5 papers
Extending GouDa: Generation of Universal Datasets with (and without) Errors for Data Quality Benchmarking
Valerie Restat, André Conrad, Kevin M. Kramer +1
Synthetic data is extremely important in areas such as data quality, data cleaning, and machine learning. It enables the analysis of use cases in which real data is insufficient, u…
Rethinking Pulmonary Embolism Segmentation: A Study of Current Approaches and Challenges with an Open Weight Model
Yixin Zhang, Ryan Chamberlain, Lawrence Ngo +2
Pulmonary Embolism (PE) is a life-threatening condition for which accurate and timely detection is critical to patient care. However, our systematic study of PE segmentation algori…
Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects
Yixin Zhang, Nicholas Konz, Kevin Kramer +1
Image segmentation foundation models (SFMs) like Segment Anything Model (SAM) have achieved impressive zero-shot and interactive segmentation across diverse domains. However, they…
Towards Next Generation Data Engineering Pipelines
Kevin M. Kramer, Valerie Restat, Sebastian Strasser +2
Data engineering pipelines are a widespread way to provide high-quality data for all kinds of data science applications. However, numerous challenges still remain in the compositio…
How to select slices for annotation to train best-performing deep learning segmentation models for cross-sectional medical images?
Yixin Zhang, Kevin Kramer, Maciej A. Mazurowski
Automated segmentation of medical images heavily relies on the availability of precise manual annotations. However, generating these annotations is often time-consuming, expensive,…