Archived record. This site preserves the DAISYlabs project (2018–2021). The group is no longer active. Content reflects the state of the project at its conclusion; some links may no longer work.
DAISYlabs competed in international medical imaging challenges and published peer-reviewed methods for skin lesion analysis, histopathology segmentation, and radiology image processing.
DAISYlabs was a joint effort of PhD, MSc and MD students of the University Medical Center Hamburg-Eppendorf (UKE) and the Hamburg University of Technology (TUHH) to establish a deep learning platform for biomedical image processing that allowed efficient collaboration and knowledge exchange between UKE and TUHH working groups in the field of biomedical imaging and image processing. It was funded by Forschungszentrum Medizintechnik Hamburg ( fmthh).
Team members as of the project’s conclusion (2021).
We developed AI systems for medical image processing challenges (2018–2019).
1st rank of 16 unique teams in Task 2: Lesion diagnosis with images and metadata
1st rank of 64 unique teams in Task 1: Lesion diagnosis with images only
2nd rank of 77 unique teams in Task 3: Lesion Diagnosis
7th rank of 17 unique teams in Task 2: Viable Tumor Burden Estimation
7th rank of 27 unique teams in Task 1: Liver Cancer Segmentation
7th rank of 17 unique teams in Task 4: Gross Target Volume segmentation of lung cancer
7th rank of 40 unique teams in Task 2: Three Label Segmentation
8th rank of 17 unique teams in Task 3: Organ-at-risk segmentation from chest CT scans
11th rank of 77 unique teams in Task 1: Lesion Boundary Segmentation
Top 20% of 1475 unique teams in identifing Pneumothorax disease in chest x-rays