[论文解读] Atherosclerotic carotid plaques on panoramic imaging: an automatic detection using deep learning with small dataset

Lazar Kats, Marilena Vered+2 more|arXiv (Cornell University)|Aug 24, 2018

Cerebrovascular and Carotid Artery Diseases参考文献 19被引用 6

一句话总结

本研究提出了一种基于小样本数据集（65张图像）的Faster R-CNN深度学习模型，用于在常规牙科曲面断层X光片中自动检测动脉粥样硬化性颈动脉斑块（ACPs）。尽管训练数据有限，该方法仍实现了75%的敏感性、80%的特异性和83%的准确率，证明了在牙科环境中用于早期脑卒中预防的可行性。

ABSTRACT

Stroke is the second most frequent cause of death worldwide with a considerable economic burden on the health systems. In about 15% of strokes, atherosclerotic carotid plaques (ACPs) constitute the main etiological factor. Early detection of ACPs may have a key-role for preventing strokes by managing the patient a-priory to the occurrence of the damage. ACPs can be detected on panoramic images. As these are one of the most common images performed for routine dental practice, they can be used as a source of available data for computerized methods of automatic detection in order to significantly increase timely diagnosis of ACPs. Recently, there has been a definite breakthrough in the field of analysis of medical images due to the use of deep learning based on neural networks. These methods, however have been barely used in dentistry. In this study we used the Faster Region-based Convolutional Network (Faster R-CNN) for deep learning. We aimed to assess the operation of the algorithm on a small database of 65 panoramic images. Due to a small amount of available training data, we had to use data augmentation by changing the brightness and randomly flipping and rotating cropped regions of interest in multiple angles. Receiver Operating Characteristic (ROC) analysis was performed to calculate the accuracy of detection. ACP was detected with a sensitivity of 75%, specificity of 80% and an accuracy of 83%. The ROC analysis showed a significant Area Under Curve (AUC) difference from 0.5. Our novelty lies in that we have showed the efficiency of the Faster R-CNN algorithm in detecting ACPs on routine panoramic images based on a small database. There is a need to further improve the application of the algorithm to the level of introducing this methodology in routine dental practice in order to enable us to prevent stroke events.

研究动机与目标

• 开发一种用于在曲面牙科X光片中自动检测动脉粥样硬化性颈动脉斑块（ACPs）的方法。
• 评估在牙科领域受限的标注医学影像数据下，深度学习在小样本图像数据集上的性能表现。
• 探索将常规牙科曲面成像技术重新用于早期脑卒中风险检测的潜力。
• 评估将基于人工智能的ACPs检测方法整合到常规牙科实践中以实现预防性医疗的可行性。

提出的方法

• 采用Faster区域卷积神经网络（Faster R-CNN）对曲面牙科X光片进行目标检测。
• 应用数据增强技术，包括亮度调节、随机翻转和感兴趣区域的旋转，以提升训练数据的多样性。
• 使用包含65张曲面图像的小样本数据集，其中ACPs由人工手动标注，用于模型训练与验证。
• 通过受试者工作特征（ROC）分析评估检测性能，并计算曲线下面积（AUC）。
• 采用迁移学习原则，端到端训练模型，以将预训练特征适配至牙科影像领域。
• 通过学习率调度策略优化模型，使用随机梯度下降法，以提升在有限数据上的收敛性能。

实验结果

研究问题

• RQ1 尽管训练数据集较小，深度学习模型是否能在曲面牙科X光片中实现高精度检测动脉粥样硬化性颈动脉斑块？
• RQ2 在牙科有限医学影像数据上，数据增强技术在提升Faster R-CNN模型泛化能力方面的有效性如何？
• RQ3 该方法在曲面X光片上识别ACPs的敏感性和特异性如何？
• RQ4 常规牙科曲面成像是否可作为早期检测与脑卒中相关的血管病变的可行来源？
• RQ5 该模型的性能在多大程度上接近临床实用化，可用于预防性脑卒中筛查？

主要发现

• 所提出的Faster R-CNN模型在曲面牙科X光片中检测动脉粥样硬化性颈动脉斑块的敏感性达到75%。
• 该模型表现出80%的特异性，表明其在正确识别无斑块病例方面具有较强能力。
• 在65张曲面图像的测试集上，检测系统的总体准确率达到83%。
• 受试者工作特征曲线下面积（AUC）与0.5存在统计学上显著差异，证实了模型的判别能力。
• 数据增强技术显著提升了模型在小样本数据集上的鲁棒性和泛化能力。
• 本研究证实了在有限牙科影像数据上应用深度学习技术，实现对与脑卒中相关的血管病变早期检测的可行性。