@article{ganz_information_2024,

title = {Information mismatch in PHH3-assisted mitosis annotation leads to interpretation shifts in H&E slide analysis},

author = {Jonathan Ganz and Christian Marzahl and Jonas Ammeling and Emely Rosbach and Barbara Richter and Chloé Puget and Daniela Denk and Elena A. Demeter and Flaviu A. Tăbăran and Gabriel Wasinger and Karoline Lipnik and Marco Tecilla and Matthew J. Valentine and Michael J. Dark and Niklas Abele and Pompei Bolfa and Ramona Erber and Robert Klopfleisch and Sophie Merz and Taryn A. Donovan and Samir Jabari and Christof A. Bertram and Katharina Breininger and Marc Aubreville},

url = {https://www.nature.com/articles/s41598-024-77244-6},

doi = {10.1038/s41598-024-77244-6},

issn = {2045-2322},

year  = {2024},

date = {2024-11-01},

urldate = {2024-11-04},

journal = {Scientific Reports},

volume = {14},

number = {1},

pages = {26273},

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.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{aubreville_prediction_2024,

title = {Prediction of tumor board procedural recommendations using large language models},

author = {Marc Aubreville and Jonathan Ganz and Jonas Ammeling and Emely Rosbach and Thomas Gehrke and Agmal Scherzad and Stephan Hackenberg and Miguel Goncalves},

url = {https://doi.org/10.1007/s00405-024-08947-9},

doi = {10.1007/s00405-024-08947-9},

issn = {1434-4726},

year  = {2024},

date = {2024-09-01},

journal = {European Archives of Oto-Rhino-Laryngology},

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.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ganz_re-identification_2024,

title = {Re-identification from histopathology images},

author = {Jonathan Ganz and Jonas Ammeling and Samir Jabari and Katharina Breininger and Marc Aubreville},

url = {https://linkinghub.elsevier.com/retrieve/pii/S1361841524002603},

doi = {10.1016/j.media.2024.103335},

issn = {13618415},

year  = {2024},

date = {2024-09-01},

urldate = {2024-09-20},

journal = {Medical Image Analysis},

pages = {103335},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{aubreville_domain_2024,

title = {Domain generalization across tumor types, laboratories, and species — Insights from the 2022 edition of the Mitosis Domain Generalization Challenge},

author = {Marc Aubreville and Nikolas Stathonikos and Taryn A. Donovan and Robert Klopfleisch and Jonas Ammeling and Jonathan Ganz and Frauke Wilm and Mitko Veta and Samir Jabari and Markus Eckstein and Jonas Annuscheit and Christian Krumnow and Engin Bozaba and Sercan Çayır and Hongyan Gu and Xiang ‘Anthony’ Chen and Mostafa Jahanifar and Adam Shephard and Satoshi Kondo and Satoshi Kasai and Sujatha Kotte and V. G. Saipradeep and Maxime W. Lafarge and Viktor H. Koelzer and Ziyue Wang and Yongbing Zhang and Sen Yang and Xiyue Wang and Katharina Breininger and Christof A. Bertram},

url = {https://linkinghub.elsevier.com/retrieve/pii/S136184152400080X},

doi = {10.1016/j.media.2024.103155},

issn = {13618415},

year  = {2024},

date = {2024-05-01},

urldate = {2024-03-27},

journal = {Medical Image Analysis},

volume = {94},

pages = {103155},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{krugel_perceived_2024-1,

title = {Perceived responsibility in AI-supported medicine},

author = {Sebastian Krügel and Jonas Ammeling and Marc Aubreville and Alexis Fritz and Angelika Kießig and Matthias Uhl},

url = {https://link.springer.com/10.1007/s00146-024-01972-6},

doi = {10.1007/s00146-024-01972-6},

issn = {0951-5666, 1435-5655},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-01},

journal = {AI & SOCIETY},

abstract = {Abstract 

 In a representative vignette study in Germany with 1,653 respondents, we investigated laypeople’s attribution of moral responsibility in collaborative medical diagnosis. Specifically, we compare people’s judgments in a setting in which physicians are supported by an AI-based recommender system to a setting in which they are supported by a human colleague. It turns out that people tend to attribute moral responsibility to the artificial agent, although this is traditionally considered a category mistake in normative ethics. This tendency is stronger when people believe that AI may become conscious at some point. In consequence, less responsibility is attributed to human agents in settings with hybrid diagnostic teams than in settings with human-only diagnostic teams. Our findings may have implications for behavior exhibited in contexts of collaborative medical decision making with AI-based as opposed to human recommenders because less responsibility is attributed to agents who have the mental capacity to care about outcomes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{krugel_perceived_2024,

title = {Perceived responsibility in AI-supported medicine},

author = {Sebastian Krügel and Jonas Ammeling and Marc Aubreville and Alexis Fritz and Angelika Kießig and Matthias Uhl},

url = {https://link.springer.com/10.1007/s00146-024-01972-6},

doi = {10.1007/s00146-024-01972-6},

issn = {0951-5666, 1435-5655},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-23},

journal = {AI & SOCIETY},

abstract = {Abstract 

 In a representative vignette study in Germany with 1,653 respondents, we investigated laypeople’s attribution of moral responsibility in collaborative medical diagnosis. Specifically, we compare people’s judgments in a setting in which physicians are supported by an AI-based recommender system to a setting in which they are supported by a human colleague. It turns out that people tend to attribute moral responsibility to the artificial agent, although this is traditionally considered a category mistake in normative ethics. This tendency is stronger when people believe that AI may become conscious at some point. In consequence, less responsibility is attributed to human agents in settings with hybrid diagnostic teams than in settings with human-only diagnostic teams. Our findings may have implications for behavior exhibited in contexts of collaborative medical decision making with AI-based as opposed to human recommenders because less responsibility is attributed to agents who have the mental capacity to care about outcomes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{aubreville_comprehensive_2023,

title = {A comprehensive multi-domain dataset for mitotic figure detection},

author = {Marc Aubreville and Frauke Wilm and Nikolas Stathonikos and Katharina Breininger and Taryn A. Donovan and Samir Jabari and Mitko Veta and Jonathan Ganz and Jonas Ammeling and Paul J. Van Diest and Robert Klopfleisch and Christof A. Bertram},

url = {https://www.nature.com/articles/s41597-023-02327-4},

doi = {10.1038/s41597-023-02327-4},

issn = {2052-4463},

year  = {2023},

date = {2023-07-01},

urldate = {2023-07-26},

journal = {Scientific Data},

volume = {10},

number = {1},

pages = {484},

abstract = {Abstract 

 The prognostic value of mitotic figures in tumor tissue is well-established for many tumor types and automating this task is of high research interest. However, especially deep learning-based methods face performance deterioration in the presence of domain shifts, which may arise from different tumor types, slide preparation and digitization devices. We introduce the MIDOG++ dataset, an extension of the MIDOG 2021 and 2022 challenge datasets. We provide region of interest images from 503 histological specimens of seven different tumor types with variable morphology with in total labels for 11,937 mitotic figures: breast carcinoma, lung carcinoma, lymphosarcoma, neuroendocrine tumor, cutaneous mast cell tumor, cutaneous melanoma, and (sub)cutaneous soft tissue sarcoma. The specimens were processed in several laboratories utilizing diverse scanners. We evaluated the extent of the domain shift by using state-of-the-art approaches, observing notable differences in single-domain training. In a leave-one-domain-out setting, generalizability improved considerably. This mitotic figure dataset is the first that incorporates a wide domain shift based on different tumor types, laboratories, whole slide image scanners, and species.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}