Conquering Class Imbalances in Deep Learning-based Segmentation of Dental Radiographs with Different Loss Functions.

Büttner, Martha; Schneider, Lisa; Krasowski, Aleksander; Pitchika, Vinay; Krois, Joachim; Meyer-Lueckel, Hendrik; Schwendicke, Falk (2024). Conquering Class Imbalances in Deep Learning-based Segmentation of Dental Radiographs with Different Loss Functions. (In Press). Journal of dentistry, 105063, p. 105063. Elsevier Science 10.1016/j.jdent.2024.105063

Text 1-s2.0-S030057122400232X-main.pdf - Accepted Version Restricted to registered users only until 10 May 2025. Available under License Publisher holds Copyright. Download (981kB) | Request a copy

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.

METHODS

Six different loss functions (Focal Loss, Dice Loss, Tversky Loss and hybrid losses of Cross-Entropy and Dice Loss, Focal and Dice Loss, Focal and Generalized Dice Loss) were compared on a tooth structure segmentation task of 1,625 bitewing radiographs. Training was performed using three different model architectures (U-Net, Linknet, DeepLavbV3+) over a 5-fold cross-validation. Tooth structures consisted of the classes (occurrence in % of samples/captures areas measured on pixel level) enamel (100%/25%), dentin (100%/50%), root canal (100%/10%), filling (81%/8%) and crown (28%/5%).

RESULTS

Hybrid loss functions significantly outperformed standalone ones and provided robust results over the different architectures for the classes enamel, dentin, root canal and filling. Specifically, the Dice Focal loss reached high performance to conquer both image level and pixel level class imbalance, respectively.

CLINICAL SIGNIFICANCE

In dental use cases it is often important to predict minority classes such as pathologies accurately. Using specific loss function may be an effective strategy to overcome data imbalance when training deep learning models.

Interest & Impact

Downloads

0 since deposited on 13 May 2024
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item