标题： 基于蒙特卡洛丢弃和深度集成的超声乳腺肿瘤分割的可信性研究 显示英文标题

标题： Towards Trustworthy Breast Tumor Segmentation in Ultrasound using Monte Carlo Dropout and Deep Ensembles for Epistemic Uncertainty Estimation

摘要： 自动分割BUS图像对于精确的病灶分界和肿瘤特征描述非常重要，但受到固有伪影和数据集不一致性的挑战。 在本工作中，我们评估了改进的残差编码器U-Net在乳腺超声分割中的使用，并重点关注不确定性量化。 我们识别并纠正了BUSI数据集中的数据重复问题，并使用去重子集来获得更可靠的泛化性能估计。 使用蒙特卡洛丢弃、深度集成及其组合来量化认知不确定性。 模型在分布内和分布外数据集上进行基准测试，以展示它们对未见过的跨领域数据的泛化能力。 我们的方法在分布内验证的Breast-Lesion-USG数据集上实现了最先进的分割准确性，并提供了校准的不确定性估计，能够有效指示模型置信度低的区域。 在分布外评估中观察到的性能下降和不确定性增加突显了医学影像中领域偏移的持续挑战，以及集成不确定性建模在可信临床部署中的重要性。 \footnote{代码可在以下位置获取：https://github.com/toufiqmusah/nn-uncertainty.git} 显示英文摘要

摘要： Automated segmentation of BUS images is important for precise lesion delineation and tumor characterization, but is challenged by inherent artifacts and dataset inconsistencies. In this work, we evaluate the use of a modified Residual Encoder U-Net for breast ultrasound segmentation, with a focus on uncertainty quantification. We identify and correct for data duplication in the BUSI dataset, and use a deduplicated subset for more reliable estimates of generalization performance. Epistemic uncertainty is quantified using Monte Carlo dropout, deep ensembles, and their combination. Models are benchmarked on both in-distribution and out-of-distribution datasets to demonstrate how they generalize to unseen cross-domain data. Our approach achieves state-of-the-art segmentation accuracy on the Breast-Lesion-USG dataset with in-distribution validation, and provides calibrated uncertainty estimates that effectively signal regions of low model confidence. Performance declines and increased uncertainty observed in out-of-distribution evaluation highlight the persistent challenge of domain shift in medical imaging, and the importance of integrated uncertainty modeling for trustworthy clinical deployment. \footnote{Code available at: https://github.com/toufiqmusah/nn-uncertainty.git}