@article{ammeling_investigation_2025,

title = {Investigation of Class Separability within Object Detection Models in Histopathology},

author = {Jonas Ammeling and Jonathan Ganz and Frauke Wilm and Katharina Breininger and Marc Aubreville},

url = {https://ieeexplore.ieee.org/document/10965484/},

doi = {10.1109/TMI.2025.3560134},

issn = {0278-0062, 1558-254X},

year  = {2025},

date = {2025-01-01},

urldate = {2025-04-16},

journal = {IEEE Transactions on Medical Imaging},

pages = {1–1},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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{haghofer_nuclear_2024,

title = {Nuclear pleomorphism in canine cutaneous mast cell tumors: Comparison of reproducibility and prognostic relevance between estimates, manual morphometry, and algorithmic morphometry},

author = {Andreas Haghofer and Eda Parlak and Alexander Bartel and Taryn A. Donovan and Charles-Antoine Assenmacher and Pompei Bolfa and Michael J. Dark and Andrea Fuchs-Baumgartinger and Andrea Klang and Kathrin Jäger and Robert Klopfleisch and Sophie Merz and Barbara Richter and F. Yvonne Schulman and Hannah Janout and Jonathan Ganz and Josef Scharinger and Marc Aubreville and Stephan M. Winkler and Matti Kiupel and Christof A. Bertram},

url = {https://journals.sagepub.com/doi/10.1177/03009858241295399},

doi = {10.1177/03009858241295399},

issn = {0300-9858, 1544-2217},

year  = {2024},

date = {2024-11-01},

urldate = {2024-11-20},

journal = {Veterinary Pathology},

pages = {03009858241295399},

abstract = {Variation in nuclear size and shape is an important criterion of malignancy for many tumor types; however, categorical estimates by pathologists have poor reproducibility. Measurements of nuclear characteristics can improve reproducibility, but current manual methods are time-consuming. The aim of this study was to explore the limitations of estimates and develop alternative morphometric solutions for canine cutaneous mast cell tumors (ccMCTs). We assessed the following nuclear evaluation methods for accuracy, reproducibility, and prognostic utility: (1) anisokaryosis estimates by 11 pathologists; (2) gold standard manual morphometry of at least 100 nuclei; (3) practicable manual morphometry with stratified sampling of 12 nuclei by 9 pathologists; and (4) automated morphometry using deep learning–based segmentation. The study included 96 ccMCTs with available outcome information. Inter-rater reproducibility of anisokaryosis estimates was low (k = 0.226), whereas it was good (intraclass correlation = 0.654) for practicable morphometry of the standard deviation (SD) of nuclear size. As compared with gold standard manual morphometry (area under the ROC curve [AUC] = 0.839, 95% confidence interval [CI] = 0.701–0.977), the prognostic value (tumor-specific survival) of SDs of nuclear area for practicable manual morphometry and automated morphometry were high with an AUC of 0.868 (95% CI = 0.737–0.991) and 0.943 (95% CI = 0.889–0.996), respectively. This study supports the use of manual morphometry with stratified sampling of 12 nuclei and algorithmic morphometry to overcome the poor reproducibility of estimates. Further studies are needed to validate our findings, determine inter-algorithmic reproducibility and algorithmic robustness, and explore tumor heterogeneity of nuclear features in entire tumor sections.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{puget_artificial_2024,

title = {Artificial intelligence can be trained to predict textitc-KIT -11 mutational status of canine mast cell tumors from hematoxylin and eosin-stained histological slides},

author = {Chloé Puget and Jonathan Ganz and Julian Ostermaier and Thomas Conrad and Eda Parlak and Christof A. Bertram and Matti Kiupel and Katharina Breininger and Marc Aubreville and Robert Klopfleisch},

url = {https://journals.sagepub.com/doi/10.1177/03009858241286806},

doi = {10.1177/03009858241286806},

issn = {0300-9858, 1544-2217},

year  = {2024},

date = {2024-10-01},

urldate = {2024-10-21},

journal = {Veterinary Pathology},

pages = {03009858241286806},

abstract = {Numerous prognostic factors are currently assessed histologically and immunohistochemically in canine mast cell tumors (MCTs) to evaluate clinical behavior. In addition, polymerase chain reaction (PCR) is often performed to detect internal tandem duplication (ITD) mutations in exon 11 of the c-KIT gene ( c-KIT-11-ITD) to predict the therapeutic response to tyrosine kinase inhibitors. This project aimed at training deep learning models (DLMs) to identify MCTs with c-KIT-11-ITD solely based on morphology. Hematoxylin and eosin (HE) stained slides of 368 cutaneous, subcutaneous, and mucocutaneous MCTs (195 with ITD and 173 without) were stained consecutively in 2 different laboratories and scanned with 3 different slide scanners. This resulted in 6 data sets (stain-scanner variations representing diagnostic institutions) of whole-slide images. DLMs were trained with single and mixed data sets and their performances were assessed under stain-scanner variations (domain shifts). The DLM correctly classified HE slides according to their c-KIT-11-ITD status in up to 87% of cases with a 0.90 sensitivity and a 0.83 specificity. A relevant performance drop could be observed when the stain-scanner combination of training and test data set differed. Multi-institutional data sets improved the average accuracy but did not reach the maximum accuracy of algorithms trained and tested on the same stain-scanner variant (ie, intra-institutional). In summary, DLM-based morphological examination can predict c-KIT-11-ITD with high accuracy in canine MCTs in HE slides. However, staining protocol and scanner type influence accuracy. Larger data sets of scans from different laboratories and scanners may lead to more robust DLMs to identify c- KIT mutations in HE slides.},

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{glahn_automated_2024,

title = {Automated Nuclear Morphometry: A Deep Learning Approach for Prognostication in Canine Pulmonary Carcinoma to Enhance Reproducibility},

author = {Imaine Glahn and Andreas Haghofer and Taryn A. Donovan and Brigitte Degasperi and Alexander Bartel and Theresa Kreilmeier-Berger and Philip S. Hyndman and Hannah Janout and Charles-Antoine Assenmacher and Florian Bartenschlager and Pompei Bolfa and Michael J. Dark and Andrea Klang and Robert Klopfleisch and Sophie Merz and Barbara Richter and F. Yvonne Schulman and Jonathan Ganz and Josef Scharinger and Marc Aubreville and Stephan M. Winkler and Christof A. Bertram},

url = {https://www.mdpi.com/2306-7381/11/6/278},

doi = {10.3390/vetsci11060278},

issn = {2306-7381},

year  = {2024},

date = {2024-06-01},

urldate = {2024-06-19},

journal = {Veterinary Sciences},

volume = {11},

number = {6},

pages = {278},

abstract = {The integration of deep learning-based tools into diagnostic workflows is increasingly prevalent due to their efficiency and reproducibility in various settings. We investigated the utility of automated nuclear morphometry for assessing nuclear pleomorphism (NP), a criterion of malignancy in the current grading system in canine pulmonary carcinoma (cPC), and its prognostic implications. We developed a deep learning-based algorithm for evaluating NP (variation in size, i.e., anisokaryosis and/or shape) using a segmentation model. Its performance was evaluated on 46 cPC cases with comprehensive follow-up data regarding its accuracy in nuclear segmentation and its prognostic ability. Its assessment of NP was compared to manual morphometry and established prognostic tests (pathologists’ NP estimates (n = 11), mitotic count, histological grading, and TNM-stage). The standard deviation (SD) of the nuclear area, indicative of anisokaryosis, exhibited good discriminatory ability for tumor-specific survival, with an area under the curve (AUC) of 0.80 and a hazard ratio (HR) of 3.38. The algorithm achieved values comparable to manual morphometry. In contrast, the pathologists’ estimates of anisokaryosis resulted in HR values ranging from 0.86 to 34.8, with slight inter-observer reproducibility (k = 0.204). Other conventional tests had no significant prognostic value in our study cohort. Fully automated morphometry promises a time-efficient and reproducible assessment of NP with a high prognostic value. Further refinement of the algorithm, particularly to address undersegmentation, and application to a larger study population are required.},

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{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}

}