arXiv subjects

Christian Matek

Publications and source records attributed to Christian Matek.

9 recordsLinked to original sources

arXiv2026

Tissue Classification and Whole-Slide Images Analysis via Modeling of the Tumor Microenvironment and Biological Pathways

Automatic integration of whole slide images (WSIs) and gene expression profiles has demonstrated substantial potential in precision clinical diagnosis and cancer progression studies. However, most existing studies focus on individual gene sequences and slide level classification tasks, with limited attention to spatial transcriptomics and patch level applications. To address this limitation, we propose a multimodal network, BioMorphNet, which automatically integrates tissue morphological features and spatial gene expression to support tissue classification and differential gene analysis. For considering morphological features, BioMorphNet constructs a graph to model the relationships between target patches and their neighbors, and adjusts the response strength based on morphological and molecular level similarity, to better characterize the tumor microenvironment. In terms of multimodal interactions, BioMorphNet derives clinical pathway features from spatial transcriptomic data based on a predefined pathway database, serving as a bridge between tissue morphology and gene expression. In addition, a novel learnable pathway module is designed to automatically simulate the biological pathway formation process, providing a complementary representation to existing clinical pathways. Compared with the latest morphology gene multimodal methods, BioMorphNet's average classification metrics improve by 2.67%, 5.48%, and 6.29% for prostate cancer, colorectal cancer, and breast cancer datasets, respectively. BioMorphNet not only classifies tissue categories within WSIs accurately to support tumor localization, but also analyzes differential gene expression between tissue categories based on prediction confidence, contributing to the discovery of potential tumor biomarkers.

cs.CV↗

arXiv2025

A Multicenter Benchmark of Multiple Instance Learning Models for Lymphoma Subtyping from HE-stained Whole Slide Images

Timely and accurate lymphoma diagnosis is essential for guiding cancer treatment. Standard diagnostic practice combines hematoxylin and eosin (HE)-stained whole slide images with immunohistochemistry, flow cytometry, and molecular genetic tests to determine lymphoma subtypes, a process requiring costly equipment, and skilled personnel, causing treatment delays. Deep learning methods could assist pathologists by extracting diagnostic information from routinely available HE-stained slides directly, yet comprehensive benchmarks for lymphoma subtyping on multicenter data are lacking. In this work, we present the first multicenter lymphoma benchmark, covering four common lymphoma subtypes and healthy control tissue. We systematically evaluate five publicly available pathology foundation models (H-optimus-1, H0-mini, Virchow2, UNI2, Titan) combined with attention-based (AB-MIL) and transformer-based (TransMIL) multiple instance learning aggregators across three magnifications (10x, 20x, 40x). On in-distribution test sets, models achieve multiclass balanced accuracies exceeding 80% across all magnifications, with foundation models performing similarly, and aggregation methods showing comparable results. The magnification study reveals that 40x resolution is sufficient, with no performance gains from higher resolutions or cross-magnification aggregation. However, on out-of-distribution test sets, performance drops substantially to around 60%, highlighting significant generalization challenges. To advance the field, larger multicenter studies covering additional rare lymphoma subtypes are needed. We provide an automated benchmarking pipeline to facilitate such future research. Our paper codes is publicly available at https://github.com/RaoUmer/LymphomaMIL.

cs.CV↗

arXiv2025

Domain-incremental White Blood Cell Classification with Privacy-aware Continual Learning

White blood cell (WBC) classification plays a vital role in hematology for diagnosing various medical conditions. However, it faces significant challenges due to domain shifts caused by variations in sample sources (e.g., blood or bone marrow) and differing imaging conditions across hospitals. Traditional deep learning models often suffer from catastrophic forgetting in such dynamic environments, while foundation models, though generally robust, experience performance degradation when the distribution of inference data differs from that of the training data. To address these challenges, we propose a generative replay-based Continual Learning (CL) strategy designed to prevent forgetting in foundation models for WBC classification. Our method employs lightweight generators to mimic past data with a synthetic latent representation to enable privacy-preserving replay. To showcase the effectiveness, we carry out extensive experiments with a total of four datasets with different task ordering and four backbone models including ResNet50, RetCCL, CTransPath, and UNI. Experimental results demonstrate that conventional fine-tuning methods degrade performance on previously learned tasks and struggle with domain shifts. In contrast, our continual learning strategy effectively mitigates catastrophic forgetting, preserving model performance across varying domains. This work presents a practical solution for maintaining reliable WBC classification in real-world clinical settings, where data distributions frequently evolve.

cs.LG↗

arXiv2024

B-Cos Aligned Transformers Learn Human-Interpretable Features

Vision Transformers (ViTs) and Swin Transformers (Swin) are currently state-of-the-art in computational pathology. However, domain experts are still reluctant to use these models due to their lack of interpretability. This is not surprising, as critical decisions need to be transparent and understandable. The most common approach to understanding transformers is to visualize their attention. However, attention maps of ViTs are often fragmented, leading to unsatisfactory explanations. Here, we introduce a novel architecture called the B-cos Vision Transformer (BvT) that is designed to be more interpretable. It replaces all linear transformations with the B-cos transform to promote weight-input alignment. In a blinded study, medical experts clearly ranked BvTs above ViTs, suggesting that our network is better at capturing biomedically relevant structures. This is also true for the B-cos Swin Transformer (Bwin). Compared to the Swin Transformer, it even improves the F1-score by up to 4.7% on two public datasets.

cs.CV↗

arXiv2023

Data Models for Dataset Drift Controls in Machine Learning With Optical Images

Camera images are ubiquitous in machine learning research. They also play a central role in the delivery of important services spanning medicine and environmental surveying. However, the application of machine learning models in these domains has been limited because of robustness concerns. A primary failure mode are performance drops due to differences between the training and deployment data. While there are methods to prospectively validate the robustness of machine learning models to such dataset drifts, existing approaches do not account for explicit models of the primary object of interest: the data. This limits our ability to study and understand the relationship between data generation and downstream machine learning model performance in a physically accurate manner. In this study, we demonstrate how to overcome this limitation by pairing traditional machine learning with physical optics to obtain explicit and differentiable data models. We demonstrate how such data models can be constructed for image data and used to control downstream machine learning model performance related to dataset drift. The findings are distilled into three applications. First, drift synthesis enables the controlled generation of physically faithful drift test cases to power model selection and targeted generalization. Second, the gradient connection between machine learning task model and data model allows advanced, precise tolerancing of task model sensitivity to changes in the data generation. These drift forensics can be used to precisely specify the acceptable data environments in which a task model may be run. Third, drift optimization opens up the possibility to create drifts that can help the task model learn better faster, effectively optimizing the data generating process itself. A guide to access the open code and datasets is available at https://github.com/aiaudit-org/raw2logit.

cs.LG↗

arXiv2015

Coarse-grained modelling of supercoiled RNA

We study the behaviour of double-stranded RNA under twist and tension using oxRNA, a recently developed coarse-grained model of RNA. Introducing explicit salt-dependence into the model allows us to directly compare our results to data from recent single-molecule experiments. The model reproduces extension curves as a function of twist and stretching force, including the buckling transition and the behaviour of plectoneme structures. For negative supercoiling, we predict denaturation bubble formation in plectoneme end-loops, suggesting preferential plectoneme localisation in weak base sequences. OxRNA exhibits a positive twist-stretch coupling constant, in agreement with recent experimental observations.

q-bio.BM↗

arXiv2014

Plectoneme tip bubbles: Coupled denaturation and writhing in supercoiled DNA

Biological information is not only stored in the digital chemical sequence of double helical DNA, but is also encoded in the mechanical properties of the DNA strands, which can influence biochemical processes involving its readout. For example, loop formation in the Lac operon can regulate the expression of key genes, and DNA supercoiling is closely correlated to rhythmic circardian gene expression in cyanobacteria. Supercoiling is also important for large scale organisation of the genome in both eukaryotic and prokaryotic cells. DNA can respond to torsional stress by writhing to form looped structures called plectonemes, thus transferring energy stored as twist into energy stored in bending. Denaturation bubbles can also relax torsional stress, with the enthalpic cost of breaking bonds being compensated by their ability to absorb undertwist. Here we predict a novel regime where bubbles form at the tips of plectonemes, and study its properties using coarse-grained simulations. These tip bubbles can occur for both positive and negative supercoiling and greatly reduce plectoneme diffusion by a pinning mechanism. They can cause plectonemes to preferentially localise to AT rich regions, because bubbles more easily form there. The tip-bubble regime occurs for supercoiling densities and forces that are typically encountered for DNA in vivo, and may be exploited for biological control of genomic processes.

cond-mat.soft↗

arXiv2013

Coarse-graining DNA for simulations of DNA nanotechnology

To simulate long time and length scale processes involving DNA it is necessary to use a coarse-grained description. Here we provide an overview of different approaches to such coarse graining, focussing on those at the nucleotide level that allow the self-assembly processes associated with DNA nanotechnology to be studied. OxDNA, our recently-developed coarse-grained DNA model, is particularly suited to this task, and has opened up this field to systematic study by simulations. We illustrate some of the range of DNA nanotechnology systems to which the model is being applied, as well as the insights it can provide into fundamental biophysical properties of DNA.

q-bio.BM↗

arXiv2012

DNA cruciform arms nucleate through a correlated but non-synchronous cooperative mechanism

Inverted repeat (IR) sequences in DNA can form non-canonical cruciform structures to relieve torsional stress. We use Monte Carlo simulations of a recently developed coarse-grained model of DNA to demonstrate that the nucleation of a cruciform can proceed through a cooperative mechanism. Firstly, a twist-induced denaturation bubble must diffuse so that its midpoint is near the centre of symmetry of the IR sequence. Secondly, bubble fluctuations must be large enough to allow one of the arms to form a small number of hairpin bonds. Once the first arm is partially formed, the second arm can rapidly grow to a similar size. Because bubbles can twist back on themselves, they need considerably fewer bases to resolve torsional stress than the final cruciform state does. The initially stabilised cruciform therefore continues to grow, which typically proceeds synchronously, reminiscent of the S-type mechanism of cruciform formation. By using umbrella sampling techniques we calculate, for different temperatures and superhelical densities, the free energy as a function of the number of bonds in each cruciform along the correlated but non-synchronous nucleation pathways we observed in direct simulations.

q-bio.BM↗