TY - JOUR A1 - Niederschweiberer, Moritz A1 - Schaefer, Patrick M. A1 - Singh, Larry N. A1 - Lausser, Ludwig A1 - Bhosale, Devyani A1 - Hesse, Raphael A1 - Calzia, Enrico A1 - Kestler, Hans A. A1 - Rueck, Angelika A1 - Wallace, Douglas A1 - Einem, Bjoern von A1 - Arnim, Christine A. F. von T1 - NADH Fluorescence Lifetime Imaging Microscopy Reveals Selective Mitochondrial Dysfunction in Neurons Overexpressing Alzheimer’s Disease–Related Proteins JF - Frontiers in Molecular Biosciences N2 - Alzheimer’s disease (AD), the most prevalent form of dementia, affects globally more than 30 million people suffering from cognitive deficits and neuropsychiatric symptoms. Substantial evidence for the involvement of mitochondrial dysfunction in the development and/or progression of AD has been shown in addition to the pathological hallmarks amyloid beta (Aβ) and tau. Still, the selective vulnerability and associated selective mitochondrial dysfunction cannot even be resolved to date. We aimed at optically quantifying mitochondrial function on a single-cell level in primary hippocampal neuron models of AD, unraveling differential involvement of cell and mitochondrial populations in amyloid precursor protein (APP)-associated mitochondrial dysfunction. NADH lifetime imaging is a highly sensitive marker-free method with high spatial resolution. However, deciphering cellular bioenergetics of complex cells like primary neurons has still not succeeded yet. To achieve this, we combined highly sensitive NADH lifetime imaging with respiratory inhibitor treatment, allowing characterization of mitochondrial function down to even the subcellular level in primary neurons. Measuring NADH lifetime of the same neuron before and after respiratory treatment reveals the metabolic delta, which can be taken as a surrogate for cellular redox capacity. Correlating NADH lifetime delta with overexpression strength of Aβ-related proteins on the single-cell level, we could verify the important role of intracellular Aβ-mediated mitochondrial toxicity. Subcellularly, we could demonstrate a higher respiration in neuronal somata in general than dendrites, but a similar impairment of somatic and dendritic mitochondria in our AD models. This illustrates the power of NADH lifetime imaging in revealing mitochondrial function on a single and even subcellular level and its potential to shed light into bioenergetic alterations in neuropsychiatric diseases and beyond. UR - https://doi.org/10.3389/fmolb.2021.671274 KW - mitochondria KW - energy metabolism KW - Alzheimer’s disease KW - NADH KW - redox imaging KW - amyloid beta Y1 - 2021 UR - https://doi.org/10.3389/fmolb.2021.671274 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27224 SN - 2296-889X N1 - Section: Molecular Diagnostics and Therapeutics VL - 8 PB - Frontiers CY - Lausanne ER - TY - JOUR A1 - Kraus, Johann M. A1 - Lausser, Ludwig A1 - Kuhn, Peter A1 - Jobst, Franz A1 - Bock, Michaela A1 - Halanke, Carolin A1 - Hummel, Michael A1 - Heuschmann, Peter A1 - Kestler, Hans A. T1 - Big data and precision medicine BT - challenges and strategies with healthcare data JF - International Journal of Data Science and Analytics UR - https://doi.org/10.1007/s41060-018-0095-0 KW - big data KW - precision medicine KW - health care KW - data science Y1 - 2018 UR - https://doi.org/10.1007/s41060-018-0095-0 SN - 2364-4168 SN - 2364-415X VL - 6 (2018) IS - 3 SP - 241 EP - 249 PB - Springer Nature CY - Cham ER - TY - JOUR A1 - Hesse, Raphael A1 - Einem, Bjoern von A1 - Wagner, Franziska A1 - Bott, Patricia A1 - Schwanzar, Daniel A1 - Jackson, Rosemary A1 - Föhr, Karl Josef A1 - Lausser, Ludwig A1 - Kroker, Katja S. A1 - Proepper, Christian A1 - Walther, Paul A1 - Kestler, Hans A. A1 - Spires-Jones, Tara A1 - Boeckers, Tobias A1 - Rosenbrock, Holger A1 - Arnim, Christine A. F. von T1 - sAPPβ and sAPPα increase structural complexity and E/I input ratio in primary hippocampal neurons and alter Ca2+ homeostasis and CREB1-signaling JF - Experimental Neurology UR - https://doi.org/10.1016/j.expneurol.2018.02.010 KW - sAPP KW - AD KW - neuronal plasticity KW - neurodevelopment KW - CREB-1 signaling Y1 - 2018 UR - https://doi.org/10.1016/j.expneurol.2018.02.010 SN - 0014-4886 VL - (2018) IS - 304 SP - 1 EP - 13 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Lausser, Ludwig A1 - Szekely, Robin A1 - Kestler, Hans A. T1 - Chained correlations for feature selection JF - Advances in Data Analysis and Classification N2 - Data-driven algorithms stand and fall with the availability and quality of existing data sources. Both can be limited in high-dimensional settings (n≫m). For example, supervised learning algorithms designed for molecular pheno- or genotyping are restricted to samples of the corresponding diagnostic classes. Samples of other related entities, such as arise in differential diagnosis, are usually not utilized in this learning scheme. Nevertheless, they might provide domain knowledge on the background or context of the original diagnostic task. In this work, we discuss the possibility of incorporating samples of foreign classes in the training of diagnostic classification models that can be related to the task of differential diagnosis. Especially in heterogeneous data collections comprising multiple diagnostic categories, the foreign ones can change the magnitude of available samples. More precisely, we utilize this information for the internal feature selection process of diagnostic models. We propose the use of chained correlations of original and foreign diagnostic classes. This method allows the detection of intermediate foreign classes by evaluating the correlation between class labels and features for each pair of original and foreign categories. Interestingly, this criterion does not require direct comparisons of the initial diagnostic groups and therefore, might be suitable for settings with restricted data access. KW - classification KW - feature selection KW - high-dimensional data KW - differential diagnosis Y1 - 2020 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27534 SN - 1862-5355 VL - 14 IS - 4 SP - 871 EP - 884 PB - Springer CY - Berlin ER - TY - JOUR A1 - Lausser, Ludwig A1 - Schäfer, Lisa M. A1 - Werle, Silke D. A1 - Kestler, Angelika M. R. A1 - Kestler, Hans A. T1 - Detecting Ordinal Subcascades JF - Neural Processing Letters N2 - Ordinal classifier cascades are constrained by a hypothesised order of the semantic class labels of a dataset. This order determines the overall structure of the decision regions in feature space. Assuming the correct order on these class labels will allow a high generalisation performance, while an incorrect one will lead to diminished results. In this way ordinal classifier systems can facilitate explorative data analysis allowing to screen for potential candidate orders of the class labels. Previously, we have shown that screening is possible for total orders of all class labels. However, as datasets might comprise samples of ordinal as well as non-ordinal classes, the assumption of a total ordering might be not appropriate. An analysis of subsets of classes is required to detect such hidden ordinal substructures. In this work, we devise a novel screening procedure for exhaustive evaluations of all order permutations of all subsets of classes by bounding the number of enumerations we have to examine. Experiments with multi-class data from diverse applications revealed ordinal substructures that generate new and support known relations. UR - https://doi.org/10.1007/s11063-020-10362-0 KW - ordinal classification KW - classifier cascades KW - error bounds KW - subsets KW - supersets Y1 - 2020 UR - https://doi.org/10.1007/s11063-020-10362-0 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27555 SN - 1573-773X SN - 1370-4621 VL - 52 IS - 3 SP - 2583 EP - 2605 PB - Springer Science+Business Media CY - Dordrecht ER - TY - JOUR A1 - Lausser, Ludwig A1 - Szekely, Robin A1 - Schmid, Florian A1 - Maucher, Markus A1 - Kestler, Hans A. T1 - Efficient cross-validation traversals in feature subset selection JF - Scientific Reports N2 - Sparse and robust classification models have the potential for revealing common predictive patterns that not only allow for categorizing objects into classes but also for generating mechanistic hypotheses. Identifying a small and informative subset of features is their main ingredient. However, the exponential search space of feature subsets and the heuristic nature of selection algorithms limit the coverage of these analyses, even for low-dimensional datasets. We present methods for reducing the computational complexity of feature selection criteria allowing for higher efficiency and coverage of screenings. We achieve this by reducing the preparation costs of high-dimensional subsets O(nm2) to those of one-dimensional ones O(m2). Our methods are based on a tight interaction between a parallelizable cross-validation traversal strategy and distance-based classification algorithms and can be used with any product distance or kernel. We evaluate the traversal strategy exemplarily in exhaustive feature subset selection experiments (perfect coverage). Its runtime, fitness landscape, and predictive performance are analyzed on publicly available datasets. Even in low-dimensional settings, we achieve approximately a 15-fold increase in exhaustively generating distance matrices for feature combinations bringing a new level of evaluations into reach. UR - https://doi.org/10.1038/s41598-022-25942-4 Y1 - 2022 UR - https://doi.org/10.1038/s41598-022-25942-4 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-30299 SN - 2045-2322 VL - 12 PB - Springer Nature CY - London ER - TY - JOUR A1 - Werle, Silke D. A1 - Ikonomi, Nensi A1 - Lausser, Ludwig A1 - Kestler, Annika M. T. U. A1 - Weidner, Felix M. A1 - Schwab, Julian D. A1 - Maier, Julia A1 - Buchholz, Malte A1 - Gress, Thomas M. A1 - Kestler, Angelika M. R. A1 - Kestler, Hans A. T1 - A systems biology approach to define mechanisms, phenotypes, and drivers in PanNETs with a personalized perspective JF - npj Systems Biology and Applications N2 - AbstractPancreatic neuroendocrine tumors (PanNETs) are a rare tumor entity with largely unpredictable progression and increasing incidence in developed countries. Molecular pathways involved in PanNETs development are still not elucidated, and specific biomarkers are missing. Moreover, the heterogeneity of PanNETs makes their treatment challenging and most approved targeted therapeutic options for PanNETs lack objective responses. Here, we applied a systems biology approach integrating dynamic modeling strategies, foreign classifier tailored approaches, and patient expression profiles to predict PanNETs progression as well as resistance mechanisms to clinically approved treatments such as the mammalian target of rapamycin complex 1 (mTORC1) inhibitors. We set up a model able to represent frequently reported PanNETs drivers in patient cohorts, such as Menin-1 (MEN1), Death domain associated protein (DAXX), Tuberous Sclerosis (TSC), as well as wild-type tumors. Model-based simulations suggested drivers of cancer progression as both first and second hits after MEN1 loss. In addition, we could predict the benefit of mTORC1 inhibitors on differentially mutated cohorts and hypothesize resistance mechanisms. Our approach sheds light on a more personalized prediction and treatment of PanNET mutant phenotypes. UR - https://doi.org/10.1038/s41540-023-00283-8 Y1 - 2023 UR - https://doi.org/10.1038/s41540-023-00283-8 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-38071 SN - 2056-7189 VL - 9 IS - 1 PB - Springer CY - Heidelberg ER - TY - CHAP A1 - Krüger, Max A1 - Lausser, Ludwig T1 - Identifying Key Features in Aggregated Real-Life AIS-Messages for Classification of Maritime Vessels by Random Forests T2 - 2023 26th International Conference on Information Fusion (FUSION) UR - https://doi.org/10.23919/FUSION52260.2023.10224109 KW - Classification KW - key features KW - AIS KW - aggregated messages KW - performance evaluation KW - experimental comparison KW - maritime surveillance systems Y1 - 2023 UR - https://doi.org/10.23919/FUSION52260.2023.10224109 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Lausser, Ludwig A1 - Szekely, Robin A1 - Kessler, Viktor A1 - Schwenker, Friedhelm ED - Pancioni, Luca ED - Schwenker, Friedhelm ED - Trentin, Edmondo T1 - Selecting Features from Foreign Classes T2 - Artificial Neural Networks in Pattern Recognition: 8th IAPR TC3 Workshop, ANNPR 2018, Siena, Italy, September 19–21, 2018: Proceedings UR - https://doi.org/10.1007/978-3-319-99978-4_5 Y1 - 2018 UR - https://doi.org/10.1007/978-3-319-99978-4_5 SN - 978-3-319-99978-4 SN - 978-3-319-99977-7 SP - 66 EP - 77 PB - Springer CY - Cham ER - TY - CHAP A1 - Bellmann, Peter A1 - Lausser, Ludwig A1 - Kestler, Hans A. ED - Torsello, Andrea ED - Rossi, Luca ED - Pelillo, Marcello ED - Biggio, Battista ED - Robles-Kelly, Antonio T1 - Experimental Analysis of Bidirectional Pairwise Ordinal Classifier Cascades T2 - Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshops, S+SSPR 2020, Padua, Italy, January 21–22, 2021: Proceedings UR - https://doi.org/10.1007/978-3-030-73973-7_6 KW - Ordinal classification KW - Ordinal classifier cascades Y1 - 2021 UR - https://doi.org/10.1007/978-3-030-73973-7_6 SN - 978-3-030-73973-7 SN - 978-3-030-73972-0 SP - 55 EP - 64 PB - Springer CY - Cham ER - TY - CHAP A1 - Bellmann, Peter A1 - Lausser, Ludwig A1 - Kestler, Hans A. A1 - Schwenker, Friedhelm ED - Del Bimbo, Alberto ED - Cucchiara, Rita ED - Sclaroff, Stan ED - Farinella, Giovanni Maria ED - Mei, Tao ED - Bertini, Marco ED - Escalante, Hugo Jair ED - Vezzani, Roberto T1 - Introducing Bidirectional Ordinal Classifier Cascades Based on a Pain Intensity Recognition Scenario T2 - Pattern Recognition: ICPR International Workshops and Challenges: Virtual Event, January 10–15, 2021: Proceedings, Part VI UR - https://doi.org/10.1007/978-3-030-68780-9_58 KW - Ordinal classifier cascades KW - Ordinal classification KW - Pain intensity recognition KW - Physiological signals Y1 - 2021 UR - https://doi.org/10.1007/978-3-030-68780-9_58 SN - 978-3-030-68780-9 SN - 978-3-030-68779-3 SP - 773 EP - 787 PB - Springer CY - Cham ER - TY - JOUR A1 - Thiam, Patrick A1 - Lausser, Ludwig A1 - Kloth, Christopher A1 - Blaich, Daniel A1 - Liebold, Andreas A1 - Beer, Meinrad A1 - Kestler, Hans A. T1 - Unsupervised domain adaptation for the detection of cardiomegaly in cross-domain chest X-ray images JF - Frontiers in Artificial Intelligence N2 - In recent years, several deep learning approaches have been successfully applied in the field of medical image analysis. More specifically, different deep neural network architectures have been proposed and assessed for the detection of various pathologies based on chest X-ray images. While the performed assessments have shown very promising results, most of them consist in training and evaluating the performance of the proposed approaches on a single data set. However, the generalization of such models is quite limited in a cross-domain setting, since a significant performance degradation can be observed when these models are evaluated on data sets stemming from different medical centers or recorded under different protocols. The performance degradation is mostly caused by the domain shift between the training set and the evaluation set. To alleviate this problem, different unsupervised domain adaptation approaches are proposed and evaluated in the current work, for the detection of cardiomegaly based on chest X-ray images, in a cross-domain setting. The proposed approaches generate domain invariant feature representations by adapting the parameters of a model optimized on a large set of labeled samples, to a set of unlabeled images stemming from a different data set. The performed evaluation points to the effectiveness of the proposed approaches, since the adapted models outperform optimized models which are directly applied to the evaluation sets without any form of domain adaptation. UR - https://doi.org/10.3389/frai.2023.1056422 KW - chest X-ray KW - cardiomegaly KW - deep learning KW - transfer learning KW - unsupervised domain adaptation Y1 - 2023 UR - https://doi.org/10.3389/frai.2023.1056422 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-32108 SN - 2624-8212 VL - 6 PB - Frontiers Media CY - Lausanne ER - TY - JOUR A1 - Weidner, Felix M. A1 - Schwab, Julian D. A1 - Werle, Silke D. A1 - Ikonomi, Nensi A1 - Lausser, Ludwig A1 - Kestler, Hans A. T1 - Response to the letter to the editor: On the feasibility of dynamical analysis of network models of biochemical regulation JF - Bioinformatics UR - https://doi.org/10.1093/bioinformatics/btac318 Y1 - 2022 UR - https://doi.org/10.1093/bioinformatics/btac318 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-40238 SN - 1367-4811 VL - 38 IS - 14 SP - 3676 PB - Oxford University Press CY - Oxford ER - TY - JOUR A1 - Seufferlein, Thomas A1 - Lausser, Ludwig A1 - Stein, Alexander A1 - Arnold, Dirk A1 - Prager, Gerald A1 - Kasper-Virchow, Stefan A1 - Niedermeier, Michael A1 - Müller, Lothar A1 - Kubicka, Stefan A1 - König, Alexander A1 - Büchner-Steudel, Petra A1 - Wille, Kai A1 - Berger, Andreas W. A1 - Kestler, Angelika M. R. A1 - Kraus, Johann M. A1 - Werle, Silke D. A1 - Perkhofer, Lukas A1 - Ettrich, Thomas J. A1 - Kestler, Hans A. T1 - Prediction of resistance to bevacizumab plus FOLFOX in metastatic colorectal cancer—Results of the prospective multicenter PERMAD trial JF - PLOS ONE N2 - Background Anti-vascular endothelial growth factor (VEGF) monoclonal antibodies (mAbs) are widely used for tumor treatment, including metastatic colorectal cancer (mCRC). So far, there are no biomarkers that reliably predict resistance to anti-VEGF mAbs like bevacizumab. A biomarker-guided strategy for early and accurate assessment of resistance could avoid the use of non-effective treatment and improve patient outcomes. We hypothesized that repeated analysis of multiple cytokines and angiogenic growth factors (CAFs) before and during treatment using machine learning could provide an accurate and earlier, i.e., 100 days before conventional radiologic staging, prediction of resistance to first-line mCRC treatment with FOLFOX plus bevacizumab. Patients and methods 15 German and Austrian centers prospectively recruited 50 mCRC patients receiving FOLFOX plus bevacizumab as first-line treatment. Plasma samples were collected every two weeks until radiologic progression (RECIST 1.1) as determined by CT scans performed every 2 months. 102 pre-selected CAFs were centrally analyzed using a cytokine multiplex assay (Luminex, Myriad RBM). Results Using random forests, we developed a predictive machine learning model that discriminated between the situations of “no progress within 100 days before radiological progress” and “progress within 100 days before radiological progress”. We could further identify a combination of ten out of the 102 CAF markers, which fulfilled this task with 78.2% accuracy, 71.8% sensitivity, and 82.5% specificity. Conclusions We identified a CAF marker combination that indicates treatment resistance to FOLFOX plus bevacizumab in patients with mCRC within 100 days prior to radiologic progress. UR - https://doi.org/10.1371/journal.pone.0304324 Y1 - 2024 UR - https://doi.org/10.1371/journal.pone.0304324 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-49003 SN - 1932-6203 VL - 19 IS - 6 PB - PLOS CY - San Francisco ER - TY - JOUR A1 - Lausser, Ludwig A1 - Szekely, Robin A1 - Kestler, Hans A. T1 - Permutation-invariant linear classifiers JF - Machine Learning N2 - Invariant concept classes form the backbone of classification algorithms immune to specific data transformations, ensuring consistent predictions regardless of these alterations. However, this robustness can come at the cost of limited access to the original sample information, potentially impacting generalization performance. This study introduces an addition to these classes—the permutation-invariant linear classifiers. Distinguished by their structural characteristics, permutation-invariant linear classifiers are unaffected by permutations on feature vectors, a property not guaranteed by other non-constant linear classifiers. The study characterizes this new concept class, highlighting its constant capacity, independent of input dimensionality. In practical assessments using linear support vector machines, the permutation-invariant classifiers exhibit superior performance in permutation experiments on artificial datasets and real mutation profiles. Interestingly, they outperform general linear classifiers not only in permutation experiments but also in permutation-free settings, surpassing unconstrained counterparts. Additionally, findings from real mutation profiles support the significance of tumor mutational burden as a biomarker. UR - https://doi.org/10.1007/s10994-024-06561-8 Y1 - 2024 UR - https://doi.org/10.1007/s10994-024-06561-8 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-49116 SN - 1573-0565 VL - 113 IS - 10 SP - 7195 EP - 7221 PB - Springer CY - Dordrecht ER - TY - INPR A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification N2 - 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. UR - https://doi.org/10.48550/arXiv.2412.06365 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2412.06365 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-59672 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Aubreville, Marc ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Palm, Christoph ED - Tolxdorff, Thomas T1 - Limits of Human Expert Ensembles in Mitosis Multi-expert Ground Truth Generation T2 - Bildverarbeitung für die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_27 Y1 - 2023 UR - https://doi.org/10.1007/978-3-658-41657-7_27 SN - 978-3-658-41657-7 SN - 978-3-658-41656-0 SP - 116 EP - 121 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Kubis, Lea A1 - Schwab, Julian D. A1 - Werle, Silke D. A1 - Lausser, Ludwig A1 - Tümpel, Stefan A1 - Pfister, Astrid S. A1 - Kühl, Michael A1 - Kestler, Hans A. T1 - A Boolean network of the crosstalk between IGF and Wnt signaling in aging satellite cells JF - PLOS ONE N2 - Aging is a complex biological process, which determines the life span of an organism. Insulin-like growth factor (IGF) and Wnt signaling pathways govern the process of aging. Both pathways share common downstream targets that allow competitive crosstalk between these branches. Of note, a shift from IGF to Wnt signaling has been observed during aging of satellite cells. Biological regulatory networks necessary to recreate aging have not yet been discovered. Here, we established a mathematical in silico model that robustly recapitulates the crosstalk between IGF and Wnt signaling. Strikingly, it predicts critical nodes following a shift from IGF to Wnt signaling. These findings indicate that this shift might cause age-related diseases. UR - https://doi.org/10.1371/journal.pone.0195126 Y1 - 2018 UR - https://doi.org/10.1371/journal.pone.0195126 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-27280 SN - 1932-6203 VL - 13 IS - 3 PB - PLOS CY - San Francisco ER - TY - JOUR A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Benchmarking Foundation Models for Mitotic Figure Classification JF - Machine Learning for Biomedical Imaging N2 - 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. UR - https://doi.org/10.59275/j.melba.2026-a3eb Y1 - 2026 UR - https://doi.org/10.59275/j.melba.2026-a3eb UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-66220 SN - 2766-905X VL - 3 IS - MELBA–BVM 2025 Special Issue SP - 38 EP - 55 PB - Melba editors CY - [s. l.] ER - TY - CHAP A1 - Ganz, Jonathan A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Palm, Christoph ED - Breininger, Katharina ED - Deserno, Thomas Martin ED - Handels, Heinz ED - Maier, Andreas ED - Maier-Hein, Klaus H. ED - Tolxdorff, Thomas T1 - Is Self-supervision Enough? BT - Benchmarking Foundation Models Against End-to-end Training for Mitotic Figure Classification T2 - Bildverarbeitung für die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09–11, 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 Y1 - 2025 UR - https://doi.org/10.1007/978-3-658-47422-5_15 SN - 978-3-658-47422-5 SP - 63 EP - 68 PB - Springer Vieweg CY - Wiesbaden ER - TY - INPR A1 - Ammeling, Jonas A1 - Ganz, Jonathan A1 - Rosbach, Emely A1 - Lausser, Ludwig A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Benchmarking Foundation Models for Mitotic Figure Classification UR - https://doi.org/10.48550/arXiv.2508.04441 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2508.04441 PB - arXiv CY - Ithaca ER -