arXiv subjects

Christof A. Bertram

Publications and source records attributed to Christof A. Bertram.

At least 19 recordsLinked to original sources

arXiv2026

Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures

Pathology foundation models (FMs) are models trained on vast amounts of typically unlabeled data and have been shown to yield regularized latent spaces that can be used effectively in downstream classification tasks. This is also true for the classification of mitotic figures vs. other cells. However, it is so far unclear if the latent space of current FMs provides features that are discriminant and spatially suitably resolved to also serve as a backbone for dense object detection paradigms. In this work, we investigate this question for common current pathology FMs (UNI, UNI2-h, Virchow, Virchow2, H-optimus-0, H-optimus-1) and compare their performance against a fully end-to-end trained baseline based on a ResNet50 architecture. We combine FM backbones with representatives of single stage, dual stage and self-attention-based detectors (RetinaNet, Faster R-CNN, Deformable DETR respectively) on the multi-domain MIDOG++ dataset, and on the TUPAC16 dataset as an out-of-domain case. We show that the H-optimus-0 and Virchow models yielded competitive performance, indicating that the latent spaces of current FMs, all trained on image-level self-supervision, are suitable for direct mitotic figure detection and may be slightly more robust on our out-of-domain test case. All code is made available publicly at https://github.com/DeepMicroscopy/FM4MFdet.

cs.CV↗

arXiv2026

Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge

Automated mitosis detection is a well-established task in computational pathology. While previous benchmarks focused on scanner-induced domain shift, clinical "real-world" application requires models to be robust across the vast variance to be expected in the histological landscape. The MItosis DOmain Generalization (MIDOG) 2025 challenge was designed to evaluate algorithmic performance across unprecedented biological and contextual diversity. We curated a test dataset of 365 cases, encompassing 12 distinct human, canine and feline tumor types, digitized across multiple scanning platforms. Moving beyond hand-selected hotspots, the challenge required detection also in random tissue areas (representative of the whole slide detection situation) and challenging areas (areas rich in hard negatives). In the second track, we introduced the classification of atypical mitotic figures (AMFs). There were 18 teams submitting to the detection track, with F1 scores ranging up to 0.740. In the AMF detection track, we had 21 submissions with balanced accuracy values up to 0.908. Our analysis reveals that while most models perform reliably in traditional hotspots, significant performance degradation occurs in challenging ROIs, where false positive rates tripled. Furthermore, performance varied significantly across the 12 tumor types, highlighting "blind spots" in current state-of-the-art architectures when encountering rare or highly pleomorphic malignancies. Moreover, we evaluated the effectiveness of ensembling and found a mean increases of 1.5 and 1.3 percentage points in F1 score and balanced accuracy, respectively. In contrast, TTA showed no relevant improvement. MIDOG 2025 demonstrates that "in the wild" mitosis detection remains a significant hurdle. The transition from hotspot-only evaluation to a multi-contextual framework provides a more realistic proxy for clinical reliability.

cs.CV↗

arXiv2026

Benchmarking Deep Learning and Vision Foundation Models for Atypical vs. Normal Mitosis Classification with Cross-Dataset Evaluation

Atypical mitosis marks a deviation in the cell division process that has been shown be an independent prognostic marker for tumor malignancy. However, atypical mitosis classification remains challenging due to low prevalence, at times subtle morphological differences from normal mitotic figures, low inter-rater agreement among pathologists, and class imbalance in datasets. Building on the Atypical Mitosis dataset for Breast Cancer (AMi-Br), this study presents a comprehensive benchmark comparing deep learning approaches for automated atypical mitotic figure (AMF) classification, including end-to-end trained deep learning models, foundation models with linear probing, and foundation models fine-tuned with low-rank adaptation (LoRA). For rigorous evaluation, we further introduce two new held-out AMF datasets - AtNorM-Br, a dataset of mitotic figures from the TCGA breast cancer cohort, and AtNorM-MD, a multi-domain dataset of mitotic figures from a subset of the MIDOG++ training set. We found average balanced accuracy values of up to 0.8135, 0.7788, and 0.7723 on the in-domain AMi-Br and the out-of-domain AtNorm-Br and AtNorM-MD datasets, respectively. Our work shows that atypical mitotic figure classification, while being a challenging problem, can be effectively addressed through the use of recent advances in transfer learning and model fine-tuning techniques. We make all code and data used in this paper available in this github repository: https://github.com/DeepMicroscopy/AMi-Br_Benchmark.

cs.CV↗

arXiv2026

Performance evaluation of deep learning models for image analysis: considerations for visual control and statistical metrics

Deep learning-based automated image analysis (DL-AIA) has been shown to outperform trained pathologists in tasks related to feature quantification. Related to these capacities the use of DL-AIA tools is currently extending from proof-of-principle studies to routine applications such as 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 (i.e., the ability of the algorithm to accurately predict patterns of interest) and possibly evaluate model robustness (i.e., 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 two approaches were identified: 1) Exclusive visual performance control (i.e. eyeballing of algorithmic predictions) plus validation of the models application utilizing secondary performance indices, and 2) Statistical performance control (alongside the other methods), which requires a dataset creation and separation of an hold-out test set prior to model training. This article compares the strengths and weaknesses of statistical and visual performance control methods. Furthermore, we discuss relevant considerations for rigorous statistical performance evaluation including metric selection, test dataset 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 strength and a combination of both provides the greatest insight into the DL model's performance and sources of error.

cs.CV↗

arXiv2026

Benchmarking Foundation Models for Mitotic Figure Classification

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.

cs.CV↗

arXiv2025

Beyond accuracy: quantifying the reliability of Multiple Instance Learning for Whole Slide Image classification

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.

cs.CV↗

arXiv2025

Dataset creation for supervised deep learning-based analysis of microscopic images -- review of important considerations and recommendations

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 validation of those DL models relies heavily on the availability of high-quality, large-scale datasets. However, creating such datasets 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 dataset creation, including: 1) image acquisition, 2) selection of annotation software, and 3) annotation creation. In addition to ensuring a sufficiently large number of images, it is crucial 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. Key quality criteria for annotations are the three "C"s: correctness, completeness, and consistency. This review explores methods to enhance annotation quality through the use of advanced techniques that mitigate the limitations of single annotators. To support dataset creators, a standard operating procedure (SOP) is provided as supplemental material, outlining best practices for dataset development. Furthermore, the article underscores the importance of open datasets in driving innovation and enhancing reproducibility of DL research. By addressing the challenges and offering practical recommendations, this review aims to advance the creation of and availability to high-quality, large-scale datasets, ultimately contributing to the development of generalizable and robust DL models for pathology applications.

cs.CV↗

arXiv2025

Exploring General-Purpose Autonomous Multimodal Agents for Pathology Report Generation

Recent advances in agentic artificial intelligence, i.e. systems capable of autonomous perception, reasoning, and tool use, offer new opportunities for digital pathology. In this pilot study, we evaluate whether two agentic multimodal AI systems (OpenAI's ChatGPT 5.0 in agentic mode, and H Company's Surfer) can autonomously navigate, describe, and interpret histopathologic features in digitized tissue slides on a slide viewing platform. A set of 35 veterinary pathology cases, curated for training purposes, was used as the test dataset. The agent was tasked with autonomously exploring whole-slide images using a web-based slide viewer, identifying salient tissue structures, generating descriptive summaries, and proposing provisional diagnoses. We fed different prompts to explore three scenarios: 1) analysis without knowledge of the signalment, 2) analysis with organ and species provided, and 3) diagnosis based on a morphological description provided. All outputs were reviewed and validated by a board-certified pathologist for accuracy and diagnostic consistency. We further tasked another board-certified pathologist with the same task to establish a baseline. We found the systems to yield accurate diagnoses in up to 28.6% of cases with only images, signalment and organ provided, and up to 68.6% when a morphological description was provided. With only the WSI provided, the models were only correct in up to 5.7% of cases. The human expert, on the other hand, achieved 85.7% diagnostic accuracy with only a single WSI, and 88.6% when also signalment and organ was provided. The study demonstrates that while the agentic AI system can meaningfully engage with web-based slide viewing software to assess complex visual pathology data and produce contextually aligned feature descriptions, diagnostic precision remains limited compared with a human expert.

cs.HC↗

arXiv2025

SWAN -- Enabling Fast and Mobile Histopathology Image Annotation through Swipeable Interfaces

The annotation of large scale histopathology image datasets remains a major bottleneck in developing robust deep learning models for clinically relevant tasks, such as mitotic figure classification. Folder-based annotation workflows are usually slow, fatiguing, and difficult to scale. To address these challenges, we introduce SWipeable ANnotations (SWAN), an open-source, MIT-licensed web application that enables intuitive image patch classification using a swiping gesture. SWAN supports both desktop and mobile platforms, offers real-time metadata capture, and allows flexible mapping of swipe gestures to class labels. In a pilot study with four pathologists annotating 600 mitotic figure image patches, we compared SWAN against a traditional folder-sorting workflow. SWAN enabled rapid annotations with pairwise percent agreement ranging from 86.52% to 93.68% (Cohen's Kappa = 0.61-0.80), while for the folder-based method, the pairwise percent agreement ranged from 86.98% to 91.32% (Cohen's Kappa = 0.63-0.75) for the task of classifying atypical versus normal mitotic figures, demonstrating high consistency between annotators and comparable performance. Participants rated the tool as highly usable and appreciated the ability to annotate on mobile devices. These results suggest that SWAN can accelerate image annotation while maintaining annotation quality, offering a scalable and user-friendly alternative to conventional workflows.

cs.CV↗

arXiv2025

Histologic Dataset of Normal and Atypical Mitotic Figures on Human Breast Cancer (AMi-Br)

Assessment of the density of mitotic figures (MFs) in histologic tumor sections is an important prognostic marker for many tumor types, including breast cancer. Recently, it has been reported in multiple works that the quantity of MFs with an atypical morphology (atypical MFs, AMFs) might be an independent prognostic criterion for breast cancer. AMFs are an indicator of mutations in the genes regulating the cell cycle and can lead to aberrant chromosome constitution (aneuploidy) of the tumor cells. To facilitate further research on this topic using pattern recognition, we present the first ever publicly available dataset of atypical and normal MFs (AMi-Br). For this, we utilized two of the most popular MF datasets (MIDOG 2021 and TUPAC) and subclassified all MFs using a three expert majority vote. Our final dataset consists of 3,720 MFs, split into 832 AMFs (22.4%) and 2,888 normal MFs (77.6%) across all 223 tumor cases in the combined set. We provide baseline classification experiments to investigate the consistency of the dataset, using a Monte Carlo cross-validation and different strategies to combat class imbalance. We found an averaged balanced accuracy of up to 0.806 when using a patch-level data set split, and up to 0.713 when using a patient-level split.

cs.CV↗

arXiv2024

Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification

Foundation models (FMs), i.e., models trained on a vast amount of typically unlabeled data, have become popular and available recently for the domain of histopathology. The key idea is to extract semantically rich vectors from any input patch, allowing for the use of simple subsequent classification networks potentially reducing the required amounts of labeled data, and increasing domain robustness. In this work, we investigate to which degree this also holds for mitotic figure classification. Utilizing two popular public mitotic figure datasets, we compared linear probing of five publicly available FMs against models trained on ImageNet and a simple ResNet50 end-to-end-trained baseline. We found that the end-to-end-trained baseline outperformed all FM-based classifiers, regardless of the amount of data provided. Additionally, we did not observe the FM-based classifiers to be more robust against domain shifts, rendering both of the above assumptions incorrect.

cs.CV↗

arXiv2024

When Two Wrongs Don't Make a Right" -- Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology

Artificial intelligence (AI)-based decision support systems hold promise for enhancing diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration can introduce and amplify cognitive biases, such as confirmation bias caused by false confirmation when erroneous human opinions are reinforced by inaccurate AI output. This bias may worsen when time pressure, ubiquitously present in routine pathology, strains practitioners' cognitive resources. We quantified confirmation bias triggered by AI-induced false confirmation and examined the role of time constraints in a web-based experiment, where trained pathology experts (n=28) estimated tumor cell percentages. Our results suggest that AI integration may fuel confirmation bias, evidenced by a statistically significant positive linear-mixed-effects model coefficient linking AI recommendations mirroring flawed human judgment and alignment with system advice. Conversely, time pressure appeared to weaken this relationship. These findings highlight potential risks of AI use in healthcare and aim to support the safe integration of clinical decision support systems.

cs.HC↗

arXiv2024

On the Value of PHH3 for Mitotic Figure Detection on H&E-stained Images

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. Deep learning algorithms can standardize this task, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithm's performance. Unlike H&E, 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 stain alone, the use of this ground truth could potentially introduce 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. We found that the annotators' object-level agreement increased when using PHH3-assisted labeling. Subsequently, MF detectors were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models' performance. Additionally, a novel dual-stain MF detector was developed to investigate the interpretation-shift of PHH3-assisted labels used in H&E, which clearly outperformed single-stain detectors. However, the PHH3-assisted labels did not have a positive effect on solely H&E-based models. The high performance of our dual-input detector reveals an information mismatch between the H&E and PHH3-stained images as the cause of this effect.

cs.CV↗

arXiv2024

Nuclear Pleomorphism in Canine Cutaneous Mast Cell Tumors: Comparison of Reproducibility and Prognostic Relevance between Estimates, Manual Morphometry and Algorithmic Morphometry

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 (morphometry) can improve reproducibility, but 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 (ccMCT). We assessed the following nuclear evaluation methods for measurement accuracy, reproducibility, and prognostic utility: 1) anisokaryosis (karyomegaly) 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 a deep learning-based segmentation algorithm. The study dataset comprised 96 ccMCT with available outcome information. The study dataset comprised 96 ccMCT with available outcome information. Inter-rater reproducibility of karyomegaly estimates was low ($κ$ = 0.226), while it was good (ICC = 0.654) for practicable morphometry of the standard deviation (SD) of nuclear size. As compared to gold standard manual morphometry (AUC = 0.839, 95% CI: 0.701 - 0.977), the prognostic value (tumor-specific survival) of SDs of nuclear area for practicable manual morphometry (12 nuclei) and automated morphometry were high with an area under the ROC curve (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.

cs.CV↗

arXiv2024

Model-based Cleaning of the QUILT-1M Pathology Dataset for Text-Conditional Image Synthesis

The QUILT-1M dataset is the first openly available dataset containing images harvested from various online sources. While it provides a huge data variety, the image quality and composition is highly heterogeneous, impacting its utility for text-conditional image synthesis. We propose an automatic pipeline that provides predictions of the most common impurities within the images, e.g., visibility of narrators, desktop environment and pathology software, or text within the image. Additionally, we propose to use semantic alignment filtering of the image-text pairs. Our findings demonstrate that by rigorously filtering the dataset, there is a substantial enhancement of image fidelity in text-to-image tasks.

cs.CV↗

arXiv2024

Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge

Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert consensus and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an $F_1$ score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. However, we also found that domain characteristics not present in the training set (feline as new species, spindle cell shape as new morphology and a new scanner) led to small but significant decreases in performance. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, but with only minor changes in the order of participants in the ranking.

cs.CV↗

arXiv2023

Automated Volume Corrected Mitotic Index Calculation Through Annotation-Free Deep Learning using Immunohistochemistry as Reference Standard

The volume-corrected mitotic index (M/V-Index) was shown to provide prognostic value in invasive breast carcinomas. However, despite its prognostic significance, it is not established as the standard method for assessing aggressive biological behaviour, due to the high additional workload associated with determining the epithelial proportion. In this work, we show that using a deep learning pipeline solely trained with an annotation-free, immunohistochemistry-based approach, provides accurate estimations of epithelial segmentation in canine breast carcinomas. We compare our automatic framework with the manually annotated M/V-Index in a study with three board-certified pathologists. Our results indicate that the deep learning-based pipeline shows expert-level performance, while providing time efficiency and reproducibility.

eess.IV↗

arXiv2023

Systematic Review of Methods and Prognostic Value of Mitotic Activity. Part 2: Canine Tumors

One of the most relevant prognostication tests for tumors is cellular proliferation, which is most commonly measured by the mitotic activity in routine tumor sections. The goal of this systematic review is to scholarly analyze the methods and prognostic relevance of histologically measuring mitotic activity in canine tumors. A total of 137 articles that correlated the mitotic activity in canine tumors with patient outcome were identified through a systematic (PubMed and Scopus) and manual (Google Scholar) literature search and eligibility screening process. These studies determined the mitotic count (MC, number of mitotic figures per tumor area) in 126 instances, presumably the mitotic count (method not specified) in 6 instances and the mitotic index (MI, proportion of mitotic figures per tumor cells) in 5 instances. A particularly high risk of bias was identified in the available details of the MC methods and statistical analysis, which often did not quantify the prognostic discriminative ability of the MC and only reported p-values. A significant association of the MC with survival was found in 72/109 (66%) studies. However, survival was evaluated by at least three studies in only 7 tumor types/groups, of which a prognostic relevance is apparent for mast cell tumors of the skin, cutaneous melanoma and soft tissue sarcoma of the skin. None of the studies on the MI found a prognostic relevance. Further studies on the MC and MI with standardized methods are needed to prove the prognostic benefit of this test for further tumor types.

q-bio.SC↗