Jakob Nikolas Kather

MoPaDi generates counterfactual explanations for histopathology images to reveal morphological features driving classifier predictions, improving interpretability in digital pathology.

HCCExplorer translates H&E slides into virtual multiplex immunofluorescence to identify prognostic spatial immune features in hepatocellular carcinoma.

SwarmMAP uses swarm learning to automate cell-type annotation in single-cell data without sharing raw data, achieving high accuracy across human tissues.

This study develops a deep learning model to predict survival across multiple squamous tumor types using H&E stained slides, showing its predictive power beyond head and neck cancer.

This study integrates multi-omic and multimodal data from IBD patients to identify molecular, histopathological, and clinical features associated with inflammatory bowel diseases.

This paper develops a multimodal transformer model using H&E images and text reports to predict recurrence scores in hormone receptor-positive breast cancer, achieving high accuracy and generalizability.

This study compares deep learning and machine learning for biomarker prediction in cancer genomes, finding DL performs better in cross-assay and data-sparse settings.

This study uses attention-based multiple instance learning to predict HRD status from H&E images across ten tumor types, achieving moderate to high AUROC values.

This study fits the Kuznetsov model to 1472 cancer patients to predict tumor growth and shows it can extrapolate future dynamics.

This paper demonstrates swarm learning for training AI models on decentralized histopathology data to predict molecular features in colorectal cancer.

This paper evaluates adversarial robustness of CNNs and ViTs in computational pathology, finding ViTs are more robust to attacks.

This study benchmarks AI methods for end-to-end computational pathology, showing ResNet and ViT outperform MIL and CLAM in mutation prediction but not in tumor subtyping.

This paper shows that digital histopathology batch effects in TCGA data affect DL model accuracy and bias, and proposes a method to address this issue.

The paper compares linear and nonlinear model performance on brain imaging data and standard datasets, finding linear models outperform nonlinear ones in brain scans despite larger sample sizes.

This paper develops a deep learning method to predict genetic alterations from histological images across multiple cancer types.