Abstract：
BACKGROUND: Early diagnosis in oral cancer is essential to reduce both morbidity and mortality. This study explores the use of uncertainty estimation in deep learning for early oral cancer diagnosis.
METHODS: We develop a Bayesian deep learning model termed \'Probabilistic HRNet\', which utilizes the ensemble MC dropout method on HRNet. Additionally, two oral lesion datasets with distinct distributions are created. We conduct a retrospective study to assess the predictive performance and uncertainty of Probabilistic HRNet across these datasets.
RESULTS: Probabilistic HRNet performs optimally on the In-domain test set, achieving an F1 score of 95.3% and an AUC of 96.9% by excluding the top 30% high-uncertainty samples. For evaluations on the Domain-shift test set, the results show an F1 score of 64.9% and an AUC of 80.3%. After excluding 30% of the high-uncertainty samples, these metrics improve to an F1 score of 74.4% and an AUC of 85.6%.
CONCLUSIONS: Redirecting samples with high uncertainty to experts for subsequent diagnosis significantly decreases the rates of misdiagnosis, which highlights that uncertainty estimation is vital to ensure safe decision making for computer-aided early oral cancer diagnosis.
METHODS: We develop a Bayesian deep learning model termed \'Probabilistic HRNet\', which utilizes the ensemble MC dropout method on HRNet. Additionally, two oral lesion datasets with distinct distributions are created. We conduct a retrospective study to assess the predictive performance and uncertainty of Probabilistic HRNet across these datasets.
RESULTS: Probabilistic HRNet performs optimally on the In-domain test set, achieving an F1 score of 95.3% and an AUC of 96.9% by excluding the top 30% high-uncertainty samples. For evaluations on the Domain-shift test set, the results show an F1 score of 64.9% and an AUC of 80.3%. After excluding 30% of the high-uncertainty samples, these metrics improve to an F1 score of 74.4% and an AUC of 85.6%.
CONCLUSIONS: Redirecting samples with high uncertainty to experts for subsequent diagnosis significantly decreases the rates of misdiagnosis, which highlights that uncertainty estimation is vital to ensure safe decision making for computer-aided early oral cancer diagnosis.
摘要：
背景：口腔癌的早期诊断对于降低发病率和死亡率至关重要。本研究探讨不确定性估计在深度学习中用于早期口腔癌诊断。
方法：我们开发了一种称为“概率HRNet”的贝叶斯深度学习模型，它利用HRNet上的集成MCdropout方法。此外,创建了两个具有不同分布的口腔病变数据集。我们进行了一项回顾性研究，以评估这些数据集的概率HRNet的预测性能和不确定性。
结果：概率HRNet在域内测试集上表现最佳，通过排除前30%的高不确定度样本，获得95.3%的F1评分和96.9%的AUC。对于Domain-shift测试集的评估，结果显示F1评分为64.9%,AUC为80.3%。排除30%的高不确定度样本后，这些指标提高到F1得分为74.4%,AUC为85.6%.
结论：将具有高不确定性的样本重新引导至专家进行后续诊断可显著降低误诊率，这强调了不确定性估计对于确保计算机辅助早期口腔癌诊断的安全决策至关重要。
方法：我们开发了一种称为“概率HRNet”的贝叶斯深度学习模型，它利用HRNet上的集成MCdropout方法。此外,创建了两个具有不同分布的口腔病变数据集。我们进行了一项回顾性研究，以评估这些数据集的概率HRNet的预测性能和不确定性。
结果：概率HRNet在域内测试集上表现最佳，通过排除前30%的高不确定度样本，获得95.3%的F1评分和96.9%的AUC。对于Domain-shift测试集的评估，结果显示F1评分为64.9%,AUC为80.3%。排除30%的高不确定度样本后，这些指标提高到F1得分为74.4%,AUC为85.6%.
结论：将具有高不确定性的样本重新引导至专家进行后续诊断可显著降低误诊率，这强调了不确定性估计对于确保计算机辅助早期口腔癌诊断的安全决策至关重要。
