Research Focus

• Medical Data Science and AI
• Explainable AI in medical settings
• Special focus: dysphagia

Projects

ManoVis

The subject of the ManoVis cooperation project is the development of optimised, multimodal analysis methods for diseases of the oesophagus. The focus is on the development of a diagnostic system that enables an optimal, functional and morphological evaluation of the oesophageal movement (motility). Up to now, the conventional approach to diagnosis has been to carry out various measurement methods (X-ray kinematography, pressure measurement, impedance measurement) one after the other. However, the direct temporal relationship between the individual measurements is lost, which reduces the diagnostic significance. The aim of the project is therefore the temporal synchronisation of the different modalities as well as the development of a fused visualization that combines all relevant partial information of the individual modalities and presents it in an intuitively understandable way.

FAIRPLAN

The aim of the FAIRPLAN project is to generate AI-based shift and OR schedules in hospitals, to make personnel planning fairer and more efficient through a multidimensional approach, to flexibly consider employee wishes in planning and to utilize resources more efficiently.

Publications

2025

• A. Geiger, L. Wagner, D. Rueckert, D. Wilhelm, A. Jell, "On the notion of missingness for path attribution explainability methods in medical settings: Guiding the selection of medically meaningful baselines", preprint, 2025 [link] [pdf]

2024

• A. Geiger, L. Bernhard, F. Gassert, H. Feußner, D. Wilhelm, H. Friess, A. Jell, "Towards multimodal visualization of esophageal motility: fusion of manometry, impedance, and videofluoroscopic image sequences", Int J CARS, 2024, [link] [pdf]
• A. Geiger, L. Wagner, D. Rueckert, D. Wilhelm, A. Jell, "Detecting and clustering swallow events in esophageal long-term high-resolution manometry", preprint, 2024 [link] [pdf]

2021

• D. Liu, K. Veeramachaneni, A. Geiger, V. OK Li, H. Qu, "AQEyes: Visual Analytics for Anomaly Detection and Examination of Air Quality Data", preprint, 2021, [link] [pdf]

2020

• A. Geiger, D. Liu, S. Alnegheimish, A. Cuesta-Infante and K. Veeramachaneni, "TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks", 2020 IEEE International Conference on Big Data (Big Data), 2020, [link] [pdf]

Talks

2024

• "Towards multimodal visualization of esophageal motility: fusion of manometry, impedance, and videofluoroscopic image sequences", CARS 2024, Barcelona
• "Fused multi-modal diagnostics of esophageal motility", DGE-BV 2024, Berlin