IEEE Trans Med Imaging. 2024 Oct;43(10):3596-3607. doi: 10.1109/TMI.2024.3375357. Epub 2024 Oct 28.
Deep neural networks (DNNs) have immense potential for precise clinical decision-making in the field of biomedical imaging. However, accessing high-quality data is crucial for ensuring the high-performance of DNNs. Obtaining medical imaging data is often challenging in terms of both quantity and quality. To address these issues, we propose a score-based counterfactual generation (SCG) framework to create counterfactual images from latent space, to compensate for scarcity and imbalance of data. In addition, some uncertainties in external physical factors may introduce unnatural features and further affect the estimation of the true data distribution. Therefore, we integrated a learnable FuzzyBlock into the classifier of the proposed framework to manage these uncertainties. The proposed SCG framework can be applied to both classification and lesion localization tasks. The experimental results revealed a remarkable performance boost in classification tasks, achieving an average performance enhancement of 3-5% compared to previous state-of-the-art (SOTA) methods in interpretable lesion localization.
深度神经网络（DNN）在生物医学成像领域的精确临床决策中具有巨大的潜力。然而，获取高质量的数据对于确保 DNN 的高性能至关重要。获取医学成像数据在数量和质量方面都具有挑战性。为了解决这些问题，我们提出了一种基于得分的反事实生成（SCG）框架，从潜在空间生成反事实图像，以弥补数据的稀缺性和不平衡。此外，外部物理因素的一些不确定性可能会引入不自然的特征，并进一步影响真实数据分布的估计。因此，我们将一个可学习的 FuzzyBlock 集成到所提出框架的分类器中，以处理这些不确定性。所提出的 SCG 框架可应用于分类和病变定位任务。实验结果表明，在分类任务中显著提高了性能，与可解释病变定位方面的先前最先进（SOTA）方法相比，平均性能提高了 3-5%。
