@article{stathonikos_breast_2024,

title = {Breast cancer survival prediction using an automated mitosis detection pipeline},

author = {Nikolas Stathonikos and Marc Aubreville and Sjoerd De Vries and Frauke Wilm and Christof A Bertram and Mitko Veta and Paul J Van Diest},

url = {https://pathsocjournals.onlinelibrary.wiley.com/doi/10.1002/2056-4538.70008},

doi = {10.1002/2056-4538.70008},

issn = {2056-4538, 2056-4538},

year  = {2024},

date = {2024-11-01},

urldate = {2024-10-29},

journal = {The Journal of Pathology: Clinical Research},

volume = {10},

number = {6},

pages = {e70008},

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 mm 

 2 

 . 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.},

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{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{frenken_feasibility_2024,

title = {Feasibility of Optical Biopsy During Endoscopic Sinus Surgery With Confocal Laser Endomicroscopy: A Pilot Study},

author = {Ann‐Kathrin Frenken and Matti Sievert and Bharat Panuganti and Marc Aubreville and Till Meyer and Agmal Scherzad and Thomas Gehrke and Matthias Scheich and Stephan Hackenberg and Miguel Goncalves},

url = {https://onlinelibrary.wiley.com/doi/10.1002/lary.31503},

doi = {10.1002/lary.31503},

issn = {0023-852X, 1531-4995},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-19},

journal = {The Laryngoscope},

pages = {lary.31503},

abstract = {Objective 

 Confocal laser endomicroscopy (CLE) is an optical imaging technique that allows in vivo, real‐time, microscope‐like assessment of superficial lesions. Although there is substantial data on CLE use in the upper GI tract, there is limited information regarding its application in the nasal cavity and paranasal sinuses. This study aims to assess the feasibility and diagnostic metrics of CLE in the nasal cavity and paranasal sinuses regarding differentiation between healthy/benign and malignant tissue. These structures show, however, a wider variety of frequent and concomitant benign and malignant pathologies, which could pose an increased challenge for optical biopsy by CLE. 

 Methods 

 We performed CLE on a case series of six patients with various findings in the nose (three chronic rhinosinusitis, adenocarcinoma, meningoenzephalozele, esthesionneuroblastoma). Forty‐two sequences (3792 images) from various structures in the nasal cavity and/or paranasal sinuses were acquired. Biopsies were taken at corresponding locations and analyzed in hematoxylin and eosin staining as a standard of reference. Three independent examiners blinded to the histopathology assessed the sequences. 

 Results 

 Healthy and inflamed mucosa could be distinguished from malignant lesions with an accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 84.1%, 85.4%, 83.1%, 72.5%, and 92.1%, respectively, with a substantial agreement between raters (Fleiss 

 κ = 0.62). 

 Conclusion 

 This technique shows, despite its limitations, potential as an adjunctive imaging technique during sinus surgery; however, the creation of a scoring system based on reproducible and defined characteristics in a larger more diverse population should be the focus of further research to improve its diagnostic value and clinical utility. 

 Level of Evidence 

 NA 

 Laryngoscope 

 , 2024},

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{oetter_oral_2024,

title = {Oral mucosa - an examination map for confocal laser endomicroscopy within the oral cavity: an experimental clinical study},

author = {Nicolai Oetter and Jonas Pröll and Matti Sievert and Miguel Goncalves and Maximilian Rohde and Christopher-Philipp Nobis and Christian Knipfer and Marc Aubreville and Zhaoya Pan and Katharina Breininger and Andreas Maier and Marco Kesting and Florian Stelzle},

url = {https://link.springer.com/10.1007/s00784-024-05664-9},

doi = {10.1007/s00784-024-05664-9},

issn = {1436-3771},

year  = {2024},

date = {2024-04-01},

urldate = {2024-04-24},

journal = {Clinical Oral Investigations},

volume = {28},

number = {5},

pages = {266},

abstract = {Abstract 

 Objectives 

 Confocal laser endomicroscopy (CLE) is an optical method that enables microscopic visualization of oral mucosa. Previous studies have shown that it is possible to differentiate between physiological and malignant oral mucosa. However, differences in mucosal architecture were not taken into account. The objective was to map the different oral mucosal morphologies and to establish a “CLE map” of physiological mucosa as baseline for further application of this powerful technology. 

 Materials and methods 

 The CLE database consisted of 27 patients. The following spots were examined: (1) upper lip (intraoral) (2) alveolar ridge (3) lateral tongue (4) floor of the mouth (5) hard palate (6) intercalary line. All sequences were examined by two CLE experts for morphological differences and video quality. 

 Results 

 Analysis revealed clear differences in image quality and possibility of depicting tissue morphologies between the various localizations of oral mucosa: imaging of the alveolar ridge and hard palate showed visually most discriminative tissue morphology. Labial mucosa was also visualized well using CLE. Here, typical morphological features such as uniform cells with regular intercellular gaps and vessels could be clearly depicted. Image generation and evaluation was particularly difficult in the area of the buccal mucosa, the lateral tongue and the floor of the mouth. 

 Conclusion 

 A physiological “CLE map” for the entire oral cavity could be created for the first time. 

 Clinical relevance 

 This will make it possible to take into account the existing physiological morphological features when differentiating between normal mucosa and oral squamous cell carcinoma in future work.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sievert_diagnosis_2024,

title = {Diagnosis of malignancy in oropharyngeal confocal laser endomicroscopy using GPT 4.0 with vision},

author = {Matti Sievert and Marc Aubreville and Sarina Katrin Mueller and Markus Eckstein and Katharina Breininger and Heinrich Iro and Miguel Goncalves},

url = {https://link.springer.com/10.1007/s00405-024-08476-5},

doi = {10.1007/s00405-024-08476-5},

issn = {0937-4477, 1434-4726},

year  = {2024},

date = {2024-02-01},

urldate = {2024-02-21},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{aubreville_developing_2024,

title = {Developing Robust AI Applications for Clinical Use: The Special Case of Pathology},

author = {Marc Aubreville},

doi = {https://doi.org/10.47184/tp.2024.01.04},

year  = {2024},

date = {2024-01-01},

journal = {Trillium Pathology},

volume = {TP 1/2004},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{haghofer_histological_2023,

title = {Histological classification of canine and feline lymphoma using a modular approach based on deep learning and advanced image processing},

author = {Andreas Haghofer and Andrea Fuchs-Baumgartinger and Karoline Lipnik and Robert Klopfleisch and Marc Aubreville and Josef Scharinger and Herbert Weissenböck and Stephan M. Winkler and Christof A. Bertram},

url = {https://www.nature.com/articles/s41598-023-46607-w},

doi = {10.1038/s41598-023-46607-w},

issn = {2045-2322},

year  = {2023},

date = {2023-11-01},

urldate = {2024-11-04},

journal = {Scientific Reports},

volume = {13},

number = {1},

pages = {19436},

abstract = {Abstract 

 Histopathological examination of tissue samples is essential for identifying tumor malignancy and the diagnosis of different types of tumor. In the case of lymphoma classification, nuclear size of the neoplastic lymphocytes is one of the key features to differentiate the different subtypes. Based on the combination of artificial intelligence and advanced image processing, we provide a workflow for the classification of lymphoma with regards to their nuclear size (small, intermediate, and large). As the baseline for our workflow testing, we use a Unet++ model trained on histological images of canine lymphoma with individually labeled nuclei. As an alternative to the Unet++, we also used a publicly available pre-trained and unmodified instance segmentation model called Stardist to demonstrate that our modular classification workflow can be combined with different types of segmentation models if they can provide proper nuclei segmentation. Subsequent to nuclear segmentation, we optimize algorithmic parameters for accurate classification of nuclear size using a newly derived reference size and final image classification based on a pathologists-derived ground truth. Our image classification module achieves a classification accuracy of up to 92% on canine lymphoma data. Compared to the accuracy ranging from 66.67 to 84% achieved using measurements provided by three individual pathologists, our algorithm provides a higher accuracy level and reproducible results. Our workflow also demonstrates a high transferability to feline lymphoma, as shown by its accuracy of up to 84.21%, even though our workflow was not optimized for feline lymphoma images. By determining the nuclear size distribution in tumor areas, our workflow can assist pathologists in subtyping lymphoma based on the nuclei size and potentially improve reproducibility. Our proposed approach is modular and comprehensible, thus allowing adaptation for specific tasks and increasing the users’ trust in computer-assisted image classification.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fragoso-garcia_automated_2023,

title = {Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images},

author = {Marco Fragoso-Garcia and Frauke Wilm and Christof A. Bertram and Sophie Merz and Anja Schmidt and Taryn Donovan and Andrea Fuchs-Baumgartinger and Alexander Bartel and Christian Marzahl and Laura Diehl and Chloe Puget and Andreas Maier and Marc Aubreville and Katharina Breininger and Robert Klopfleisch},

url = {http://journals.sagepub.com/doi/10.1177/03009858231189205},

doi = {10.1177/03009858231189205},

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

year  = {2023},

date = {2023-07-01},

urldate = {2023-08-07},

journal = {Veterinary Pathology},

pages = {03009858231189205},

abstract = {Microscopic evaluation of hematoxylin and eosin-stained slides is still the diagnostic gold standard for a variety of diseases, including neoplasms. Nevertheless, intra- and interrater variability are well documented among pathologists. So far, computer assistance via automated image analysis has shown potential to support pathologists in improving accuracy and reproducibility of quantitative tasks. In this proof of principle study, we describe a machine-learning-based algorithm for the automated diagnosis of 7 of the most common canine skin tumors: trichoblastoma, squamous cell carcinoma, peripheral nerve sheath tumor, melanoma, histiocytoma, mast cell tumor, and plasmacytoma. We selected, digitized, and annotated 350 hematoxylin and eosin-stained slides (50 per tumor type) to create a database divided into training},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hirling_segmentation_2023,

title = {Segmentation metric misinterpretations in bioimage analysis},

author = {Dominik Hirling and Ervin Tasnadi and Juan Caicedo and Maria V. Caroprese and Rickard Sjögren and Marc Aubreville and Krisztian Koos and Peter Horvath},

url = {https://www.nature.com/articles/s41592-023-01942-8},

doi = {10.1038/s41592-023-01942-8},

issn = {1548-7091, 1548-7105},

year  = {2023},

date = {2023-07-01},

urldate = {2023-07-28},

journal = {Nature Methods},

abstract = {Abstract 

 Quantitative evaluation of image segmentation algorithms is crucial in the field of bioimage analysis. The most common assessment scores, however, are often misinterpreted and multiple definitions coexist with the same name. Here we present the ambiguities of evaluation metrics for segmentation algorithms and show how these misinterpretations can alter leaderboards of influential competitions. We also propose guidelines for how the currently existing problems could be tackled.},

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}

}

@article{wilm_pan-tumor_2023,

title = {Pan-tumor T-lymphocyte detection using deep neural networks: Recommendations for transfer learning in immunohistochemistry},

author = {Frauke Wilm and Christian Ihling and Gábor Méhes and Luigi Terracciano and Chloé Puget and Robert Klopfleisch and Peter Schüffler and Marc Aubreville and Andreas Maier and Thomas Mrowiec and Katharina Breininger},

url = {https://linkinghub.elsevier.com/retrieve/pii/S2153353923001153},

doi = {10.1016/j.jpi.2023.100301},

issn = {21533539},

year  = {2023},

date = {2023-02-01},

urldate = {2023-07-01},

journal = {Journal of Pathology Informatics},

volume = {14},

pages = {100301},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{aubreville_mitosis_2023,

title = {Mitosis domain generalization in histopathology images — The MIDOG challenge},

author = {Marc Aubreville and Nikolas Stathonikos and Christof A. Bertram and Robert Klopfleisch and Natalie Ter Hoeve and Francesco Ciompi and Frauke Wilm and Christian Marzahl and Taryn A. Donovan and Andreas Maier and Jack Breen and Nishant Ravikumar and Youjin Chung and Jinah Park and Ramin Nateghi and Fattaneh Pourakpour and Rutger H. J. Fick and Saima Ben Hadj and Mostafa Jahanifar and Adam Shephard and Jakob Dexl and Thomas Wittenberg and Satoshi Kondo and Maxime W. Lafarge and Viktor H. Koelzer and Jingtang Liang and Yubo Wang and Xi Long and Jingxin Liu and Salar Razavi and April Khademi and Sen Yang and Xiyue Wang and Ramona Erber and Andrea Klang and Karoline Lipnik and Pompei Bolfa and Michael J. Dark and Gabriel Wasinger and Mitko Veta and Katharina Breininger},

url = {https://linkinghub.elsevier.com/retrieve/pii/S1361841522003279},

doi = {10.1016/j.media.2022.102699},

issn = {13618415},

year  = {2023},

date = {2023-01-01},

urldate = {2023-05-19},

journal = {Medical Image Analysis},

volume = {84},

pages = {102699},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pan_defining_2023,

title = {Defining a baseline identification of artifacts in confocal laser endomicroscopy in head and neck cancer imaging},

author = {Zhaoya Pan and Katharina Breininger and Marc Aubreville and Florian Stelzle and Nicolai Oetter and Andreas Maier and Konstantinos Mantsopoulos and Heinrich Iro and Miguel Goncalves and Matti Sievert},

url = {https://linkinghub.elsevier.com/retrieve/pii/S0196070922004069},

doi = {10.1016/j.amjoto.2022.103779},

issn = {01960709},

year  = {2023},

date = {2023-01-01},

urldate = {2023-07-01},

journal = {American Journal of Otolaryngology},

volume = {44},

number = {2},

pages = {103779},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sievert_validation_2022,

title = {Validation of a classification and scoring system for the diagnosis of laryngeal and pharyngeal squamous cell carcinomas by confocal laser endomicroscopy},

author = {Matti Sievert and Konstantinos Mantsopoulos and Sarina K. Mueller and Robin Rupp and Markus Eckstein and Florian Stelzle and Nicolai Oetter and Andreas Maier and Marc Aubreville and Heinrich Iro and Miguel Goncalves},

url = {https://linkinghub.elsevier.com/retrieve/pii/S1808869421001245},

doi = {10.1016/j.bjorl.2021.06.002},

issn = {18088694},

year  = {2022},

date = {2022-11-01},

urldate = {2023-06-30},

journal = {Brazilian Journal of Otorhinolaryngology},

volume = {88},

pages = {S26–S32},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wilm_pan-tumor_2022,

title = {Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset},

author = {Frauke Wilm and Marco Fragoso and Christian Marzahl and Jingna Qiu and Chloé Puget and Laura Diehl and Christof A. Bertram and Robert Klopfleisch and Andreas Maier and Katharina Breininger and Marc Aubreville},

url = {https://www.nature.com/articles/s41597-022-01692-w},

doi = {10.1038/s41597-022-01692-w},

issn = {2052-4463},

year  = {2022},

date = {2022-09-01},

urldate = {2023-06-30},

journal = {Scientific Data},

volume = {9},

number = {1},

pages = {588},

abstract = {Abstract 

 Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists in this regard. However, many of these supervised algorithms require a large amount of annotated data for robust development. We present a publicly available dataset of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes, including seven cutaneous tumor subtypes. In inter-rater experiments, we show a high consistency of the provided labels, especially for tumor annotations. We further validate the dataset by training a deep neural network for the task of tissue segmentation and tumor subtype classification. We achieve a class-averaged Jaccard coefficient of 0.7047, and 0.9044 for tumor in particular. For classification, we achieve a slide-level accuracy of 0.9857. Since canine cutaneous tumors possess various histologic homologies to human tumors the added value of this dataset is not limited to veterinary pathology but extends to more general fields of application.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{marzahl_inter-species_2022,

title = {Inter-species cell detection - datasets on pulmonary hemosiderophages in equine, human and feline specimens},

author = {Christian Marzahl and Jenny Hill and Jason Stayt and Dorothee Bienzle and Lutz Welker and Frauke Wilm and Jörn Voigt and Marc Aubreville and Andreas Maier and Robert Klopfleisch and Katharina Breininger and Christof A. Bertram},

url = {https://www.nature.com/articles/s41597-022-01389-0},

doi = {10.1038/s41597-022-01389-0},

issn = {2052-4463},

year  = {2022},

date = {2022-06-01},

urldate = {2023-07-01},

journal = {Scientific Data},

volume = {9},

number = {1},

pages = {269},

abstract = {Abstract 

 Pulmonary hemorrhage (P-Hem) occurs among multiple species and can have various causes. Cytology of bronchoalveolar lavage fluid (BALF) using a 5-tier scoring system of alveolar macrophages based on their hemosiderin content is considered the most sensitive diagnostic method. We introduce a novel, fully annotated multi-species P-Hem dataset, which consists of 74 cytology whole slide images (WSIs) with equine, feline and human samples. To create this high-quality and high-quantity dataset, we developed an annotation pipeline combining human expertise with deep learning and data visualisation techniques. We applied a deep learning-based object detection approach trained on 17 expertly annotated equine WSIs, to the remaining 39 equine, 12 human and 7 feline WSIs. The resulting annotations were semi-automatically screened for errors on multiple types of specialised annotation maps and finally reviewed by a trained pathologist. Our dataset contains a total of 297,383 hemosiderophages classified into five grades. It is one of the largest publicly available WSIs datasets with respect to the number of annotations, the scanned area and the number of species covered.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sievert_impact_2022,

title = {Impact of intraepithelial capillary loops and atypical vessels in confocal laser endomicroscopy for the diagnosis of laryngeal and hypopharyngeal squamous cell carcinoma},

author = {Matti Sievert and Markus Eckstein and Konstantinos Mantsopoulos and Sarina K. Mueller and Florian Stelzle and Marc Aubreville and Nicolai Oetter and Andreas Maier and Heinrich Iro and Miguel Goncalves},

url = {https://link.springer.com/10.1007/s00405-021-06954-8},

doi = {10.1007/s00405-021-06954-8},

issn = {0937-4477, 1434-4726},

year  = {2022},

date = {2022-04-01},

urldate = {2023-06-30},

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

volume = {279},

number = {4},

pages = {2029–2037},

abstract = {Abstract 

 Purpose 

 Confocal laser endomicroscopy (CLE) allows surface imaging of the laryngeal and pharyngeal mucosa in vivo at a thousand-fold magnification. This study aims to compare irregular blood vessels and intraepithelial capillary loops in healthy mucosa and squamous cell carcinoma (SCC) via CLE. 

 Materials and methods 

 We included ten patients with confirmed SCC and planned total laryngectomy in this study between March 2020 and February 2021. CLE images of these patients were collected and compared with the corresponding histology in hematoxylin and eosin staining. We analyzed the characteristic endomicroscopic patterns of blood vessels and intraepithelial capillary loops for the diagnosis of SCC. 

 Results 

 In a total of 54 sequences, we identified 243 blood vessels which were analyzed regarding structure, diameter, and Fluorescein leakage, confirming that irregular, corkscrew-like vessels (24.4% vs. 1.3%; 

 P 

 < .001), dilated intraepithelial capillary loops (90.8% vs. 28.7%; 

 P 

 < .001), and increased capillary leakage (40.7% vs. 2.5%; 

 P 

 < .001), are significantly more frequently detected in SCC compared to the healthy epithelium. We defined a vessel diameter of 30 μm in capillary loops as a cut-off value, obtaining a sensitivity, specificity, PPV, and NPV and accuracy of 90.6%, 71.3%, 57.4%, 94.7%, and 77.1%, respectively, for the detection of malignancy based solely on capillary architecture. 

 Conclusion 

 Capillaries within malignant lesions are fundamentally different from those in healthy mucosa regions. The capillary architecture is a significant feature aiding the identification of malignant mucosa areas during in-vivo, real-time CLE examination.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bertram_computer-assisted_2022,

title = {Computer-assisted mitotic count using a deep learning–based algorithm improves interobserver reproducibility and accuracy},

author = {Christof A. Bertram and Marc Aubreville and Taryn A. Donovan and Alexander Bartel and Frauke Wilm and Christian Marzahl and Charles-Antoine Assenmacher and Kathrin Becker and Mark Bennett and Sarah Corner and Brieuc Cossic and Daniela Denk and Martina Dettwiler and Beatriz Garcia Gonzalez and Corinne Gurtner and Ann-Kathrin Haverkamp and Annabelle Heier and Annika Lehmbecker and Sophie Merz and Erica L. Noland and Stephanie Plog and Anja Schmidt and Franziska Sebastian and Dodd G. Sledge and Rebecca C. Smedley and Marco Tecilla and Tuddow Thaiwong and Andrea Fuchs-Baumgartinger and Donald J. Meuten and Katharina Breininger and Matti Kiupel and Andreas Maier and Robert Klopfleisch},

url = {http://journals.sagepub.com/doi/10.1177/03009858211067478},

doi = {10.1177/03009858211067478},

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

year  = {2022},

date = {2022-03-01},

urldate = {2023-06-30},

journal = {Veterinary Pathology},

volume = {59},

number = {2},

pages = {211–226},

abstract = {The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intraobserver discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying or classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, computer-assisted review by pathologists may ensure reliability. In the present study, we compared partial (MC-ROI preselection) and full (additional visualization of MF candidates and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole-slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MFs, and improving classification against imposters. The interobserver consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sievert_intraoperative_2021,

title = {Intraoperative free margins assessment of oropharyngeal squamous cell carcinoma with confocal laser endomicroscopy: a pilot study},

author = {Matti Sievert and Florian Stelzle and Marc Aubreville and Sarina K. Mueller and Markus Eckstein and Nicolai Oetter and Andreas Maier and Konstantinos Mantsopoulos and Heinrich Iro and Miguel Goncalves},

url = {https://link.springer.com/10.1007/s00405-021-06659-y},

doi = {10.1007/s00405-021-06659-y},

issn = {0937-4477, 1434-4726},

year  = {2021},

date = {2021-11-01},

urldate = {2023-06-30},

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

volume = {278},

number = {11},

pages = {4433–4439},

abstract = {Abstract 

 Purpose 

 This pilot study aimed to assess the feasibility of intraoperative assessment of safe margins with confocal laser endomicroscopy (CLE) during oropharyngeal squamous cell carcinoma (OPSCC) surgery. 

 Methods 

 We included five consecutive patients confirmed OPSCC and planned tumor resection in September and October 2020. Healthy appearing mucosa in the marginal zone, and the tumor margin, were examined with CLE and biopsy during tumor resection. A total of 12,809 CLE frames were correlated with the gold standard of hematoxylin and eosin staining. Three head and neck surgeons and one pathologist were asked to identify carcinoma in a sample of 169 representative images, blinded to the histological results. 

 Results 

 Healthy mucosa showed epithelium with uniform size and shape with distinct cytoplasmic membranes and regular vessel architecture. CLE optical biopsy of OPSCC demonstrated a disorganized arrangement of variable cellular morphology. We calculated an accuracy, sensitivity, specificity, PPV, and NPV of 86%, 90%, 79%, 88%, and 82%, respectively, with inter-rater reliability and 

 κ 

 -value of 0.60. 

 Conclusion 

 CLE can be easily integrated into the intraoperative setting, generate real-time, in-vivo microscopic images of the oropharynx for evaluation and demarcation of cancer. It can eventually contribute to a less radical approach by enabling a more precise evaluation of the cancer margin.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{meuten_international_2021,

title = {International Guidelines for Veterinary Tumor Pathology: A Call to Action},

author = {Donald J. Meuten and Frances M. Moore and Taryn A. Donovan and Christof A. Bertram and Robert Klopfleisch and Robert A. Foster and Rebecca C. Smedley and Michael J. Dark and Milan Milovancev and Paul Stromberg and Bruce H. Williams and Marc Aubreville and Giancarlo Avallone and Pompei Bolfa and John Cullen and Michelle M. Dennis and Michael Goldschmidt and Richard Luong and Andrew D. Miller and Margaret A. Miller and John S. Munday and Paola Roccabianca and Elisa N. Salas and F. Yvonne Schulman and Renee Laufer-Amorim and Midori G. Asakawa and Linden Craig and Nick Dervisis and D. Glen Esplin and Jeanne W. George and Marlene Hauck and Yumiko Kagawa and Matti Kiupel and Keith Linder and Kristina Meichner and Laura Marconato and Michelle L. Oblak and Renato L. Santos and R. Mark Simpson and Harold Tvedten and Derick Whitley},

url = {http://journals.sagepub.com/doi/10.1177/03009858211013712},

doi = {10.1177/03009858211013712},

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

year  = {2021},

date = {2021-09-01},

urldate = {2023-06-30},

journal = {Veterinary Pathology},

volume = {58},

number = {5},

pages = {766–794},

abstract = {Standardization of tumor assessment lays the foundation for validation of grading systems, permits reproducibility of oncologic studies among investigators, and increases confidence in the significance of study results. Currently, there is minimal methodological standardization for assessing tumors in veterinary medicine, with few attempts to validate published protocols and grading schemes. The current article attempts to address these shortcomings by providing standard guidelines for tumor assessment parameters and protocols for evaluating specific tumor types. More detailed information is available in the Supplemental Files, the intention of which is 2-fold: publication as part of this commentary, but more importantly, these will be available as “living documents” on a website ( www.vetcancerprotocols.org ), which will be updated as new information is presented in the peer-reviewed literature. Our hope is that veterinary pathologists will agree that this initiative is needed, and will contribute to and utilize this information for routine diagnostic work and oncologic studies. Journal editors and reviewers can utilize checklists to ensure publications include sufficient detail and standardized methods of tumor assessment. To maintain the relevance of the guidelines and protocols, it is critical that the information is periodically updated and revised as new studies are published and validated with the intent of providing a repository of this information. Our hope is that this initiative (a continuation of efforts published in this journal in 2011) will facilitate collaboration and reproducibility between pathologists and institutions, increase case numbers, and strengthen clinical research findings, thus ensuring continued progress in veterinary oncologic pathology and improving patient care.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sievert_feasibility_2021,

title = {Feasibility of intraoperative assessment of safe surgical margins during laryngectomy with confocal laser endomicroscopy: A pilot study},

author = {Matti Sievert and Nicolai Oetter and Marc Aubreville and Florian Stelzle and Andreas Maier and Markus Eckstein and Konstantinos Mantsopoulos and Antoniu-Oreste Gostian and Sarina K Mueller and Michael Koch and Abbas Agaimy and Heinrich Iro and Miguel Goncalves},

url = {https://linkinghub.elsevier.com/retrieve/pii/S0385814621000237},

doi = {10.1016/j.anl.2021.01.005},

issn = {03858146},

year  = {2021},

date = {2021-08-01},

urldate = {2023-06-30},

journal = {Auris Nasus Larynx},

volume = {48},

number = {4},

pages = {764–769},

keywords = {},

pubstate = {published},

tppubtype = {article}

}