TY - JOUR A1 - Ganz, Jonathan A1 - Marzahl, Christian A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Richter, Barbara A1 - Puget, Chloé A1 - Denk, Daniela A1 - Demeter, Elena A. A1 - Tabaran, Flaviu A. A1 - Wasinger, Gabriel A1 - Lipnik, Karoline A1 - Tecilla, Marco A1 - Valentine, Matthew J. A1 - Dark, Michael A1 - Abele, Niklas A1 - Bolfa, Pompei A1 - Erber, Ramona A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Donovan, Taryn A1 - Jabari, Samir A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Information mismatch in PHH3-assisted mitosis annotation leads to interpretation shifts in H&E slide analysis JF - Scientific Reports N2 - The count of mitotic figures (MFs) observed in hematoxylin and eosin (H&E)-stained slides is an important prognostic marker, as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. In a computer-aided setting, deep learning algorithms can help to mitigate this, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithms’ performance. Unlike H&E, where identification of MFs is based mainly on morphological features, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H&E staining alone, the use of this ground truth could potentially introduce an interpretation shift and even label noise into the H&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. Subsequently, MF detectors, including a novel dual-stain detector, were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models’ performance. We found that the annotators’ object-level agreement significantly increased when using PHH3-assisted labeling (F1: 0.53 to 0.74). However, this enhancement in label consistency did not translate to improved performance for H&E-based detectors, neither during the training phase nor the evaluation phase. Conversely, the dual-stain detector was able to benefit from the higher consistency. This reveals an information mismatch between the H&E and PHH3-stained images as the cause of this effect, which renders PHH3-assisted annotations not well-aligned for use with H&E-based detectors. Based on our findings, we propose an improved PHH3-assisted labeling procedure. UR - https://doi.org/10.1038/s41598-024-77244-6 Y1 - 2024 UR - https://doi.org/10.1038/s41598-024-77244-6 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53559 SN - 2045-2322 VL - 14 IS - 1 PB - Springer Nature CY - London ER - TY - JOUR A1 - Aubreville, Marc A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Gehrke, Thomas A1 - Scherzad, Agmal A1 - Hackenberg, Stephan A1 - Goncalves, Miguel T1 - Prediction of tumor board procedural recommendations using large language models JF - European Archives of Oto-Rhino-Laryngology UR - https://doi.org/10.1007/s00405-024-08947-9 Y1 - 2024 UR - https://doi.org/10.1007/s00405-024-08947-9 SN - 1434-4726 SN - 0937-4477 VL - 282 IS - 3 SP - 1619 EP - 1629 PB - Springer CY - Berlin ER - TY - JOUR A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Benchmarking Foundation Models for Mitotic Figure Classification JF - Machine Learning for Biomedical Imaging N2 - The performance of deep learning models is known to scale with data quantity and diversity. In pathology, as in many other medical imaging domains, the availability of labeled images for a specific task is often limited. Self-supervised learning techniques have enabled the use of vast amounts of unlabeled data to train large-scale neural networks, i.e., foundation models, that can address the limited data problem by providing semantically rich feature vectors that can generalize well to new tasks with minimal training effort increasing model performance and robustness. In this work, we investigate the use of foundation models for mitotic figure classification. The mitotic count, which can be derived from this classification task, is an independent prognostic marker for specific tumors and part of certain tumor grading systems. In particular, we investigate the data scaling laws on multiple current foundation models and evaluate their robustness to unseen tumor domains. Next to the commonly used linear probing paradigm, we also adapt the models using low-rank adaptation (LoRA) of their attention mechanisms. We compare all models against end-to-end-trained baselines, both CNNs and Vision Transformers. Our results demonstrate that LoRA-adapted foundation models provide superior performance to those adapted with standard linear probing, reaching performance levels close to 100 % data availability with only 10 % of training data. Furthermore, LoRA-adaptation of the most recent foundation models almost closes the out-of-domain performance gap when evaluated on unseen tumor domains. However, full fine-tuning of traditional architectures still yields competitive performance. UR - https://doi.org/10.59275/j.melba.2026-a3eb Y1 - 2026 UR - https://doi.org/10.59275/j.melba.2026-a3eb UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-66220 SN - 2766-905X VL - 3 IS - MELBA–BVM 2025 Special Issue SP - 38 EP - 55 PB - Melba editors CY - [s. l.] ER - TY - JOUR A1 - Rosbach, Emely A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Bertram, Christof A1 - Conrad, Thomas A1 - Riener, Andreas A1 - Aubreville, Marc T1 - Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology JF - Machine Learning for Biomedical Imaging N2 - Artificial intelligence (AI)-driven clinical decision support systems (CDSS) hold promise to improve diagnostic accuracy and efficiency in computational pathology. However, collaboration between human experts and AI may give rise to cognitive biases, such as automation and anchoring bias, wherein users may be inclined to blindly adopt system recommendations or be disproportionately influenced by the presence of AI predictions, even when they are inaccurate. These biases may be exacerbated under time pressure, pervasive in routine pathology diagnostics, or shaped by individual user characteristics. To investigate these effects, we conducted a web-based experiment in which trained pathology experts (n = 28) estimated tumor cell percentages twice: once independently and once with the aid of an AI. A subset of the estimates in each condition was performed under time constraints. Our findings indicate that AI integration generally enhances diagnostic performance. However, it also introduced a 7% automation bias rate, quantified as the number of accepted negative consultations, where a previously correct independent assessment gets overturned by inaccurate AI guidance. While time pressure did not increase the frequency of automation bias occurrence, it appeared to intensify its severity, as evidenced by a performance decline linked to increased automation reliance under cognitive load. A linear mixed-effects model (LMM) analysis, simulating weighted averaging, revealed a statistically significant positive coefficient for AI advice, indicating a moderate degree of anchoring on system output. This effect was further intensified under time pressure, suggesting that anchoring bias may become more pronounced when cognitive resources are limited. A secondary LMM evaluation assessing automation reliance, used as a proxy for both automation and anchoring bias, demonstrated that professional experience and self-efficacy were associated with reduced dependence on system support, whereas higher confidence during AI-assisted decision-making was linked to increased automation reliance. Together, these findings underscore the dual nature of AI integration in clinical workflows, offering performance benefits while also introducing risks of cognitive bias–driven diagnostic errors. As an initial investigation focused on a single medical specialty and diagnostic task, this study aims to lay the groundwork for future research to explore these phenomena across diverse clinical contexts, ultimately supporting the establishment of appropriate reliance on automated systems and the safe, effective integration of human–AI collaboration in medical decision-making. UR - https://doi.org/10.59275/j.melba.2026-87b1 Y1 - 2026 UR - https://doi.org/10.59275/j.melba.2026-87b1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-67787 SN - 2766-905X VL - 3 IS - MELBA–BVM 2025 Special Issue SP - 126 EP - 147 PB - Melba editors CY - [s. l.] ER -