From inconsistent annotations to ground truth: Aggregation strategies for annotations of proximal carious lesions in dental imagery.

Journal: Journal of dentistry
Published Date: Mar 30, 2025

Abstract

OBJECTIVES: Annotating carious lesions on images is challenging. For artificial intelligence (AI) applications, the aggregation of heterogeneous multi-examiner annotations into one single annotation (e.g. via majority voting, MV) is usually needed. We assessed different aggregation strategies for multi-examiner annotations of primary proximal carious lesions on orthoradial radiographs and Near-Infrared Light Transillumination (NILT) images.

Authors

  • Vanessa Klein
    Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Berlin, Germany; Conservative Dentistry and Periodontology, LMU University Hospital, LMU Munich, Munich, Germany.
  • Martha Büttner
    Charité - Universitätsmedizin Berlin, Berlin, Germany. bdjmanuscripts@nature.com.
  • Gerd Göstemeyer
    Department of Operative and Preventive Dentistry, Charité-Universitätsmedizin Berlin, Berlin, Germany.
  • Sarina Rolle
    Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Antonín Tichý
    Institute of Dental Medicine, First Faculty of Medicine of the Charles University and General University Hospital, Prague, Czech Republic.
  • Falk Schwendicke
    Department of Operative and Preventive Dentistry, Charité - Universitätsmedizin Berlin, Berlin, Germany. falk.schwendicke@charite.de.
  • Noah F Nordblom
    Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Berlin, Germany. Electronic address: noah.nordblom@charite.de.

Keywords

External Resources

Popular Topics
Recent Journals