In recent years, deep learning models have revolutionized medical image interpretation, offering substantial improvements in diagnostic accuracy. However, these models often struggle with challenging images where critical features are partially or fully occluded, which is a common scenario in clinical practice. In this paper, we propose a novel curriculum learning-based approach to train deep learning models to handle occluded medical images effectively. Our method progressively introduces occlusion, starting from clear, unobstructed images and gradually moving to images with increasing occlusion levels. This ordered learning process, akin to human learning, allows the model to first grasp simple, discernable patterns and subsequently build upon this knowledge to understand more complicated, occluded scenarios. Furthermore, we present three novel occlusion synthesis methods, namely Wasserstein Curriculum Learning (WCL), Information Adaptive Learning (IAL), and Geodesic Curriculum Learning (GCL). Our extensive experiments on diverse medical image datasets demonstrate substantial improvements in model robustness and diagnostic accuracy over conventional training methodologies.

翻译：近年来，深度学习模型革新了医学图像解读，显著提升了诊断准确性。然而，这些模型在处理临床实践中常见的、关键特征被部分或完全遮挡的困难图像时，仍面临挑战。本文提出一种新颖的基于课程学习的方法，旨在有效训练深度学习模型处理被遮挡的医学图像。该方法渐进式引入遮挡，从清晰无遮挡图像开始，逐步过渡到遮挡程度递增的图像。这种类似于人类学习的有序学习过程，使模型能够先掌握简单可辨模式，并在此基础上逐步理解更复杂的遮挡场景。此外，我们提出了三种新型遮挡合成方法：Wasserstein课程学习、信息自适应学习和测地线课程学习。通过在多样化医学图像数据集上的大量实验，我们证实该方法相比传统训练方式，在模型鲁棒性和诊断准确性方面均取得了显著提升。