@article{HesseEinemWagneretal.2018, author = {Hesse, Raphael and Einem, Bjoern von and Wagner, Franziska and Bott, Patricia and Schwanzar, Daniel and Jackson, Rosemary and F{\"o}hr, Karl Josef and Lausser, Ludwig and Kroker, Katja S. and Proepper, Christian and Walther, Paul and Kestler, Hans A. and Spires-Jones, Tara and Boeckers, Tobias and Rosenbrock, Holger and Arnim, Christine A. F. von}, title = {sAPPβ and sAPPα increase structural complexity and E/I input ratio in primary hippocampal neurons and alter Ca2+ homeostasis and CREB1-signaling}, volume = {(2018)}, journal = {Experimental Neurology}, number = {304}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0014-4886}, doi = {https://doi.org/10.1016/j.expneurol.2018.02.010}, pages = {1 -- 13}, year = {2018}, language = {en} } @article{LausserSzekelyKestler2020, author = {Lausser, Ludwig and Szekely, Robin and Kestler, Hans A.}, title = {Chained correlations for feature selection}, volume = {14}, journal = {Advances in Data Analysis and Classification}, number = {4}, publisher = {Springer}, address = {Berlin}, issn = {1862-5355}, pages = {871 -- 884}, year = {2020}, abstract = {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.}, language = {en} } @article{LausserSchaeferWerleetal.2020, author = {Lausser, Ludwig and Sch{\"a}fer, Lisa M. and Werle, Silke D. and Kestler, Angelika M. R. and Kestler, Hans A.}, title = {Detecting Ordinal Subcascades}, volume = {52}, journal = {Neural Processing Letters}, number = {3}, publisher = {Springer Science+Business Media}, address = {Dordrecht}, issn = {1573-773X}, doi = {https://doi.org/10.1007/s11063-020-10362-0}, pages = {2583 -- 2605}, year = {2020}, abstract = {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.}, language = {en} } @article{LausserSzekelySchmidetal.2022, author = {Lausser, Ludwig and Szekely, Robin and Schmid, Florian and Maucher, Markus and Kestler, Hans A.}, title = {Efficient cross-validation traversals in feature subset selection}, volume = {12}, pages = {21485}, journal = {Scientific Reports}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-022-25942-4}, year = {2022}, abstract = {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.}, language = {en} } @article{WerleIkonomiLausseretal.2023, author = {Werle, Silke D. and Ikonomi, Nensi and Lausser, Ludwig and Kestler, Annika M. T. U. and Weidner, Felix M. and Schwab, Julian D. and Maier, Julia and Buchholz, Malte and Gress, Thomas M. and Kestler, Angelika M. R. and Kestler, Hans A.}, title = {A systems biology approach to define mechanisms, phenotypes, and drivers in PanNETs with a personalized perspective}, volume = {9}, pages = {22}, journal = {npj Systems Biology and Applications}, number = {1}, publisher = {Springer}, address = {Heidelberg}, issn = {2056-7189}, doi = {https://doi.org/10.1038/s41540-023-00283-8}, year = {2023}, abstract = {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.}, language = {en} } @inproceedings{KruegerLausser2023, author = {Kr{\"u}ger, Max and Lausser, Ludwig}, title = {Identifying Key Features in Aggregated Real-Life AIS-Messages for Classification of Maritime Vessels by Random Forests}, booktitle = {2023 26th International Conference on Information Fusion (FUSION)}, publisher = {IEEE}, address = {Piscataway}, doi = {https://doi.org/10.23919/FUSION52260.2023.10224109}, year = {2023}, language = {en} } @inproceedings{LausserSzekelyKessleretal.2018, author = {Lausser, Ludwig and Szekely, Robin and Kessler, Viktor and Schwenker, Friedhelm}, title = {Selecting Features from Foreign Classes}, booktitle = {Artificial Neural Networks in Pattern Recognition: 8th IAPR TC3 Workshop, ANNPR 2018, Siena, Italy, September 19-21, 2018: Proceedings}, editor = {Pancioni, Luca and Schwenker, Friedhelm and Trentin, Edmondo}, publisher = {Springer}, address = {Cham}, isbn = {978-3-319-99978-4}, doi = {https://doi.org/10.1007/978-3-319-99978-4_5}, pages = {66 -- 77}, year = {2018}, language = {en} } @inproceedings{BellmannLausserKestler2021, author = {Bellmann, Peter and Lausser, Ludwig and Kestler, Hans A.}, title = {Experimental Analysis of Bidirectional Pairwise Ordinal Classifier Cascades}, booktitle = {Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshops, S+SSPR 2020, Padua, Italy, January 21-22, 2021: Proceedings}, editor = {Torsello, Andrea and Rossi, Luca and Pelillo, Marcello and Biggio, Battista and Robles-Kelly, Antonio}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-73973-7}, doi = {https://doi.org/10.1007/978-3-030-73973-7_6}, pages = {55 -- 64}, year = {2021}, language = {en} } @inproceedings{BellmannLausserKestleretal.2021, author = {Bellmann, Peter and Lausser, Ludwig and Kestler, Hans A. and Schwenker, Friedhelm}, title = {Introducing Bidirectional Ordinal Classifier Cascades Based on a Pain Intensity Recognition Scenario}, booktitle = {Pattern Recognition: ICPR International Workshops and Challenges: Virtual Event, January 10-15, 2021: Proceedings, Part VI}, editor = {Del Bimbo, Alberto and Cucchiara, Rita and Sclaroff, Stan and Farinella, Giovanni Maria and Mei, Tao and Bertini, Marco and Escalante, Hugo Jair and Vezzani, Roberto}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-68780-9}, doi = {https://doi.org/10.1007/978-3-030-68780-9_58}, pages = {773 -- 787}, year = {2021}, language = {en} } @article{ThiamLausserKlothetal.2023, author = {Thiam, Patrick and Lausser, Ludwig and Kloth, Christopher and Blaich, Daniel and Liebold, Andreas and Beer, Meinrad and Kestler, Hans A.}, title = {Unsupervised domain adaptation for the detection of cardiomegaly in cross-domain chest X-ray images}, volume = {6}, pages = {1056422}, journal = {Frontiers in Artificial Intelligence}, publisher = {Frontiers Media}, address = {Lausanne}, issn = {2624-8212}, doi = {https://doi.org/10.3389/frai.2023.1056422}, year = {2023}, abstract = {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.}, language = {en} } @article{WeidnerSchwabWerleetal.2022, author = {Weidner, Felix M. and Schwab, Julian D. and Werle, Silke D. and Ikonomi, Nensi and Lausser, Ludwig and Kestler, Hans A.}, title = {Response to the letter to the editor: On the feasibility of dynamical analysis of network models of biochemical regulation}, volume = {38}, journal = {Bioinformatics}, number = {14}, publisher = {Oxford University Press}, address = {Oxford}, issn = {1367-4811}, doi = {https://doi.org/10.1093/bioinformatics/btac318}, pages = {3676}, year = {2022}, language = {en} } @article{SeufferleinLausserSteinetal.2024, author = {Seufferlein, Thomas and Lausser, Ludwig and Stein, Alexander and Arnold, Dirk and Prager, Gerald and Kasper-Virchow, Stefan and Niedermeier, Michael and M{\"u}ller, Lothar and Kubicka, Stefan and K{\"o}nig, Alexander and B{\"u}chner-Steudel, Petra and Wille, Kai and Berger, Andreas W. and Kestler, Angelika M. R. and Kraus, Johann M. and Werle, Silke D. and Perkhofer, Lukas and Ettrich, Thomas J. and Kestler, Hans A.}, title = {Prediction of resistance to bevacizumab plus FOLFOX in metastatic colorectal cancer—Results of the prospective multicenter PERMAD trial}, volume = {19}, pages = {e0304324}, journal = {PLOS ONE}, number = {6}, publisher = {PLOS}, address = {San Francisco}, issn = {1932-6203}, doi = {https://doi.org/10.1371/journal.pone.0304324}, year = {2024}, abstract = {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.}, language = {en} } @article{LausserSzekelyKestler2024, author = {Lausser, Ludwig and Szekely, Robin and Kestler, Hans A.}, title = {Permutation-invariant linear classifiers}, volume = {113}, journal = {Machine Learning}, number = {10}, publisher = {Springer}, address = {Dordrecht}, issn = {1573-0565}, doi = {https://doi.org/10.1007/s10994-024-06561-8}, pages = {7195 -- 7221}, year = {2024}, abstract = {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.}, language = {en} } @unpublished{GanzAmmelingRosbachetal.2024, author = {Ganz, Jonathan and Ammeling, Jonas and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2412.06365}, year = {2024}, abstract = {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.}, language = {en} } @inproceedings{LausserBertramKlopfleischetal.2023, author = {Lausser, Ludwig and Bertram, Christof and Klopfleisch, Robert and Aubreville, Marc}, title = {Limits of Human Expert Ensembles in Mitosis Multi-expert Ground Truth Generation}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2023: Proceedings, German Workshop on Medical Image Computing, Braunschweig, July 2-4, 2023}, editor = {Deserno, Thomas Martin and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Palm, Christoph and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-41657-7}, doi = {https://doi.org/10.1007/978-3-658-41657-7_27}, pages = {116 -- 121}, year = {2023}, language = {en} } @article{KubisSchwabWerleetal.2018, author = {Kubis, Lea and Schwab, Julian D. and Werle, Silke D. and Lausser, Ludwig and T{\"u}mpel, Stefan and Pfister, Astrid S. and K{\"u}hl, Michael and Kestler, Hans A.}, title = {A Boolean network of the crosstalk between IGF and Wnt signaling in aging satellite cells}, volume = {13}, pages = {e0195126}, journal = {PLOS ONE}, number = {3}, publisher = {PLOS}, address = {San Francisco}, issn = {1932-6203}, doi = {https://doi.org/10.1371/journal.pone.0195126}, year = {2018}, abstract = {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.}, language = {en} } @article{AmmelingGanzRosbachetal.2026, author = {Ammeling, Jonas and Ganz, Jonathan and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Benchmarking Foundation Models for Mitotic Figure Classification}, volume = {3}, pages = {2026:003}, journal = {Machine Learning for Biomedical Imaging}, number = {MELBA-BVM 2025 Special Issue}, publisher = {Melba editors}, address = {[s. l.]}, issn = {2766-905X}, doi = {https://doi.org/10.59275/j.melba.2026-a3eb}, pages = {38 -- 55}, year = {2026}, 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.}, language = {en} } @inproceedings{GanzAmmelingRosbachetal.2025, author = {Ganz, Jonathan and Ammeling, Jonas and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Is Self-supervision Enough?}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, subtitle = {Benchmarking Foundation Models Against End-to-end Training for Mitotic Figure Classification}, editor = {Palm, Christoph and Breininger, Katharina and Deserno, Thomas Martin and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Tolxdorff, Thomas}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-47422-5}, doi = {https://doi.org/10.1007/978-3-658-47422-5_15}, pages = {63 -- 68}, year = {2025}, language = {en} } @unpublished{AmmelingGanzRosbachetal.2025, author = {Ammeling, Jonas and Ganz, Jonathan and Rosbach, Emely and Lausser, Ludwig and Bertram, Christof and Breininger, Katharina and Aubreville, Marc}, title = {Benchmarking Foundation Models for Mitotic Figure Classification}, publisher = {arXiv}, address = {Ithaca}, doi = {https://doi.org/10.48550/arXiv.2508.04441}, year = {2025}, language = {en} }