Conquering class imbalances in deep learning-based segmentation of dental radiographs with different loss functions.

Journal: Journal of dentistry
PMID: 38735467

Abstract

OBJECTIVE: The imbalanced nature of real-world datasets is an ongoing challenge in the field of machine and deep learning. In medicine and in dentistry, most data samples represent patients not affected by pathologies, and on imagery, pathologic image areas are often smaller than healthy ones. Selecting suitable loss functions during deep learning is essential and may help to overcome the resulting imbalance. We assessed six different loss functions for one exemplary task, tooth structure segmentation on bitewing radiographs, for their performance.

Authors

  • Martha Büttner
    Charité - Universitätsmedizin Berlin, Berlin, Germany. bdjmanuscripts@nature.com.
  • Lisa Schneider
    Department of Simulation and Graphics, Otto von Guericke University Magdeburg, Germany.
  • Aleksander Krasowski
    Department of Oral Diagnostics, Digital Health and Health Services Research, Charité-Universitätsmedizin Berlin, Aßmannshauser Str. 4-6, 14197, Berlin, Germany.
  • Vinay Pitchika
    Clinic for Conservative Dentistry and Periodontology, Ludwig-Maximilians-University Munich, Germany.
  • Joachim Krois
    Department of Operative and Preventive Dentistry, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Hendrik Meyer-Lueckel
    Department of Restorative, Preventive and Pediatric Dentistry, Zmk Bern, University of Bern, Bern, Switzerland.
  • Falk Schwendicke
    Department of Operative and Preventive Dentistry, Charité - Universitätsmedizin Berlin, Berlin, Germany. falk.schwendicke@charite.de.

Keywords

External Resources

Popular Topics
Recent Journals