3 papers
cs.CV2025
Uncertainty-Aware ControlNet: Bridging Domain Gaps with Synthetic Image Generation
Joshua Niemeijer, Jan Ehrhardt, Heinz Handels +1
Generative Models are a valuable tool for the controlled creation of high-quality image data. Controlled diffusion models like the ControlNet have allowed the creation of labeled d…
cs.CV2024
TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification
Joshua Niemeijer, Jan Ehrhardt, Hristina Uzunova +1
The usage of medical image data for the training of large-scale machine learning approaches is particularly challenging due to its scarce availability and the costly generation of…
cs.CV2024
LNQ Challenge 2023: Learning Mediastinal Lymph Node Segmentation with a Probabilistic Lymph Node Atlas
Sofija Engelson, Jan Ehrhardt, Timo Kepp +2
The evaluation of lymph node metastases plays a crucial role in achieving precise cancer staging, influencing subsequent decisions regarding treatment options. Lymph node detection…