Deep metric learning for otitis media classification

Josefine Vilsbøll Sundgaard*, James Harte, Peter Bray, Søren Laugesen, Yosuke Kamide, Chiemi Tanaka, Rasmus R. Paulsen, Anders Nymark Christensen

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

318 Downloads (Pure)


In this study, we propose an automatic diagnostic algorithm for detecting otitis media based on otoscopy images of the tympanic membrane. A total of 1336 images were assessed by a medical specialist into three diagnostic groups: acute otitis media, otitis media with effusion, and no effusion. To provide proper treatment and care and limit the use of unnecessary antibiotics, it is crucial to correctly detect tympanic membrane abnormalities, and to distinguish between acute otitis media and otitis media with effusion. The proposed approach for this classification task is based on deep metric learning, and this study compares the performance of different distance-based metric loss functions. Contrastive loss, triplet loss and multi-class N-pair loss are employed, and compared with the performance of standard cross-entropy and class-weighted cross-entropy classification networks. Triplet loss achieves high precision on a highly imbalanced data set, and the deep metric methods provide useful insight into the decision making of a neural network. The results are comparable to the best clinical experts and paves the way for more accurate and operator-independent diagnosis of otitis media.

Original languageEnglish
Article number102034
JournalMedical Image Analysis
Number of pages9
Publication statusPublished - Jul 2021

Bibliographical note

Funding Information:
We would like to thank William Demant Fonden (Denmark) for financially supporting this study.

Publisher Copyright:
© 2021


  • Convolutional neural network
  • Deep metric learning
  • Image classification
  • Otitis media


Dive into the research topics of 'Deep metric learning for otitis media classification'. Together they form a unique fingerprint.

Cite this