TY - CHAP A1 - Rosbach, Emely A1 - Ammeling, Jonas A1 - Krügel, Sebastian A1 - Kießig, Angelika A1 - Fritz, Alexis A1 - Ganz, Jonathan A1 - Puget, Chloé A1 - Donovan, Taryn A1 - Klang, Andrea A1 - Köller, Maximilian C. A1 - Bolfa, Pompei A1 - Tecilla, Marco A1 - Denk, Daniela A1 - Kiupel, Matti A1 - Paraschou, Georgios A1 - Kok, Mun Keong A1 - Haake, Alexander F. H. A1 - de Krijger, Ronald R. A1 - Sonnen, Andreas F.-P. A1 - Kasantikul, Tanit A1 - Dorrestein, Gerry M. A1 - Smedley, Rebecca C. A1 - Stathonikos, Nikolas A1 - Uhl, Matthias A1 - Bertram, Christof A1 - Riener, Andreas A1 - Aubreville, Marc ED - Yamashita, Naomi ED - Evers, Vanessa ED - Yatani, Koji ED - Ding, Xianghua ED - Lee, Bongshin ED - Chetty, Marshini ED - Toups-Dugas, Phoebe T1 - "When Two Wrongs Don't Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology T2 - CHI'25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems N2 - Artificial intelligence (AI)-based decision support systems hold promise for enhancing diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration can introduce and amplify cognitive biases, like confirmation bias caused by false confirmation when erroneous human opinions are reinforced by inaccurate AI output. This bias may increase under time pressure, a ubiquitous factor in routine pathology, as it strains practitioners’ cognitive resources. We quantified confirmation bias triggered by AI-induced false confirmation and examined the role of time constraints in a web-based experiment, where trained pathology experts (n=28) estimated tumor cell percentages. Our results suggest that AI integration fuels confirmation bias, evidenced by a statistically significant positive linear-mixed-effects model coefficient linking AI recommendations mirroring flawed human judgment and alignment with system advice. Conversely, time pressure appeared to weaken this relationship. These findings highlight potential risks of AI in healthcare and aim to support the safe integration of clinical decision support systems. UR - https://doi.org/10.1145/3706598.3713319 Y1 - 2025 UR - https://doi.org/10.1145/3706598.3713319 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-58797 SN - 979-8-4007-1394-1 PB - ACM CY - New York ER - TY - INPR A1 - Rosbach, Emely A1 - Ammeling, Jonas A1 - Krügel, Sebastian A1 - Kießig, Angelika A1 - Fritz, Alexis A1 - Ganz, Jonathan A1 - Puget, Chloé A1 - Donovan, Taryn A1 - Klang, Andrea A1 - Köller, Maximilian C. A1 - Bolfa, Pompei A1 - Tecilla, Marco A1 - Denk, Daniela A1 - Kiupel, Matti A1 - Paraschou, Georgios A1 - Kok, Mun Keong A1 - Haake, Alexander F. H. A1 - de Krijger, Ronald R. A1 - Sonnen, Andreas F.-P. A1 - Kasantikul, Tanit A1 - Dorrestein, Gerry M. A1 - Smedley, Rebecca C. A1 - Stathonikos, Nikolas A1 - Uhl, Matthias A1 - Bertram, Christof A1 - Riener, Andreas A1 - Aubreville, Marc T1 - "When TwoWrongs Don’t Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology UR - https://doi.org/10.48550/arXiv.2411.01007 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2411.01007 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Rosbach, Emely A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Riener, Andreas A1 - Aubreville, Marc T1 - Automation Bias in AI-Assisted Medical Decision-Making under Time Pressure in Computational Pathology UR - https://doi.org/10.48550/arXiv.2411.00998 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2411.00998 ER - TY - CHAP A1 - Manger, Carina A1 - Vogl, Annalena A1 - Rosbach, Emely A1 - Ziegler, Carina A1 - Riener, Andreas T1 - Automation's Not Perfect But Neither Are We: Unveiling Illusionary Control And Automation Bias In Automated Driving T2 - 15th International ACM Conference on Automotive User Interfaces: Adjunct Conference Proceedings UR - https://doi.org/10.1145/3581961.3609897 KW - Automated Driving KW - Cognitive Biases KW - User Study KW - Illusionary Control KW - Automation Bias Y1 - 2023 UR - https://doi.org/10.1145/3581961.3609897 SN - 979-8-4007-0112-2 SP - 25 EP - 29 PB - ACM CY - New York ER - TY - CHAP A1 - Hoffer, Sabrina A1 - Lell, Alice A1 - Maral, Muhammed A1 - Rosbach, Emely A1 - Reuter, Hannah A1 - Muhammad, Muhammad A1 - Talabani-Durmus, Larin A1 - Ziegler, Carina A1 - Peintner, Jakob A1 - Riener, Andreas ED - Hirsch, L. ED - Kurz, M. ED - Wagener, N. T1 - HapTech: Intelligent controls in public spaces through mid-air haptic interaction T2 - Mensch und Computer 2023 – Workshopband UR - https://doi.org/10.18420/muc2023-mci-src-404 Y1 - 2023 UR - https://doi.org/10.18420/muc2023-mci-src-404 PB - Gesellschaft für Informatik e.V. CY - Bonn ER - TY - THES A1 - Rosbach, Emely T1 - On the influence of explainable AI and time pressure on confirmation bias in digital pathology N2 - The rapid development of artificial intelligence (AI) in recent years has opened the door to its employment for life-saving applications in the medical field. In particular, the increasing prevalence of AI in diagnostic pathology holds the potential to enhance diagnostic accuracy and provide more efficient patient care. While explainability is often identified as a crucial component in terms of safety and AI acceptance for future clinical use, it may also introduce or strengthen human cognitive biases such as the confirmation bias. Confirmation Bias describes the selective search for and intake of information to strengthen prior existing beliefs, which could be further amplified by the time pressure ubiquitously present in everyday pathology. To date, very few user-centric studies have been carried out in this domain, thus this thesis seeks to empirically examine the effects of explainable AI and time pressure on confirmation bias during the interaction with clinical decision support systems in a mixed-method study and aims to contribute to the safe and efficient development and design of intelligent support systems in the medical sector. Y1 - 2024 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-47445 CY - Ingolstadt ER - TY - INPR A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification N2 - Foundation models (FMs), i.e., models trained on a vast amount of typically unlabeled data, have become popular and available recently for the domain of histopathology. The key idea is to extract semantically rich vectors from any input patch, allowing for the use of simple subsequent classification networks potentially reducing the required amounts of labeled data, and increasing domain robustness. In this work, we investigate to which degree this also holds for mitotic figure classification. Utilizing two popular public mitotic figure datasets, we compared linear probing of five publicly available FMs against models trained on ImageNet and a simple ResNet50 end-to-end-trained baseline. We found that the end-to-end-trained baseline outperformed all FM-based classifiers, regardless of the amount of data provided. Additionally, we did not observe the FM-based classifiers to be more robust against domain shifts, rendering both of the above assumptions incorrect. UR - https://doi.org/10.48550/arXiv.2412.06365 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2412.06365 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59672 PB - arXiv CY - Ithaca ER - TY - INPR 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 T2 - Research Square 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/10.21203/rs.3.rs-4900505/v1 Y1 - 2024 UR - https://doi.org/10.21203/rs.3.rs-4900505/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-57630 SN - 2693-5015 PB - Research Square CY - Durham ER - 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 - CHAP A1 - Rosbach, Emely A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Riener, Andreas A1 - Aubreville, Marc ED - Palm, Christoph ED - Breininger, Katharina ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Tolxdorff, Thomas T1 - Automation Bias in AI-assisted Medical Decision-making under Time Pressure in Computational Pathology T2 - Bildverarbeitung für die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09–11, 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_27 Y1 - 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_27 SN - 978-3-658-47422-5 SP - 129 EP - 134 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Palm, Christoph ED - Breininger, Katharina ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Tolxdorff, Thomas T1 - Is Self-supervision Enough? BT - Benchmarking Foundation Models Against End-to-end Training for Mitotic Figure Classification T2 - Bildverarbeitung für die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09–11, 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 Y1 - 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 SN - 978-3-658-47422-5 SP - 63 EP - 68 PB - Springer Vieweg CY - Wiesbaden ER - TY - INPR 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 UR - https://doi.org/10.48550/arXiv.2508.04441 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2508.04441 PB - arXiv CY - Ithaca 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 -