Publications

@article{rosbach_cognitive_2026,

title = {Cognitive biases in AI–assisted medical decision making: A structured review as a primer for veterinary and human pathology},

author = {Emely Rosbach and Jonas Ammeling and Christof A. Bertram and Andreas Riener and Marc Aubreville},

url = {https://journals.sagepub.com/doi/10.1177/03009858261472493},

doi = {10.1177/03009858261472493},

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

year  = {2026},

date = {2026-08-01},

urldate = {2026-08-06},

journal = {Veterinary Pathology},

pages = {03009858261472493},

abstract = {Cognitive biases are systematic patterns of error in human thinking. While artificial intelligence (AI)-based decision support systems offer great potential to enhance diagnostic accuracy and efficiency in pathology, collaboration between medical professionals and AI can also introduce or amplify these biases. This review aims to identify cognitive biases and their modes of manifestation in human-computer interaction (HCI) within pathology and to extrapolate potential manifestations of biases not yet explored in this domain but reported in HCIs across other medical specialties. We conducted a structured literature review (19 August 2025) across the ACM, IEEE, and PubMed databases. Studies were eligible if they operationalized cognitive biases during expert–machine interaction in diagnostic decision-making using qualitative or quantitative methods, including review articles citing primary studies that met these criteria. The final corpus comprised 24 studies (8 primary studies and 16 review articles). From these review articles, 18 additional primary studies were extracted and used in their place solely for analysis purposes. A narrative synthesis of the identified primary research revealed 12 cognitive biases reported in AI-assisted medical decision-making, with only one study originating from pathology. For each bias, definitions and hypothetical pathology-specific examples were derived. This review is intended as a primer for the veterinary and human pathology communities and strives to contribute to the safe and effective integration of AI into diagnostic practice.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bertram_performance_2026,

title = {Performance evaluation of deep learning models for image analysis: Considerations for visual assessment and statistical metrics},

author = {Christof A. Bertram and Jonas Ammeling and Alexander Bartel and Gillian Beamer and Marc Aubreville},

url = {https://journals.sagepub.com/doi/10.1177/03009858261461760},

doi = {10.1177/03009858261461760},

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

year  = {2026},

date = {2026-07-01},

urldate = {2026-07-07},

journal = {Veterinary Pathology},

pages = {03009858261461760},

abstract = {Deep learning-based automated image analysis (DL-AIA) has been shown to outperform trained pathologists in tasks related to feature quantification. Related to these capabilities, the use of DL-AIA tools is currently extending from proof-of-principle studies to routine applications, including the evaluation of patient samples (diagnostic pathology), regulatory safety assessment (toxicologic pathology), and recurrent research tasks. To ensure that DL-AIA applications are safe and reliable, it is critical to conduct a thorough and objective generalization performance assessment to evaluate an algorithm’s ability to accurately predict patterns of interest and possibly evaluate model robustness (ie, the algorithm’s capacity to maintain predictive accuracy on images from different sources). In this article, we review the practices for performance assessment in veterinary pathology publications by which 2 main approaches were identified: (1) exclusive visual performance assessment (ie, eyeballing algorithmic predictions) plus validation of the model’s application utilizing secondary performance indices and (2) statistical performance assessment (alongside other methods), which requires creation of a test set with ground truth labels that is a hold-out from model development. This article compares the strengths and weaknesses of statistical and visual performance assessment methods. Furthermore, we discuss relevant considerations for rigorous statistical performance evaluation including metric selection, test data set image composition, ground truth label quality, resampling methods such as bootstrapping, statistical comparison of multiple models, and evaluation of model stability. It is our conclusion that visual and statistical evaluation have complementary strengths and a combined approach provides the greatest insight into the DL model’s performance and sources of error.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bertram_intratumoral_2026,

title = {Intratumoral distribution of anisokaryosis in canine cutaneous mast cell tumors},

author = {Christof A. Bertram and Frauke Wilm and Eda Parlak and Taryn A. Donovan and Hannah Janout and Pompei Bolfa and Michael J. Dark and Andrea Fuchs-Baumgartinger and Andrea Klang and Robert Klopfleisch and Barbara Richter and Marc Aubreville and Stephan M. Winkler and Matti Kiupel and Alexander Bartel},

url = {https://journals.sagepub.com/doi/10.1177/03009858261465447},

doi = {10.1177/03009858261465447},

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

year  = {2026},

date = {2026-07-01},

urldate = {2026-07-14},

journal = {Veterinary Pathology},

pages = {03009858261465447},

abstract = {Automated measurements of anisokaryosis in canine cutaneous mast cell tumors (ccMCTs) have been shown to be predictive of survival, but questions remain regarding the intratumoral distribution of anisokaryosis. Whole-slide images of 96 ccMCTs were analyzed with a deep learning-based segmentation algorithm to quantify anisokaryosis using the standard deviation (SD) of the nuclear area. In 35/96 cases, >5% of the non-overlapping 256 × 256 µm 

 2 

 regions were hotspots (SD ≥11.5 µm 

 2 

 ). Regions selected by 7 pathologists within these 35 cases matched hotspots in 32% of the instances. Outcome analysis (tumor-related death) based on single tumor regions yielded an area under the curve (AUC) of 0.901 for pathologist-selected hotspots, falling between random region selection (AUC: 0.862) and 90th-percentile targeted selection (AUC: 0.956). Whole-slide analysis of the hotspot proportion predicted survival with an AUC of 0.956, with 20% of hotspots as a prognostically meaningful threshold. Whereas pathologists-selected tumor regions are prognostically meaningful for nuclear morphometry, whole-slide analysis may provide additional prognostic information.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{banerjee_reporting_2026,

title = {Reporting transparency in veterinary pathology deep learning: A systematic review of reproducibility-critical details},

author = {Sweta Banerjee and Christof A. Bertram and Viktoria Weiss and Jonas Ammeling and Thomas Conrad and Nils Porsche and Robert Klopfleisch and Christoph Stroblberger and Christopher Kaltenecker and Katharina Breininger and Marc Aubreville},

url = {https://journals.sagepub.com/doi/10.1177/03009858261459452},

doi = {10.1177/03009858261459452},

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

year  = {2026},

date = {2026-06-01},

urldate = {2026-06-30},

journal = {Veterinary Pathology},

pages = {03009858261459452},

abstract = {Whereas reproducibility of studies is a prerequisite for trustworthy deep learning (DL) in veterinary histopathology and microscopy, the actual degree of methodological transparency that exists in the literature remains uncertain. We performed a Preferred Reporting Items for Systematic Reviews and Meta-Analyses-guided systematic review to quantify the degree to which supervised DL and supervised machine learning studies report reproducibility-critical details. Using a veterinary-journal-restricted Boolean search executed in PubMed and Scopus, we screened 180 unique records and included 50 primary research articles for full-text analysis. Based on a recently published guideline for the development of DL models in veterinary pathology, we extracted information for each study across 5 dimensions: (1) study and task characterization, (2) data transparency, (3) experimental design and data-leakage control, (4) model and training details, and (5) performance evaluation and reporting. Among the included studies, private data sets predominated, with 90% of studies relying on private data. Sharing of code was uncommon (3%). Key training details such as augmentation and hyperparameters were often incompletely reported; augmentation was not reported in 56% of studies, and key hyperparameters were absent in 40% of studies. It was often not clear whether patient-level stratification (necessary to avoid data leakage) was performed. In summary, these results highlight major deficits in the reporting of details and experimental design necessary for reproducing DL results in veterinary histopathology. This review provides a practical baseline and reporting roadmap to support more transparent and reproducible research in veterinary computational pathology.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bertram_data_2026,

title = {Data set creation for supervised deep learning–based analysis of microscopic images: Review of important considerations and recommendations},

author = {Christof A. Bertram and Viktoria Weiss and Jonas Ammeling and F. Maria Schabel and Taryn A. Donovan and Frauke Wilm and Christian Marzahl and Katharina Breininger and Marc Aubreville},

url = {https://journals.sagepub.com/doi/10.1177/03009858261457959},

doi = {10.1177/03009858261457959},

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

year  = {2026},

date = {2026-06-01},

urldate = {2026-06-30},

journal = {Veterinary Pathology},

pages = {03009858261457959},

abstract = {Supervised deep learning (DL) receives great interest for automated analysis of microscopic images with an increasing body of literature supporting its potential. The development and testing of those DL models rely heavily on the availability of high-quality, large-scale data sets. However, creating such data sets is a complex and resource-intensive process, often hindered by challenges such as time constraints, domain variability, and risks of bias in image collection and label creation. This review provides a comprehensive guide to the critical steps in data set creation, including (1) image acquisition, (2) selection of annotation software, and (3) annotation creation. For image acquisition, besides ensuring a sufficiently large number, it is important to address sources of image variability (domain shifts), such as those related to slide preparation and digitization, that could lead to algorithmic errors if not adequately represented in the training data. For annotations, key quality criteria are the 3 “C”s: correctness, consistency, and completeness. For mitigation of annotation bias of a single annotator, this review explores advanced annotation methods (eg, computer-assisted annotations). To support data set creators, a standard operating procedure is provided as supplemental material, summarizing all important considerations for data set creation. Furthermore, this article underscores the importance of open data sets in driving innovation and enhancing reproducibility of DL research. By addressing the challenges and offering practical recommendations, this review aims to advance the creation and availability of high-quality, large-scale data sets, ultimately contributing to the development of generalizable and robust DL models for pathology applications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rosbach_stuck_2026,

title = {Stuck on Suggestions: Automation Bias, the Anchoring Effect, and the Factors That Shape Them in Computational Pathology},

author = {Emely Rosbach and Jonas Ammeling and Jonathan Ganz and Christof A. Bertram and Thomas Conrad and Andreas Riener and Marc Aubreville},

doi = {https://doi.org/10.59275/j.melba.2026-87b1},

year  = {2026},

date = {2026-03-01},

journal = {Machine Learning for Biomedical Imaging},

volume = {3},

number = {MELBA–BVM 2025 Special Issue},

pages = {126–147},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ivan_subphase-labeled_2026,

title = {A Subphase-Labeled Mitotic Dataset for AI-powered Cell Division Analysis},

author = {Zsanett Zsofia Ivan and Dominik Hirling and Istvan Grexa and Jonas Ammeling and Csaba Molnar and Tamas Micsik and Katalin Dobra and Levente Kuthi and Farkas Sukosd and Janos Fillinger and Judit Moldvay and Erika Toth and Marc Aubreville and Vivien Miczan and Peter Horvath},

url = {https://www.nature.com/articles/s41597-026-07007-7},

doi = {10.1038/s41597-026-07007-7},

issn = {2052-4463},

year  = {2026},

date = {2026-03-01},

urldate = {2026-03-21},

journal = {Scientific Data},

abstract = {Abstract 

 Mitosis detection represents a critical task in digital pathology, as it plays an important role in the tumor grading and prognosis of patients. Manual determination is a labor-intensive task for practitioners with high interobserver variability, thus, automation is a priority. There has been substantial progress towards creating robust mitosis detection algorithms, primarily driven by the Mitosis Domain Generalization (MIDOG) challenges. Also, there has been growing interest in the molecular characterization of mitosis to achieve a more comprehensive understanding of its underlying mechanisms in a subphase-specific manner. We introduce a new mitotic figure dataset annotated with subphase information based on the MIDOG++ dataset as well as a previously unrepresented tumor domain to enhance the diversity and applicability. We envision a new perspective for domain generalization by improving model performance with subtyping mitosis, complemented with an atypical mitotic class. Our work has implications in two main areas: subtyping information can provide helpful information in mitosis detection, while also providing promising new directions in answering biological questions, such as molecular analysis of subphases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{muller-diesing_optical_2026,

title = {Optical biopsy of nasal cavity cancer with confocal laser endomicroscopy – a pilot study},

author = {Flurin Müller-Diesing and Matti Sievert and Bharat Akhanda Panuganti and Marc Aubreville and Nils Porsche and Stephan Hackenberg and Manuel Stöth and Agmal Scherzad and Markus Wirth and Philipp Winnand and Miguel Goncalves},

url = {https://link.springer.com/10.1007/s00405-025-09968-8},

doi = {10.1007/s00405-025-09968-8},

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

year  = {2026},

date = {2026-03-01},

urldate = {2026-05-19},

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

volume = {283},

number = {3},

pages = {1763–1770},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{muller-diesing_feasibility_2026,

title = {Feasibility of confocal laser endomicroscopy as an optical biopsy method for SCC on the auricle : an exploratory study},

author = {Flurin Müller-Diesing and Matti Sievert and Bharat Akhanda Panuganti and Marc Aubreville and Nils Porsche and Stephan Hackenberg and Manuel Stöth and Agmal Scherzad and Jasper Meyer and Markus Wirth and Miguel Goncalves},

url = {https://link.springer.com/10.1007/s10006-026-01506-y},

doi = {10.1007/s10006-026-01506-y},

issn = {1865-1569},

year  = {2026},

date = {2026-01-01},

urldate = {2026-02-01},

journal = {Oral and Maxillofacial Surgery},

volume = {30},

number = {1},

pages = {21},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ammeling_benchmarking_2026,

title = {Benchmarking Foundation Models for Mitotic Figure Classification},

author = {Jonas Ammeling and Jonathan Ganz and Emely Rosbach and Ludwig Lausser and Christof A. Bertram and Katharina Breininger and Marc Aubreville},

url = {https://melba-journal.org/2026:003},

doi = {10.59275/j.melba.2026-a3eb},

issn = {2766-905X},

year  = {2026},

date = {2026-01-01},

urldate = {2026-02-01},

journal = {Machine Learning for Biomedical Imaging},

volume = {3},

number = {MELBA–BVM 2025 Special Issue},

pages = {38–55},

abstract = {The performance of deep learning models is known to scale with data quantity and diversity. In pathology, as in many other medical imaging domains, the availability of labeled images for a specific task is often limited. Self-supervised learning techniques have enabled the use of vast amounts of unlabeled data to train large-scale neural networks, i.e., foundation models, that can address the limited data problem by providing semantically rich feature vectors that can generalize well to new tasks with minimal training effort increasing model performance and robustness. In this work, we investigate the use of foundation models for mitotic figure classification. The mitotic count, which can be derived from this classification task, is an independent prognostic marker for specific tumors and part of certain tumor grading systems. In particular, we investigate the data scaling laws on multiple current foundation models and evaluate their robustness to unseen tumor domains. Next to the commonly used linear probing paradigm, we also adapt the models using low-rank adaptation (LoRA) of their attention mechanisms. We compare all models against end-to-end-trained baselines, both CNNs and Vision Transformers. Our results demonstrate that LoRA-adapted foundation models provide superior performance to those adapted with standard linear probing, reaching performance levels close to 100 % data availability with only 10 % of training data. Furthermore, LoRA-adaptation of the most recent foundation models almost closes the out-of-domain performance gap when evaluated on unseen tumor domains. However, full fine-tuning of traditional architectures still yields competitive performance.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{banerjee_benchmarking_2026,

title = {Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation},

author = {Sweta Banerjee and Viktoria Weiss and Taryn A. Donovan and Rutger H. J. Fick and Thomas Conrad and Jonas Ammeling and Nils Porsche and Robert Klopfleisch and Christopher Kaltenecker and Katharina Breininger and Marc Aubreville and Christof A Bertram},

doi = {https://doi.org/10.59275/j.melba.2026-6c1g},

year  = {2026},

date = {2026-01-01},

journal = {Machine Learning for Biomedical Imaging},

number = {MELBA–BVM 2025 Special Issue},

pages = {115–125},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{keshvarikhojasteh_beyond_2025,

title = {Beyond accuracy: Quantifying the reliability of multiple instance learning for whole slide image classification},

author = {Hassan Keshvarikhojasteh and Marc Aubreville and Christof A. Bertram and Josien P. W. Pluim and Mitko Veta},

editor = {Elnaz Pashaei},

url = {https://dx.plos.org/10.1371/journal.pone.0337261},

doi = {10.1371/journal.pone.0337261},

issn = {1932-6203},

year  = {2025},

date = {2025-12-01},

urldate = {2025-12-06},

journal = {PLOS One},

volume = {20},

number = {12},

pages = {e0337261},

abstract = {Machine learning models have become integral to many fields, but their reliability, defined as producing dependable, trustworthy, and domain-consistent predictions, remains a critical concern. Multiple Instance Learning (MIL) models designed for Whole Slide Image (WSI) classification in computational pathology are rarely evaluated in terms of reliability, leaving a key gap in understanding their suitability for high-stakes applications like clinical decision-making. In this paper, we address this gap by introducing three quantitative metrics for reliability assessment and applying them to several widely used MIL architectures across three region-wise annotated pathology datasets. Our findings indicate that the mean pooling instance (MEAN-POOL-INS) model demonstrates superior reliability compared to other networks, despite its simple architectural design and computational efficiency. These findings underscore the need of reliability evaluation alongside predictive performance in MIL models and establish MEAN-POOL-INS as a strong, trustworthy baseline for future research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{puget_artificial_2025,

title = {Artificial intelligence predicts textitc-KIT exon 11 genotype by phenotype in canine cutaneous mast cell tumors: Can human observers learn it?},

author = {Chloé Puget and Jonathan Ganz and Christof A. Bertram and Thomas Conrad and Malte Baeblich and Anne Voss and Katharina Landmann and Alexander F. H. Haake and Andreas Spree and Svenja Hartung and Leonore Aeschlimann and Sara Soto and Simone De Brot and Martina Dettwiler and Heike Aupperle-Lellbach and Pompei Bolfa and Alexander Bartel and Matti Kiupel and Katharina Breininger and Marc Aubreville and Robert Klopfleisch},

url = {https://journals.sagepub.com/doi/10.1177/03009858251380284},

doi = {10.1177/03009858251380284},

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

year  = {2025},

date = {2025-10-01},

urldate = {2025-10-09},

journal = {Veterinary Pathology},

pages = {03009858251380284},

abstract = {Canine cutaneous mast cell tumors (ccMCTs) are frequent neoplasms with variable biological behaviors. Internal tandem duplication mutations in 

 c-KIT 

 exon 11 ( 

 c-KIT 

 -11-ITD) are associated with poor prognosis but predict therapeutic response to tyrosine kinase inhibitors. In a previous work, deep learning algorithms managed to predict the presence of 

 c-KIT 

 -11-ITD on digitalized hematoxylin and eosin-stained histological slides (whole-slide images, WSIs) in up to 87% of cases, suggesting the existence of morphological features characterizing ccMCTs carrying 

 c-KIT 

 -11-ITD. This 3-stage blinded study aimed to identify morphological features indicative of 

 c-KIT 

 -11-ITD and to evaluate the ability of human observers to learn this task. 17 untrained pathologists first classified 8 WSIs and 200 image patches (highly relevant for algorithmic classification) of ccMCTs as either positive or negative for 

 c-KIT 

 -11-ITD. Second, they self-trained to recognize 

 c-KIT 

 -11-ITD by looking at the same WSIs and patches correctly sorted. Third, pathologists classified 15 new WSIs and 200 new patches according to 

 c-KIT 

 -11-ITD status. In addition, participants reported microscopic features they considered relevant for their decision. Without training, participants correctly classified the 

 c-KIT 

 -11-ITD status of 63%–88% of WSIs and 43%–55% of patches. With self-training, 25%–38% of WSIs and 55%–56% of patches were correctly classified. High cellular pleomorphism, anisokaryosis, and sparse cytoplasmic granulation were commonly suggested as features associated with 

 c-KIT 

 -11-ITD-positive ccMCTs, none of which showed reliable predictivity in a follow-up study. The results indicate that transfer of algorithmic skills to the human observer is difficult. A 

 c-KIT 

 -11-ITD-specific morphological feature remains to be extracted from the artificial intelligence model.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{bertram_reporting_2025,

title = {Reporting guidelines for manuscripts that use artificial intelligence–based automated image analysis in Vetarinary Pathology},

author = {Christof A. Bertram and Melissa Schutten and Lorenzo Ressel and Katharina Breininger and Joshua D. Webster and Marc Aubreville},

url = {https://journals.sagepub.com/doi/10.1177/03009858251344320},

doi = {10.1177/03009858251344320},

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

year  = {2025},

date = {2025-09-01},

urldate = {2025-09-01},

journal = {Veterinary Pathology},

volume = {62},

number = {5},

pages = {615–617},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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 = {2025-08-01},

urldate = {2025-04-16},

journal = {IEEE Transactions on Medical Imaging},

volume = {44},

number = {8},

pages = {3162–3174},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ammeling_interdisciplinary_2025,

title = {An interdisciplinary perspective on AI-supported decision making in medicine},

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

url = {https://linkinghub.elsevier.com/retrieve/pii/S0160791X24003397},

doi = {10.1016/j.techsoc.2024.102791},

issn = {0160791X},

year  = {2025},

date = {2025-06-01},

urldate = {2024-12-08},

journal = {Technology in Society},

volume = {81},

pages = {102791},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{thesing_characterization_2025,

title = {Characterization of irradiated mucosa using confocal laser endomicroscopy in the upper aerodigestive tract},

author = {Lisa Thesing and Matti Sievert and Bharat Akhanda Panuganti and Marc Aubreville and Till Meyer and Flurin Müller-Diesing and Agmal Scherzad and Stephan Hackenberg and Miguel Goncalves},

url = {https://link.springer.com/10.1007/s00405-025-09318-8},

doi = {10.1007/s00405-025-09318-8},

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

year  = {2025},

date = {2025-05-01},

urldate = {2025-11-06},

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

volume = {282},

number = {5},

pages = {2507–2514},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{wilm_domanenubergreifende_2025-1,

title = {Domänenübergreifende Generalisierbarkeit von Deep Learning-basierten Bildanalysealgorithmen in der HistopathologieCross-Domain Generalization of Deep Learning-Based Image Analysis Algorithms in Histopathology},

author = {Frauke Wilm},

url = {https://open.fau.de/handle/openfau/35170},

doi = {10.25593/OPEN-FAU-1699},

year  = {2025},

date = {2025-01-01},

urldate = {2025-05-10},

publisher = {Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)},

abstract = {The visual assessment of microscopic samples by pathologists constitutes an essential component of cancer diagnostics. Traditional pathology workflows were based on the visual assessment of samples under the microscope. The development of designated slide scanners has facilitated the digitization of microscopy samples which not only allowed for digital archiving and remote expert consultancy but also facilitated the use of machine learning-based image analysis algorithms for computer-aided diagnosis. Meanwhile, a wide range of computer-aided systems has been developed in the field of histopathology, often matching the performance of trained pathologists. Previous work has shown that machine learning-based image analysis algorithms, and especially convolutional neural networks, can be very susceptible to changes in the visual appearance of images. In pathology, these textbackslashemphdomain shifts can be caused when applying trained algorithms to different morphologies, or samples prepared at a different pathology lab. The preparation of histologic samples follows routine stages, including tissue fixation, dehydration, paraffin embedding, and microtome sectioning. Subsequently, a sample is usually stained with a specific dye and digitized with a designated scanning system. The visual manifestation of these sample preparation steps can be very unique for the respective pathology lab. This thesis investigates the impact of different domain shifts on the performance of convolutional neural networks in histopathology. For these experiments, three routine tasks in cancer diagnostics were considered: cross-scanner mitotic figure detection, cross-domain tumor segmentation, and pan-tumor T-lymphocyte detection on immunohistochemistry samples. For the task of cross-scanner mitotic figure detection, domain adversarial training was employed. Evaluations of the learned embeddings demonstrated the successful extraction of scanner-agnostic features. For the task of cross-domain tumor segmentation, representation learning and, in particular, self-supervised learning was explored as a pre-training strategy to align feature embeddings across domains and thereby enhance the domain agnosticity for the downstream task. The results provide insights into the applicability of self-supervised learning in the context of histopathology. To date, this technique has mostly been employed in the field of natural images. In a project addressing the detection of tumor-infiltrating lymphocytes in immunohistochemistry samples, fine-tuning was leveraged to bridge the domain gap between different tumor indications. Initial experiments exhibited degraded performance on out-of-distribution samples. By exploiting fine-tuning on a limited number of target domain samples, this degradation was effectively mitigated. The experiments allowed for recommendations on the development of robust algorithms for the detection of lymphocytes across different tumor morphologies. In the course of the thesis, several cross-domain datasets were curated, focusing on different sources of domain shift. This includes a fully annotated dataset of 350 whole slide images covering seven canine cutaneous tumor subtypes, which constitutes one of the most comprehensive open histopathology segmentation datasets to date. A high annotation quality of each published dataset was ensured through extensive multi-rater experiments on selected subsets of the data. By making these datasets publicly available, future work on the cross-domain generalization for histopathology was facilitated.},

note = {Publisher: Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ammeling_interdisciplinary_2024,

title = {An Interdisciplinary Perspective on AI-Supported Decision Making in Medicine},

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

url = {https://linkinghub.elsevier.com/retrieve/pii/S0160791X24003397},

doi = {10.1016/j.techsoc.2024.102791},

issn = {0160791X},

year  = {2024},

date = {2024-12-01},

urldate = {2024-12-06},

journal = {Technology in Society},

pages = {102791},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@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}

}