Self-supervised learning methods for label-efficient dental caries classification

• Autor(a) principal: Taleb, Aiham
• Data de Publicação: 2022
• Outros Autores: Rohrer, Csaba, Bergner, Benjamin Sebastian, De Leon, Guilherme, Rodrigues, Jonas de Almeida, Schwendicke, Falk, Lippert, Christoph, Krois, Joachim
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Institucional da UFRGS
• Texto Completo: http://hdl.handle.net/10183/242600
• topic: Cárie dentária; Unsupervised methods; Self-supervised learning; Representation learning; Dental caries classification; Data driven approaches; Annotation efficient deep learning

High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. In this work, we propose employing self-supervised methods. To that end, we trained with three selfsupervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. In other words, the resulting models can be fine-tuned using few labels (annotations). Our results show that using as few as 18 annotations can produce ě45% sensitivity, which is comparable to human-level diagnostic performance. This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.