超越真值:一种用于诊断牙科分割中校准盲区的启发式无监督质量保证引擎
Beyond Ground Truth: A Heuristic Unsupervised Quality Assurance Engine for Diagnosing Calibrational Blindness in Dental Segmentation
AI总结:
本研究针对牙科X光分割的校准盲区问题,提出无监督质量保证引擎HUS-QA,无需真值即可评估分割质量,其性能优于标准置信度方法,可作为临床质控工具。
摘要:
在实际临床场景中,使用深度学习方法进行牙科X光分割存在可靠性问题。即使分割质量很差,深度学习模型对其预测仍表现出高置信度(即校准盲区)。此外,在实际使用中,医生没有真值掩码来检查分割的准确性。为解决该问题,我们提出一种名为HUS-QA的简单质量检查引擎,包含三个阶段。我们在PRAD(根尖周牙科X光)数据集上训练SimCLR自监督ResNet-18 U-Net模型,该模型生成分割掩码并评估其质量。我们的HUS-QA无需真值掩码即可检查分割掩码质量,本研究考虑的简单指标包括预测置信度、边缘清晰度、形状连通性和面积大小惩罚。结果显示,标准置信度方法表现不佳(r=-0.1394,p=1.7864e-3,ROC AUC=0.4275);相比之下,我们的HUS-QA与实际Dice分数呈正相关(r=0.4647,p=3.7510e-28),且达到0.8405的强ROC-AUC。因此,HUS-QA可作为临床质量控制的实用工具。
英文摘要:
In real-world clinical settings, dental X-ray segmentation using deep learning methods suffers from reliability issues. Even when the segmentation quality is bad, deep learning models show high confidence in their predictions (calibrational blindness). Moreover, in real use, doctors do not have ground-truth masks to check their accuracy. To address this problem, we introduce a simple quality-checking engine called HUS-QA with three stages. We train it on the PRAD (Periapical Dental X-ray) dataset to build our SimCLR self-supervised ResNet-18 U-Net model, which generates the segmentation mask and then evaluates its quality. Our HUS-QA checks the segmentation mask quality without a ground-truth mask. Prediction confidence, edge sharpness, shape connectivity, and area-size penalty are the simple indicators considered in this research. Results show that standard confidence methods fail (r = -0.1394, p = 1.7864e-3, ROC AUC = 0.4275). By contrast, our HUS-QA shows a positive correlation with actual Dice scores (r = 0.4647, p = 3.7510e-28) and achieves a strong ROC-AUC of 0.8405. Therefore, HUS-QA serves as a practical tool for clinical quality control.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。