Publications Repository - Helmholtz-Zentrum Dresden-Rossendorf

2 Publications

Label-efficient Machine Learning for Diagnosing Urinary Tract Infection (UTI) in Urine Microscopy

De, T.; Liou, N.; Horsley, H.; Yakimovich, A.


Urinary tract infections (UTI) belong to the most common clinically relevant bacterial infections. 1 in 3 women worldwide will have at least one UTI by 24 years of age and 40 - 50% of women will experience one UTI during their lifetime with 44% experiencing recurrences. In this project, using a clinical dataset of brightfield microscopy of patients’ urine with few annotated samples,
we aim to develop a diagnostic phenotype quantification workflow using label-efficient machine learning (ML) approaches. There are several challenges to the clinical dataset at hand. Firstly, in the absence of specific labeling for phenotype-relevant objects in the micrographs ground truth is ambiguous. Secondly, obtaining manual annotations is laborious and requires highly-skilled annotators. Thirdly, the variation in scale and shape of a particular type of phenotype-relevant object is challenging for instance segmentation.

Keywords: urinary tract infection; clinical dataset; microscopy; label-efficient machine learning; ambiguous ground truth; phenotype quantification

  • Poster
    IDESSAI 2022, 29.08.2022, Saarland, Germany
  • Poster
    Big data analytical methods for complex systems, 06.10.2022, Wroclaw, Poland


Years: 2023 2022 2021 2020 2019 2018 2017 2016 2015