-specific features in their embeddings. We examined Macenko normalization and random convolutions as potential solutions to combat dataset-dominated embeddings and show that ensembling FM embeddings over multiple augmented views improves downstream classifier performance. In summary, our findings highlight both the promise and current limitations of computational pathology foundation models for glioma classification, emphasizing the critical roles of training data composition and downstream augmentation to achieve strong task performance.

Domain shift is a critical problem for pathology AI as pathology data is heavily influenced by center-specific conditions. Current pathology domain adaptation methods focus on image patches rather than WSI, thus failing to capture global WSI features required in typical clinical scenarios. In this work, we address the challenges of slide-level domain shift by proposing a Hierarchical Adaptation framework for Slide-level Domain-shift (HASD). HASD achieves multi-scale feature consistency and computationally efficient slide-level domain adaptation through two key components: (1) a hierarchical adaptation framework that integrates a Domain-level Alignment Solver for feature alignment, a Slide-level Geometric Invariance Regularization to preserve the morphological structure, and a Patch-level Attention Consistency Regularization to maintain local critical diagnostic cues; and (2) a prototype selection mechanism that reduces computational overhead. We validate our method on two slide-level tasks across five datasets, achieving a 4.1% AUROC improvement in a Breast Cancer HER2 Grading cohort and a 3.9% C-index gain in a UCEC survival prediction cohort. Our method provides a practical and reliable slide-level domain adaption solution for pathology institutions, minimizing both computational and annotation costs.

Cone Beam Computed Tomography (CBCT) is widely used in medical imaging. However, the limited number and intensity of X-ray projections make reconstruction an ill-posed problem with severe artifacts. NeRF-based methods have achieved great success in this task. However, they suffer from a local-global training mismatch between their two key components: the hash encoder and the neural network. Specifically, in each training step, only a subset of the hash encoder’s parameters is used (local sparse), whereas all parameters in the neural network participate (global dense). Consequently, hash features generated in each step are highly misaligned, as they come from different subsets of the hash encoder. These misalignments from different training steps are then fed into the neural network, causing repeated inconsistent global updates in training, which leads to unstable training, slower convergence, and degraded reconstruction quality. Aiming to alleviate the impact of this local-global optimization mismatch, we introduce a Normalized Hash Encoder, which enhances feature consistency and mitigates the mismatch. Additionally, we propose a Mapping Consistency Initialization(MCI) strategy that initializes the neural network before training by leveraging the global mapping property from a well-trained model. The initialized neural network exhibits improved stability during early training, enabling faster convergence and enhanced reconstruction performance. Our method is simple yet effective, requiring only a few lines of code while substantially improving training efficiency on 128 CT cases collected from 4 different datasets, covering 7 distinct anatomical regions.

Hematoxylin and eosin (H&E) staining is the clinical standard for assessing tissue morphology, but it lacks molecular-level diagnostic information. In contrast, immunohistochemistry (IHC) provides crucial insights into biomarker expression, such as HER2 status for breast cancer grading, but remains costly and time-consuming, limiting its use in time-sensitive clinical workflows. To address this gap, virtual staining from H&E to IHC has emerged as a promising alternative, yet faces two core challenges: (1) Lack of fair evaluation of synthetic images against misaligned IHC ground truths, and (2) preserving structural integrity and biological variability during translation. To this end, we present an end-to-end framework encompassing both generation and evaluation in this work. We introduce Star-Diff, a structure-aware staining restoration diffusion model that reformulates virtual staining as an image restoration task. By combining residual and noise-based generation pathways, Star-Diff maintains tissue structure while modeling realistic biomarker variability. To evaluate the diagnostic consistency of the generated IHC patches, we propose the Semantic Fidelity Score (SFS), a clinical-grading-task-driven metric that quantifies class-wise semantic degradation based on biomarker classification accuracy. Unlike pixel-level metrics such as SSIM and PSNR, SFS remains robust under spatial misalignment and classifier uncertainty. Experiments on the BCI dataset demonstrate that Star-Diff achieves state-of-the-art (SOTA) performance in both visual fidelity and diagnostic relevance. With rapid inference and strong clinical alignment,it presents a practical solution for applications such as intraoperative virtual IHC synthesis.

Neural Cellular Automata (NCA) offer a robust and interpretable approach to image classification, making them a promising choice for microscopy image analysis. However, a performance gap remains between NCA and larger, more complex architectures. We address this challenge by integrating attention pooling with NCA to enhance feature extraction and improve classification accuracy. The attention pooling mechanism refines the focus on the most informative regions, leading to more accurate predictions. We evaluate our method on eight diverse microscopy image datasets and demonstrate that our approach significantly outperforms existing NCA methods while remaining parameter-efficient and explainable. Furthermore, we compare our method with traditional lightweight convolutional neural network and vision transformer architectures, showing improved performance while maintaining a significantly lower parameter count. Our results highlight the potential of NCA-based models an alternative for explainable image classification.

Assessing climate-driven mortality risk has become an emerging area of research in recent decades. In this paper, we propose a novel approach to explicitly incorporate climate-driven effects into both single- and multi-population stochastic mortality models. The new model consists of two components: a stochastic mortality model, and a distributed lag non-linear model (DLNM). The first component captures the non-climate long-term trend and volatility in mortality rates. The second component captures non-linear and lagged effects of climate variables on mortality, as well as the impact of heat waves and cold waves across different age groups. For model calibration, we propose a backfitting algorithm that allows us to disentangle the climate-driven mortality risk from the non-climate-driven stochastic mortality risk. We illustrate the effectiveness and superior performance of our model using data from three European regions: Athens, Lisbon, and Rome. Furthermore, we utilize future UTCI data generated from climate models to provide mortality projections into 2045 across these regions under two Representative Concentration Pathway (RCP) scenarios. The projections show a noticeable decrease in winter mortality alongside a rise in summer mortality, driven by a general increase in UTCI over time. Although we expect slightly lower overall mortality in the short term under RCP8.5 compared to RCP2.6, a long-term increase in total mortality is anticipated under the RCP8.5 scenario.

Digital pathology offers a groundbreaking opportunity to transform clinical practice in histopathological image analysis, yet faces a significant hurdle: the substantial file sizes of pathological whole slide images (WSIs). Whereas current digital pathology solutions rely on lossy JPEG compression to address this issue, lossy compression can introduce color and texture disparities, potentially impacting clinical decision-making. Whereas prior research addresses perceptual image quality and downstream performance independently of each other, we jointly evaluate compression schemes for perceptual and downstream task quality on four different datasets. In addition, we collect an initially uncompressed dataset for an unbiased perceptual evaluation of compression schemes. Our results show that deep learning models fine-tuned for perceptual quality outperform conventional compression schemes like JPEG-XL or WebP for further compression of WSI. However, they exhibit a significant bias towards the compression artifacts present in the training data and struggle to generalize across various compression schemes. We introduce a novel evaluation metric based on feature similarity between original files and compressed files that aligns very well with the actual downstream performance on the compressed WSI. Our metric allows for a general and standardized evaluation of lossy compression schemes and mitigates the requirement to independently assess different downstream tasks. Our study provides novel insights for the assessment of lossy compression schemes for WSI and encourages a unified evaluation of lossy compression schemes to accelerate the clinical uptake of digital pathology.

Digital pathology is revolutionizing clinical diagnostics by offering enhanced efficiency, accuracy, and accessibility of pathological examinations. This study explores the implementation and validation of digital pathology in a large tertiary academic center, focusing on its gradual integration and transition into routine clinical diagnostics. In a comprehensive validation process over a 6-month period, we compared sign-out of digital and physical glass slides of a wide range of different tissue specimens and histopathological diagnoses. Key metrics such as diagnostic concordance and user satisfaction were assessed by involving the pathologists in a validation training and study phase. We measured turnaround times before and after transitioning to digital pathology to assess the impact on overall efficiency. Our results demonstrate a 99% concordance between the analog and digital reports while at the same time reducing the time to sign out a case by almost a minute, suggesting potential long-term efficiency gains. Our digital transition positively impacted our pathology workflow: Pathologists reported increased flexibility and satisfaction due to the ease of accessing and sharing digital slides. However, challenges were identified, including technical issues related to image quality and system integration. Lessons learned from this study emphasize the importance of robust training programs, adequate IT support, and ongoing evaluation to ensure successful integration. This validation study confirms that digital pathology is a viable and beneficial tool for accurate clinical routine diagnostics in large academic centers, offering insights for other institutions considering similar endeavors.

Processing histopathological Whole Slide Images (WSI) leads to massive storage requirements for clinics worldwide. Even after lossy image compression during image acquisition, additional lossy compression is frequently possible without substantially affecting the performance of deep learning-based (DL) downstream tasks. In this paper, we show that the commonly used JPEG algorithm is not best suited for further compression and we propose Stain Quantized Latent Compression (SQLC), a novel DL based histopathology data compression approach. SQLC compresses staining and RGB channels before passing it through a compression autoencoder (CAE) in order to obtain quantized latent representations for maximizing the compression. We show that our approach yields superior performance in a classification downstream task, compared to traditional approaches like JPEG, while image quality metrics like the Multi-Scale Structural Similarity Index (MS-SSIM) is largely preserved.

The incidence of colorectal cancer (CRC), one of the deadliest cancers around the world, is increasing. Tissue microenvironment (TME) features such as tumor-infiltrating lymphocytes (TILs) can have a crucial impact on diagnosis or decision-making for treating patients with CRC. While clinical studies showed that TILs improve the host immune response, leading to a better prognosis, inter-observer agreement for quantifying TILs is not perfect. Incorporating machine learning (ML) based applications in clinical routine may promote diagnosis reliability. Recently, ML has shown potential for making progress in routine clinical procedures. We aim to systematically review the TILs analysis based on ML in CRC histological images. Deep learning (DL) and non-DL techniques can aid pathologists in identifying TILs, and automated TILs are associated with patient outcomes. However, a large multi-institutional CRC dataset with a diverse and multi-ethnic population is necessary to generalize ML methods.

Künstliche Intelligenz verspricht viele Erneuerungen und Erleichterungen in der Pathologie, wirft jedoch ebenso viele Fragen und Ungewissheiten auf. In diesem Artikel geben wir eine kurze Übersicht über den aktuellen Stand, die bereits erreichten Ziele vorhandener Algorithmen und immer noch ausstehende Herausforderungen.