Polytechnic School University of São Paulo, Av. Prof. Luciano Gualberto, 158 - Butantã, São Paulo, 05089030, São Paulo, Brazil.
University of São Paulo, Alameda Dr. Octávio Pinheiro Brisolla, Quadra 9, Bauru, 17012901, São Paulo, Brazil.
Comput Biol Med. 2024 Dec;183:109221. doi: 10.1016/j.compbiomed.2024.109221. Epub 2024 Oct 7.
Diagnosing dental caries poses a significant challenge in dentistry, necessitating precise and early detection for effective management. This study utilizes Self-Supervised Learning (SSL) tasks to improve the classification of dental caries in Cone Beam Computed Tomography (CBCT) images, employing the International Caries Detection and Assessment System (ICDAS). Faced with the challenge of scarce annotated medical images, our research employs SSL to utilize unlabeled data, thereby improving model performance. We have developed a pipeline incorporating unlabeled data extraction from CBCT exams and subsequent model training using SSL tasks. A distinctive aspect of our approach is the integration of image processing techniques with SSL tasks, along with exploring the necessity for unlabeled data. Our research aims to identify the most effective image processing techniques for data extraction, the most efficient deep learning architectures for caries classification, the impact of unlabeled dataset sizes on model performance, and the comparative effectiveness of different SSL approaches in this domain. Among the tested architectures, ResNet-18, combined with the SimCLR task, demonstrated an average F1-score macro of 88.42%, Precision macro of 90.44%, and Sensitivity macro of 86.67%, reaching a 5.5% increase in F1-score compared to models using only deep learning architecture. These results suggest that SSL can significantly enhance the accuracy and efficiency of caries classification in CBCT images.
在牙科领域，诊断龋齿是一项极具挑战性的任务，需要精确且及早地发现龋齿，以便进行有效的管理。本研究利用自监督学习（SSL）任务来提高基于 Cone Beam Computed Tomography（CBCT）图像的龋齿分类准确性，采用国际龋齿检测和评估系统（ICDAS）作为评估标准。鉴于医学图像标注数据稀缺的挑战，我们的研究利用 SSL 来利用未标注数据，从而提高模型性能。我们开发了一个包含从 CBCT 检查中提取未标注数据，以及使用 SSL 任务进行模型训练的流水线。我们的方法的一个显著特点是将图像处理技术与 SSL 任务相结合，并探索未标注数据的必要性。我们的研究旨在确定最有效的数据提取图像处理技术、最有效的龋齿分类深度学习架构、未标注数据集大小对模型性能的影响，以及不同 SSL 方法在该领域的比较有效性。在测试的架构中，ResNet-18 与 SimCLR 任务相结合，平均 F1-score 宏值为 88.42%，精度宏值为 90.44%，敏感度宏值为 86.67%，与仅使用深度学习架构的模型相比，F1-score 提高了 5.5%。这些结果表明，SSL 可以显著提高 CBCT 图像中龋齿分类的准确性和效率。
