Computational Pathology |

Histopathologische Klassifikation konjunktivaler melanozytärer intraepithelialer Läsionen (CMIL) mit einem Deep-Learning-Algorithmus

Sat, 26 Sep 2026 00:00:00 +0000

Eyelid Tumor Triage using Uncertainty-Aware and Explainable Artificial Intelligence

Fri, 25 Sep 2026 00:00:00 +0000

MISTAI: Medical Intelligence & Skills Training in AI

Wed, 01 Jul 2026 00:00:00 +0000

The war in Ukraine has severely disrupted medical research and teaching. Digital pathology and AI offer a way to keep both going without depending on physical infrastructure. MISTAI is a bilateral cooperation between the University Hospital Bonn and Dnipro State Medical University (DSMU), funded by the Ministry of Culture and Science of North Rhine-Westphalia (MKW NRW).

Goals

Shared data infrastructure: digitise and validate at least 100 H&E and IHC whole-slide images from a DSMU cohort of muscle-invasive bladder cancer (MIBC), on a joint secure platform.
AI diagnostic pipeline: fine-tune state-of-the-art pathology foundation models on the combined Bonn–Dnipro data, including spatial analysis of tumour-infiltrating lymphocytes from routine H&E slides, inspired by the UC-TIL approach.
Clinical tool: a QuPath plugin that lets pathologists run the trained model directly in their existing workflow.
Capacity building: weekly remote collaboration, a one-week exchange visit to Bonn, and a Computational Pathology teaching module for the DSMU curriculum.
Follow-on work: a joint DFG/BMBF proposal outline and a MICCAI challenge concept.

Partners

Bonn contributes high-resolution slide scanners, AI infrastructure and expertise in computational medical imaging (Prof. Shadi Albarqouni) and translational lung and tumour pathology (Prof. Verena Tischler). DSMU contributes a clinically distinct bladder-cancer cohort and long-standing pathology expertise (Assoc. Prof. Nina Bondarenko, Department of Pathological Anatomy).

INTERACT-CMIL: Multi-Task Shared Learning and Inter-Task Consistency for Conjunctival Melanocytic Intraepithelial Lesion Grading

Thu, 01 Jan 2026 00:00:00 +0000

Conjunctival Melanocytic Intraepithelial Lesion (CMIL) Histopathology Dataset

Wed, 01 Jan 2025 00:00:00 +0000

Curated with Prof. Martina C. Herwig-Carl (Ophthalmic Pathology, UKB) together with University Hospitals Tübingen and Erlangen.

FLamby — Federated Learning Benchmark for Healthcare

Wed, 01 Jan 2025 00:00:00 +0000

International collaboration led by Owkin (Jean Ogier du Terrail) with EPFL, Inria, IP Paris, USC and UC Berkeley. Our lab contributed dataset preparation, benchmark design and federated evaluation.

LYSTO — Lymphocyte Assessment Hackathon Benchmark

Wed, 01 Jan 2025 00:00:00 +0000

International initiative with Francesco Ciompi (Radboudumc).

INTERACT-CMIL: Interpretable multi-task grading of conjunctival melanocytic lesions

Mon, 01 Jan 2024 00:00:00 +0000

Collaborators: University Hospital Tübingen, University Hospital Erlangen

This project addresses the grading of conjunctival melanocytic intraepithelial lesions (CMIL), rare precursors of conjunctival melanoma characterized by complex, interdependent histopathological criteria and substantial inter-observer variability. Together with clinical partners, we curated a multi-center, expert-annotated histopathology dataset comprising 486 conjunctival biopsy image patches labeled along five clinically defined grading axes. Methodologically, we developed INTERACT-CMIL, a multi-task deep learning framework modeling inter-criterion dependencies via selective multi-head supervision and an inter-task consistency loss.

The proposed approach outperformed CNN and pathology foundation-model baselines (macro-F1 up to 85%), producing coherent and interpretable predictions aligned with expert grading standards. Methodological development and evaluation were coordinated within my group in close collaboration with the clinical partners.

Perspective

The project established a reproducible computational benchmark for CMIL grading and contributed to the standardization of digital ocular pathology. A related follow-up project on AI-assisted eyelid tumor analysis received a University of Bonn Prototype Grant, supporting translational development and clinical feasibility studies.

LYSTO: The lymphocyte assessment hackathon and benchmark dataset

Wed, 25 Oct 2023 00:00:00 +0000

Guest Editorial Special Issue on Federated Learning for Medical Imaging: Enabling Collaborative Development of Robust AI Models

Sun, 01 Jan 2023 00:00:00 +0000

Flamby: Datasets and benchmarks for cross-silo federated learning in realistic healthcare settings

Sat, 01 Jan 2022 00:00:00 +0000

FLamby: Federated learning benchmarks for realistic healthcare settings

Tue, 01 Jun 2021 00:00:00 +0000

Collaborators: EPFL (Switzerland), INRIA (France), University of Southern California (USA), Institut Polytechnique de Paris (France), University of California, Berkeley (USA)

A central bottleneck in federated learning research is the lack of realistic, multi-center benchmarks reflecting the heterogeneity of clinical data. Within this international collaboration, I contributed to the development of FLamby, a benchmark suite comprising seven real-world medical datasets with natural institutional splits across histopathology, radiology, dermatology, and tabular clinical data. Published at NeurIPS 2022 (Datasets and Benchmarks Track), FLamby demonstrated that standard federated learning approaches often underperform pooled training and highlighted the need for heterogeneity-aware optimization methods.

Our role

Contributing collaborator with responsibility for dataset preparation, benchmark design, and evaluation of federated learning methods.

Perspective

FLamby established a widely used community reference for cross-silo federated learning in healthcare. Its open-source release continues to inform benchmarking practices and supports subsequent federated learning studies and methodological developments.

The Federated Tumor Segmentation (FeTS) Challenge

Fri, 01 Jan 2021 00:00:00 +0000

Seamless Virtual Whole Slide Image Synthesis and Validation Using Perceptual Embedding Consistency

Wed, 19 Feb 2020 00:00:00 +0000

BigPicture Project

Wed, 01 Jan 2020 00:00:00 +0000

A new consortium of the EU Innovative Medicines Initiative (IMI) will establish the biggest database of pathology images to accelerate the development of artificial intelligence in medicine.

To take AI development in pathology to the next level, a European consortium combining leading European research centres, hospitals as well as major pharmaceutical industries, is going to develop a repository for the sharing of pathology data. The 6-year project called , will herald a new era in pathology.

Background

Pathology is the cornerstone of the workup of many diseases such as cancer, autoimmune diseases, of the follow up after transplantation and is also critical for the evaluation of the safety of drugs. It’s based on the examination of tissue samples (slides) under the microscope. However, despite its pivotal role, it still relies heavily on the qualitative interpretation by a qualified pathologist.

While the microscope symbolizes the profession, the digitalisation of slides in recent years ignited a revolution: not only images can now be shared and accessed from distant locations, they can also be processed by computers. This opens the door for artificial intelligence (AI) applications to assist the pathologist and help study diseases, find better treatments and contribute to the 3Rs (replace, reduce, and refine animal use in research). However, the development of robust AI applications requires large amounts of data, which in the case of pathology means a huge collection of digital slides and the medical data necessary for their interpretation. Sharing these has so far remained challenging due to the data storage capacity required to host a sufficiently large collection and to concerns regarding the confidential character of the medical information.

To allow the fast development of AI in pathology, the project aims to create the first European, ethical and GDPR-compliant (General Data Protection Regulation), quality-controlled platform, in which both large-scale data and AI algorithms will coexist. The platform will be developed in a sustainable and inclusive way by connecting communities of pathologists, researchers, AI developers, patients, and industry parties.

Our participation (TU Munich, until 2020)

Our involvement was limited to the period at TU Munich and ended in 2020, when Shadi Albarqouni moved from Munich; we are not part of the consortium since. In this project, , and from , together with will be leading and contributing to the development of Federated Deep Learning algorithms leveraging massive amounts of data, distributed in multiple sources, in a privacy-preserved fashion. This will enable deep learning models to be trained using sensitive data that cannot be made publicly available due to GPDR or sensitivity, e.g. rare diseases. Please visit the website of for further details.

Intended results

The project is divided into four main aspects that concern the large-scale collection of data. First, an infrastructure (hardware and software) must be created to store, share and process millions of images that can be gigabytes each. Second, legal and ethical constraints must be put in place to ensure adequate usage of data while fully respecting patient’s privacy and data confidentiality. Then, an initial set of 3 million digital slides from humans and laboratory animals will be collected and stored into the repository to provide data for the development of pathology AI tools. Finally, functionalities that aid the use of the database as well as the processing of images for diagnostic and research purposes will be developed.

Funding

This project has received funding from the Innovative Medicines Initiative 2 Joint Undertaking (IMI2 JU) under grant agreement No 945358. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA.

European Congress on Digital Pathology

Tue, 01 Jan 2019 00:00:00 +0000

Generalizing multistain immunohistochemistry tissue segmentation using one-shot color deconvolution deep neural networks

Tue, 01 Jan 2019 00:00:00 +0000

LYSTO: Benchmark and hackathon for lymphocyte assessment

Tue, 01 Jan 2019 00:00:00 +0000

Reliable assessment of tumor-infiltrating lymphocytes in immunohistochemistry is clinically relevant for prognosis and immunotherapy decision-making but remains time-consuming and subject to inter-observer variability. Within the international LYSTO initiative, I contributed to the development and consolidation of a benchmark initially introduced as a MICCAI 2019 hackathon. The benchmark comprises multi-center, multi-organ IHC datasets with over 170,000 cell-level annotations and formulates lymphocyte assessment as a weakly supervised learning problem. Multiple methods achieved pathologist-level agreement across institutions and organs, and extended analyses incorporating community feedback culminated in a comprehensive peer-reviewed publication in 2024.

Our role

Contributing collaborator with responsibility for methodological analysis, evaluation, and consolidation of benchmark results.

Perspective

LYSTO emphasizes the importance of sustained, community-driven benchmarking that extends beyond time-limited challenges. The experience informed subsequent work on multi-center robustness, evaluation, and trustworthy assessment of medical AI.

Perceptual Embedding Consistency for Seamless Reconstruction of Tilewise Style Transfer

Tue, 01 Jan 2019 00:00:00 +0000

Staingan: Stain style transfer for digital histological images

Tue, 01 Jan 2019 00:00:00 +0000

Virtualization of tissue staining in digital pathology using an unsupervised deep learning approach

Tue, 01 Jan 2019 00:00:00 +0000

Capsule networks against medical imaging data challenges

Mon, 01 Jan 2018 00:00:00 +0000

Fine-Tuning Deep Learning by Crowd Participation

Mon, 01 Jan 2018 00:00:00 +0000

Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer

Sun, 01 Jan 2017 00:00:00 +0000

Machine Learning for Biomedical Applications: From Crowdsourcing to Deep Learning

Sun, 01 Jan 2017 00:00:00 +0000

Aggnet: deep learning from crowds for mitosis detection in breast cancer histology images

Fri, 01 Jan 2016 00:00:00 +0000

Structure-preserving color normalization and sparse stain separation for histological images

Fri, 01 Jan 2016 00:00:00 +0000

Virtual staining in digital pathology: GAN-based stain virtualization of whole slide images

Fri, 01 Jan 2016 00:00:00 +0000

Histopathological evaluation is central to diagnosis and drug development, especially in oncology. Beyond the standard H&E stain, target-specific stains such as immunohistochemistry (IHC) are often needed — but tissue is scarce, staining is slow and costly, and every additional stain consumes another tissue section. Cancer-immunotherapy biomarker research adds the burden of manually annotating multistain slides.

What we did

Segmenting multistain slides from one shot. A fully convolutional network with one-shot colour deconvolution segments digitised slides with multiple stainings into tumour, healthy tissue, necrosis and background, generalising across immunohistochemistry stains to reduce pathologists’ annotation workload ( ).
Virtualizing the stain. Unsupervised style-transfer GANs generate realistic, clinically meaningful images of stained tissue — for example FAP-CK immunofluorescence from other stainings — opening the way to in-silico multiplexing of several stains on the same tissue section ( ).
Seamless at gigapixel scale. Whole slide images must be processed tile by tile, and instance normalization leaves visible tiling artifacts when the tiles are stitched back together. A perceptual embedding consistency loss removes these artifacts ( ), and the full framework was validated for seamless virtual whole-slide synthesis ( ).

Our role

Scientific lead as a postdoc at the Chair for Computer Aided Medical Procedures (TU Munich, PI: Nassir Navab), and co-supervision — with Eldad Klaiman (Roche Diagnostics, Penzberg) — of Amal Lahiani’s industrial PhD (2016–2020).

Perspective

The project showed that virtual staining can be made clinically interpretable and seamless at whole-slide scale, and seeded our later work on trustworthy digital staining in hematology.

Structure-preserved color normalization for histological images

Thu, 01 Jan 2015 00:00:00 +0000