Büttner Martha, Schneider Lisa, Krasowski Aleksander, Pitchika Vinay, Krois Joachim, Meyer-Lueckel Hendrik, Schwendicke Falk
Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Germany; ITU/WHO Focus Group AI4Health.
Department of Oral Diagnostics, Digital Health and Health Services Research, Charité - Universitätsmedizin Berlin, Germany.
J Dent. 2024 Sep;148:105063. doi: 10.1016/j.jdent.2024.105063. Epub 2024 May 10.
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.
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 %).
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.
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.
现实世界数据集的不平衡特性是机器学习和深度学习领域中一个持续存在的挑战。在医学和牙科领域，大多数数据样本代表未受疾病影响的患者，并且在图像方面，病理图像区域通常小于健康区域。在深度学习过程中选择合适的损失函数至关重要，这可能有助于克服由此产生的不平衡。我们针对一项示例性任务——咬合翼片X线片上的牙齿结构分割，评估了六种不同损失函数的性能。
在1625张咬合翼片X线片的牙齿结构分割任务中，比较了六种不同的损失函数（焦点损失、骰子损失、Tversky损失以及交叉熵与骰子损失的混合损失、焦点与骰子损失、焦点与广义骰子损失）。使用三种不同的模型架构（U-Net、Linknet、DeepLabV3+）进行了5折交叉验证训练。牙齿结构由以下类别组成（在像素级别上样本出现的百分比/测量的捕获区域）：牙釉质（100%/25%）、牙本质（100%/50%）、根管（100%/10%）、充填物（81%/8%）和牙冠（28%/5%）。
混合损失函数显著优于单独的损失函数，并且在牙釉质、牙本质、根管和充填物类别上，不同架构均能得到稳健的结果。具体而言，骰子焦点损失分别在克服图像级别和像素级别类别不平衡方面达到了高性能。
在牙科应用案例中，准确预测少数类别（如病变）通常很重要。在训练深度学习模型时，使用特定的损失函数可能是克服数据不平衡的有效策略。
