PDF(Pubmed)
Abstract：
BACKGROUND: Oral tumors necessitate a dependable computer-assisted pathological diagnosis system considering their rarity and diversity. A content-based image retrieval (CBIR) system using deep neural networks has been successfully devised for digital pathology. No CBIR system for oral pathology has been investigated because of the lack of an extensive image database and feature extractors tailored to oral pathology.
METHODS: This study uses a large CBIR database constructed from 30 categories of oral tumors to compare deep learning methods as feature extractors.
RESULTS: The highest average area under the receiver operating characteristic curve (AUC) was achieved by models trained on database images using self-supervised learning (SSL) methods (0.900 with SimCLR and 0.897 with TiCo). The generalizability of the models was validated using query images from the same cases taken with smartphones. When smartphone images were tested as queries, both models yielded the highest mean AUC (0.871 with SimCLR and 0.857 with TiCo). We ensured the retrieved image result would be easily observed by evaluating the top 10 mean accuracies and checking for an exact diagnostic category and its differential diagnostic categories.
CONCLUSIONS: Training deep learning models with SSL methods using image data specific to the target site is beneficial for CBIR tasks in oral tumor histology to obtain histologically meaningful results and high performance. This result provides insight into the effective development of a CBIR system to help improve the accuracy and speed of histopathology diagnosis and advance oral tumor research in the future.
METHODS: This study uses a large CBIR database constructed from 30 categories of oral tumors to compare deep learning methods as feature extractors.
RESULTS: The highest average area under the receiver operating characteristic curve (AUC) was achieved by models trained on database images using self-supervised learning (SSL) methods (0.900 with SimCLR and 0.897 with TiCo). The generalizability of the models was validated using query images from the same cases taken with smartphones. When smartphone images were tested as queries, both models yielded the highest mean AUC (0.871 with SimCLR and 0.857 with TiCo). We ensured the retrieved image result would be easily observed by evaluating the top 10 mean accuracies and checking for an exact diagnostic category and its differential diagnostic categories.
CONCLUSIONS: Training deep learning models with SSL methods using image data specific to the target site is beneficial for CBIR tasks in oral tumor histology to obtain histologically meaningful results and high performance. This result provides insight into the effective development of a CBIR system to help improve the accuracy and speed of histopathology diagnosis and advance oral tumor research in the future.
摘要：
背景：考虑到口腔肿瘤的稀有性和多样性，需要一个可靠的计算机辅助病理诊断系统。已成功设计出使用深度神经网络的基于内容的图像检索（CBIR）系统，用于数字病理学。由于缺乏针对口腔病理学量身定制的广泛的图像数据库和特征提取器，因此尚未研究用于口腔病理学的CBIR系统。
方法：本研究使用从30类口腔肿瘤中构建的大型CBIR数据库来比较深度学习方法作为特征提取器。
结果：通过使用自监督学习（SSL）方法（SimCLR为0.900，TiCo为0.897）在数据库图像上训练的模型，获得了接收器工作特征曲线（AUC）下的最高平均面积。使用来自使用智能手机拍摄的相同案例的查询图像验证了模型的可泛化性。当智能手机图像作为查询进行测试时，两种模型的平均AUC最高(SimCLR为0.871，TiCo为0.857)。我们通过评估前10个平均准确度并检查确切的诊断类别及其鉴别诊断类别来确保检索到的图像结果很容易观察到。
结论：使用特定于目标部位的图像数据使用SSL方法训练深度学习模型有利于口腔肿瘤组织学中的CBIR任务，以获得组织学上有意义的结果和高性能。这一结果为CBIR系统的有效开发提供了见解，以帮助提高组织病理学诊断的准确性和速度，并在未来推进口腔肿瘤研究。
方法：本研究使用从30类口腔肿瘤中构建的大型CBIR数据库来比较深度学习方法作为特征提取器。
结果：通过使用自监督学习（SSL）方法（SimCLR为0.900，TiCo为0.897）在数据库图像上训练的模型，获得了接收器工作特征曲线（AUC）下的最高平均面积。使用来自使用智能手机拍摄的相同案例的查询图像验证了模型的可泛化性。当智能手机图像作为查询进行测试时，两种模型的平均AUC最高(SimCLR为0.871，TiCo为0.857)。我们通过评估前10个平均准确度并检查确切的诊断类别及其鉴别诊断类别来确保检索到的图像结果很容易观察到。
结论：使用特定于目标部位的图像数据使用SSL方法训练深度学习模型有利于口腔肿瘤组织学中的CBIR任务，以获得组织学上有意义的结果和高性能。这一结果为CBIR系统的有效开发提供了见解，以帮助提高组织病理学诊断的准确性和速度，并在未来推进口腔肿瘤研究。
