Publikationen

"When Two Wrongs Don t Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology

Rosbach, E. ., Ammeling, J. ., Krügel, S. ., Kießig, A. ., Fritz, A. ., Ganz, J. ., … Aubreville, M. . (2025). "When Two Wrongs Don t Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (S. 1–18). Yokohama Japan: ACM. http://doi.org/10.1145/3706598.3713319 (Original work published 2025)
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Abteilung/Einrichtung
  
  CIVU – Center for Interaction, Visualization and Usability
  
  FLAIR - Flensburg Artificial Intelligence Research
- Profilbereich
  
  Gesundheit und Life Sciences
- Forschungsfeld
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Automation Bias in AI-assisted Medical Decision-making under Time Pressure in Computational Pathology

Rosbach, E. ., Ganz, J. ., Ammeling, J. ., Riener, A. ., & Aubreville, M. . (2025). Automation Bias in AI-assisted Medical Decision-making under Time Pressure in Computational Pathology. Bildverarbeitung für die Medizin 2025. Wiesbaden: Springer Fachmedien Wiesbaden. (Original work published 2025)

Abstract

Artificial intelligence (AI)-based clinical decision support systems (CDSS) promise to enhance diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration might introduce automation bias, where users uncritically follow automated cues. This bias may worsen when time pressure strains practitioners’ cognitive resources. We quantified automation bias by measuring the adoption of negative system consultations and examined the role of time pressure in a web-based experiment, where trained pathology experts (n=28) estimated tumor cell percentages. Our results indicate that while AI integration led to a statistically significant increase in overall performance, it also resulted in a 7% automation bias rate, where initially correct evaluations were overturned by erroneous AI advice. Conversely, time pressure did not exacerbate automation bias occurrence, but appeared to increase its severity, evidenced by heightened reliance on the system’s negative consultations and subsequent performance decline. These findings highlight potential risks of AI use in healthcare. The final dataset (including a table with image patch details), participant demographics, and source code are available at: https://github.com/emelyrosbach/AB-TP.git
- Suche auf Google Scholar
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Abteilung/Einrichtung
  
  CIVU – Center for Interaction, Visualization and Usability
  
  FLAIR - Flensburg Artificial Intelligence Research
- Profilbereich
  
  Gesundheit und Life Sciences
- Forschungsfeld
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Is Self-supervision Enough?

Ganz, J. ", Ammeling, J. ., Rosbach, E. ., Lausser, L. ., Bertram, C. A., Breininger, K. ., & Aubreville, M. . (2025). Is Self-supervision Enough?. In "Bildverarbeitung für die Medizin 2025" (S. 63–68). "Wiesbaden": "Springer Fachmedien Wiesbaden".

Abstract

"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."
- Suche auf Google Scholar
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Forschungsprojekt
  
  Robust and Accurate Multi-Tumor, Multi-Species, Multi-Laboratory and Multi-Scanner Mitosis Detection with Large-Scale Datasets and Artificial Intelligence
- Abteilung/Einrichtung
  
  CIVU – Center for Interaction, Visualization and Usability
  
  FLAIR - Flensburg Artificial Intelligence Research
- Profilbereich
  
  Gesundheit und Life Sciences
- Forschungsfeld
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Comprehensive Dataset of Coarse Tumor Annotations for The Cancer Genome Atlas Breast Invasive Carcinoma

Banerjee, S. ", Bertram, C. A., Ammeling, J. ., Weiss, V. ., Conrad, T. ., Klopfleisch, R. ., … Aubreville, M. . (2025). Comprehensive Dataset of Coarse Tumor Annotations for The Cancer Genome Atlas Breast Invasive Carcinoma. In Bildverarbeitung für die Medizin 2025 (S. 260–265). Wiesbaden: Springer Fachmedien Wiesbaden. http://doi.org/10.1007/978-3-658-47422-5_56

Abstract

Automated tumor segmentation of histologic images is crucial for the development of computer-assisted diagnostic workflows aiming at accurate prognostication. We present a dataset of coarse annotations of over 1,000 highresolution breast tumor images from The cancer genome atlas breast invasive carcinoma (TCGA-BRCA) repository, each annotated with binary segmentation masks that delineate coarse tumor areas. Additionally, a subset of 20 images includes fine-grained annotations, providing precise delineation of tumor boundaries beyond the broader outlines used in coarse annotations. Initial evaluations using U-Net and DeepLabv3 models show promising segmentation performance. On a held-out, coarsely annotated test set, U-Net achieved an average intersection over union (IoU) score of 0.795, while DeepLabv3 scored 0.783. On the finely annotated subset of this test set, U-Net reached an average IoU of 0.746, with DeepLabv3 slightly outperforming at 0.765. The public availability of this dataset aims to support research in automated tumor analysis, advancing diagnostic workflows and thereby ultimately improving breast cancer management.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Forschungsprojekt
  
  Robust and Accurate Multi-Tumor, Multi-Species, Multi-Laboratory and Multi-Scanner Mitosis Detection with Large-Scale Datasets and Artificial Intelligence
- Abteilung/Einrichtung
  
  CIVU – Center for Interaction, Visualization and Usability
  
  FLAIR - Flensburg Artificial Intelligence Research
- Profilbereich
  
  Gesundheit und Life Sciences
- Forschungsfeld
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Investigation of Class Separability within Object Detection Models in Histopathology

Ammeling, J. ., Ganz, J. ., Wilm, F. ., Breininger, K. ., & Aubreville, M. . (2025). Investigation of Class Separability within Object Detection Models in Histopathology. IEEE Transactions on Medical Imaging, 1–1. http://doi.org/10.1109/TMI.2025.3560134
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Forschungsprojekt
  
  Robust and Accurate Multi-Tumor, Multi-Species, Multi-Laboratory and Multi-Scanner Mitosis Detection with Large-Scale Datasets and Artificial Intelligence
- Abteilung/Einrichtung
  
  FLAIR - Flensburg Artificial Intelligence Research
- Profilbereich
  
  Informatik und Gestaltung
- Forschungsfeld
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)

Bertram, C. A. ", Weiss, V. ., Donovan, T. A., Banerjee, S. ., Conrad, T. ., Ammeling, J. ., … Aubreville, M. . (2025). Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br). In "Bildverarbeitung für die Medizin 2025" (S. 113–118). "Wiesbaden": "Springer Fachmedien Wiesbaden".

Abstract

"Assessment of the density of mitotic figures (MFs) in histologic tumor sections is an important prognostic marker for many tumor types, including breast cancer. Recently, it has been reported in multiple works that the quantity of MFs with an atypical morphology (atypical MFs, AMFs) might be an independent prognostic criterion for breast cancer. AMFs are an indicator of mutations in the genes regulating the cell cycle and can lead to aberrant chromosome constitution (aneuploidy) of the tumor cells. To facilitate further research on this topic using pattern recognition, we present the first ever publicly available dataset of atypical and normal MFs (AMi-Br). For this, we utilized two of the most popular MF datasets (MIDOG 2021 and TUPAC) and subclassified all MFs using a three expert majority vote. Our final dataset consists of 3,720 MFs, split into 832 AMFs (22.4\%) and 2,888 normal MFs (77.6\%) across all 223 tumor cases in the combined set. We provide baseline classification experiments to investigate the consistency of the dataset, using a Monte Carlo cross-validation and different strategies to combat class imbalance.We found an averaged balanced accuracy of up to 0.806 when using a patch-level data set split, and up to 0.713 when using a patient-level split."
- Suche auf Google Scholar
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Forschungsprojekt
  
  Robust and Accurate Multi-Tumor, Multi-Species, Multi-Laboratory and Multi-Scanner Mitosis Detection with Large-Scale Datasets and Artificial Intelligence
- Abteilung/Einrichtung
  
  FLAIR - Flensburg Artificial Intelligence Research
  
  CIVU – Center for Interaction, Visualization and Usability
- Profilbereich
  
  Gesundheit und Life Sciences
- Forschungsfeld
  
  Digitale Transformation
  
  Human-Computer-Interaction
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Prediction of tumor board procedural recommendations using large language models

Aubreville, M. ., Ganz, J. ., Ammeling, J. ., Rosbach, E. ., Gehrke, T. ., Scherzad, A. ., … Goncalves, M. . (2024). Prediction of tumor board procedural recommendations using large language models. European Archives of Oto-Rhino-Laryngology. http://doi.org/10.1007/s00405-024-08947-9 (Original work published 2025)

Abstract

Multidisciplinary tumor boards are meetings where a team of medical specialists, including medical oncologists, radiation oncologists, radiologists, surgeons, and pathologists, collaborate to determine the best treatment plan for cancer patients. While decision-making in this context is logistically and cost-intensive, it has a significant positive effect on overall cancer survival.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Abteilung/Einrichtung
  
  FLAIR - Flensburg Artificial Intelligence Research
- Profilbereich
  
  Informatik und Gestaltung
- Forschungsfeld
  
  Digitalisierung im Gesundheitswesen
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Re-identification from histopathology images

Ganz, J. ., Ammeling, J. ., Jabari, S. ., Breininger, K. ., & Aubreville, M. . (2024). Re-identification from histopathology images. Medical Image Analysis, 103335. http://doi.org/10.1016/j.media.2024.103335 (Original work published 2025)
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Abteilung/Einrichtung
  
  FLAIR - Flensburg Artificial Intelligence Research
- Forschungsfeld
  
  Digitalisierung im Gesundheitswesen
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Breast cancer survival prediction using an automated mitosis detection pipeline

Stathonikos, N. ., Aubreville, M. ., de Vries, S. ., Wilm, F. ., Bertram, C. A., Veta, M. ., & van Diest, P. J. (2024). Breast cancer survival prediction using an automated mitosis detection pipeline. The Journal of Pathology: Clinical Research, 10, e70008. http://doi.org/https://doi.org/10.1002/2056-4538.70008

Abstract

Abstract Mitotic count (MC) is the most common measure to assess tumor proliferation in breast cancer patients and is highly predictive of patient outcomes. It is, however, subject to inter- and intraobserver variation and reproducibility challenges that may hamper its clinical utility. In past studies, artificial intelligence (AI)-supported MC has been shown to correlate well with traditional MC on glass slides. Considering the potential of AI to improve reproducibility of MC between pathologists, we undertook the next validation step by evaluating the prognostic value of a fully automatic method to detect and count mitoses on whole slide images using a deep learning model. The model was developed in the context of the Mitosis Domain Generalization Challenge 2021 (MIDOG21) grand challenge and was expanded by a novel automatic area selector method to find the optimal mitotic hotspot and calculate the MC per 2 mm2. We employed this method on a breast cancer cohort with long-term follow-up from the University Medical Centre Utrecht (N = 912) and compared predictive values for overall survival of AI-based MC and light-microscopic MC, previously assessed during routine diagnostics. The MIDOG21 model was prognostically comparable to the original MC from the pathology report in uni- and multivariate survival analysis. In conclusion, a fully automated MC AI algorithm was validated in a large cohort of breast cancer with regard to retained prognostic value compared with traditional light-microscopic MC.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Abteilung/Einrichtung
  
  FLAIR - Flensburg Artificial Intelligence Research
- Profilbereich
  
  Informatik und Gestaltung
- Forschungsfeld
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags
Information mismatch in PHH3-assisted mitosis annotation leads to interpretation shifts in H&E slide analysis

Ganz, J. ., Marzahl, C. ., Ammeling, J. ., Rosbach, E. ., Richter, B. ., Puget, C. ., … Aubreville, M. . (2024). Information mismatch in PHH3-assisted mitosis annotation leads to interpretation shifts in H&E slide analysis. Scientific Reports, 14, 26273. http://doi.org/10.1038/s41598-024-77244-6

Abstract

Abstract 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.
- Suche auf Google Scholar
- DOI Verweis
Exportformate
Weiterführende Links
- Personenseiten
  
  Aubreville, Marc
- Forschungsprojekt
  
  Robust and Accurate Multi-Tumor, Multi-Species, Multi-Laboratory and Multi-Scanner Mitosis Detection with Large-Scale Datasets and Artificial Intelligence
- Abteilung/Einrichtung
  
  FLAIR - Flensburg Artificial Intelligence Research
  
  CIVU – Center for Interaction, Visualization and Usability
- Profilbereich
  
  Informatik und Gestaltung
- Forschungsfeld
  
  Human-Computer-Interaction
  
  Data Science und Künstliche Intelligenz
- Fachbereich
  
  Fachbereich 3: Information und Kommunikation
Filter Tags

Publikationen

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags

Abstract

Exportformate

Weiterführende Links

Filter Tags