Bildverarbeitung für die Medizin 2022

15 papers
The 2022 edition of Bildverarbeitung für die Medizin (BVM) featured research focused on advancing medical image analysis through automated deep learning and standardized data infrastructures. A primary research direction involved self-configuring neural networks, exemplified by the nnDetection method for medical object detection. Other technical themes included anchor-free architectures, geometric priors for optimization, and the integration of local inductive biases with global contextual attention. Researchers also explored unsupervised anomaly detection and the evaluation of semi-supervised learning models on imbalanced medical datasets. Beyond algorithmic development, the proceedings emphasized bridging the gap between technical innovation and clinical utility. Notable work included the use of formal consensus methods to standardize scientific frameworks and define patient benefits in surgical data science. Infrastructure projects like Kaapana were highlighted for their role in enabling efficient DICOM image tagging and whole slide imaging for computational pathology. Clinical applications spanned longitudinal analysis of COVID-19 disease progression and multi-sequence 3D MRI brain classification. Prolific contributors to this year's volume included Klaus H. Maier-Hein, Fabian Isensee, and Paul F. Jäger.

Top Research Directions

The 8 research directions with Bildverarbeitung für die Medizin 2022 papers, ranked by paper count, next to 2021. Share is the fraction of the edition’s papers in the direction.

#Direction20222021Share 2022Share 20212021 rank
1Automated Quality Control for Large Medical Imaging Datasets106.7%0.0%—
2Bridging the Clinical Translation Gap for Machine Learning116.7%4.5%5
3Dataset Specific Anchor Box Optimization106.7%0.0%—
4Efficient Hyperparameter Optimization via Multi Fidelity and Online Tuning106.7%0.0%—
5Eliminating Predefined Anchors in Object Detection106.7%0.0%—
6Iterative Consensus Building with the Delphi Method106.7%0.0%—
7Overcoming Clinical Data Fragmentation for Medical AI106.7%0.0%—
8Self-Configuring Frameworks for Medical Image Segmentation116.7%4.5%41

Download all directions as CSV

Institutions

Institutions credited by Bildverarbeitung für die Medizin 2022 papers: a paper credits every institution named in its affiliations, once. 9 institutions share 5 credited papers.

#InstitutionPapersShare20212021 rank
1Friedrich-Alexander-Universität Erlangen-Nürnberg 240.0%41
2German Cancer Research Center 240.0%26
3Technische Hochschule Ingolstadt 240.0%22
4University of Veterinary Medicine Vienna 240.0%0—
503kf3ks42 120.0%24
6Freie Universität Berlin 120.0%25
7Michigan State University 120.0%116
8Technische Universität Darmstadt 120.0%118
9University Hospital Frankfurt 120.0%111

Download all institutions as CSV

About this data

Papers. Bildverarbeitung für die Medizin 2022 lists 15 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2021 use shares, since the edition went from 22 to 15 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 5 of 15 papers (33.3%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Bildverarbeitung für die Medizin 2022”, https://lacuna.tiptreesystems.com/venue/bildverarbeitung-fur-die-medizin/2022.

Top Authors

AuthorPapers
Klaus Maier-Hein6
Lena Maier-hein3
David Zimmerer2
Paul F Jaeger2
Benjamin Bergner1
Camila Gonzalez1
Carsten T. Lüth1
Chang Liu1
Christoph Lippert1
Gregor Koehler1
Jens Kleesiek1
Maximilian Zenk1
Michael Baumgartner1
Sarina Thomas1

Papers

Title
Abstract: C-arm Positioning for Spinal Standard Projections in Different Intra-operative Settings
Abstract: How to Generate Patient Benefit with Surgical Data Science - Results of an International Delphi Process
Abstract: nnDetection - A Self-configuring Method for Medical Object Detection
Abstract: Task Fingerprinting for Meta Learning in Biomedical Image Analysis
Deep Learning-based Automatic Assessment of AgNOR-scores in Histopathology Images
Deep Learning-based Subtyping of Atypical and Normal Mitoses using a Hierarchical Anchor-free Object Detector
Deep Learning Models for 3D MRI Brain Classification - A Multi-sequence Comparison
DICOM Whole Slide Imaging for Computational Pathology Research in Kaapana and the Joint Imaging Platform
Efficient DICOM Image Tagging and Cohort Curation Within Kaapana
Extending nnU-Net Is All You Need
Longitudinal Analysis of Disease Progression Using Image and Laboratory Data for Covid-19 Patients
Multi-organ Segmentation with Partially Annotated Datasets
Quality Monitoring of Federated Covid-19 Lesion Segmentation
Realistic Evaluation of FixMatch on Imbalanced Medical Image Classification Tasks
Unsupervised Anomaly Detection in the Wild