Abstract
Mammographic screening is an effective method for detecting breast cancer, facilitating early diagnosis. However, the current need to manually inspect images places a heavy burden on healthcare systems, spurring a desire for automated diagnostic protocols. Techniques based on deep neural networks have been shown effective in some studies, but their tendency to overfit leaves considerable risk for poor generalisation and misdiagnosis, preventing their widespread adoption in clinical settings. Data augmentation schemes based on unpaired neural style transfer models have been proposed that improve generalisability by diversifying the representations of training image features in the absence of paired training data (images of the same tissue in either image style). But these models are similarly prone to various pathologies, and evaluating their performance is challenging without ground truths/large datasets (as is often the case in medical imaging). Here, we consider two frameworks/architectures: a GAN-based cycleGAN, and the more recently developed diffusion-based SynDiff. We evaluate their performance when trained on image patches parsed from three open access mammography datasets and one non-medical image dataset. We consider the use of uncertainty quantification to assess model trustworthiness, and propose a scheme to evaluate calibration quality in unpaired training scenarios. This ultimately helps facilitate the trustworthy use of image-to-image translation models in domains where ground truths are not typically available.
Abstract (translated)
乳腺摄影筛查是一种有效的检测乳腺癌的方法，有助于早期诊断。然而，当前需要人工检查图像给医疗系统带来了沉重负担，因此产生了对自动化诊断程序的需求。基于深度神经网络的技术在一些研究中显示出有效性，但这些技术倾向于过拟合，这使得它们存在较差的泛化能力和误诊风险，从而阻碍了其在临床环境中的广泛应用。 为了改进训练数据不足或缺乏配对样本的情况下模型的表现，已经提出了一些基于未配对神经风格转换模型的数据增强方案。这些方法通过改变训练图像特征的表示方式来提高模型的通用性，但同样容易受到各种病态的影响，并且由于缺乏地面真实值/大型数据集（这种情况在医学成像中经常发生），评估它们的表现具有挑战性。 在这里，我们考虑了两个框架/架构：基于GAN的cycleGAN和最近开发的基于扩散模型的SynDiff。我们将训练这两个模型使用从三个开放访问乳腺摄影数据集中以及一个非医疗图像数据集中解析出的图像补丁，并评估其性能。 为了衡量这些模型的信任度，我们探讨了不确定性量化方法的应用，同时提出了一种在未配对训练场景中评价校准质量的方法。这最终有助于促进在地面真实值通常不可用的情况下可信地使用图像到图像转换模型。
URL
https://arxiv.org/abs/2501.17570
