论文标题
在CT扫描中有效的无锚通用病变检测
An Efficient Anchor-free Universal Lesion Detection in CT-scans
论文作者
论文摘要
现有的通用病变检测（ULD）方法利用基于计算密集型锚固架构，依赖于预定义的锚固盒，从而导致检测性能不令人满意，尤其是在中小型病变中。此外，这些默认的固定锚固尺寸和比率不能很好地推广到不同的数据集。因此，我们提出了一个健壮的一阶段无锚固病变检测网络，该网络可以通过利用一个事实，即可以根据其中心而不是与对象重叠的相关性来分类盒子预测的事实。此外，我们证明，可以通过使用多个HU Windows生成的多强度图像的形式明确地提供特定于域的信息，从而改善ULD，然后使用多个基于自我注意力的特征融合和骨干初始化，使用通过CT-Scans的自我实验来学习的权重。我们获得了与最先进方法的可比结果，在深层数据集中达到了86.05％的总体灵敏度，该数据集由大约32K CT扫描构成，并在各个体型器官中注释了病变。
Existing universal lesion detection (ULD) methods utilize compute-intensive anchor-based architectures which rely on predefined anchor boxes, resulting in unsatisfactory detection performance, especially in small and mid-sized lesions. Further, these default fixed anchor-sizes and ratios do not generalize well to different datasets. Therefore, we propose a robust one-stage anchor-free lesion detection network that can perform well across varying lesions sizes by exploiting the fact that the box predictions can be sorted for relevance based on their center rather than their overlap with the object. Furthermore, we demonstrate that the ULD can be improved by explicitly providing it the domain-specific information in the form of multi-intensity images generated using multiple HU windows, followed by self-attention based feature-fusion and backbone initialization using weights learned via self-supervision over CT-scans. We obtain comparable results to the state-of-the-art methods, achieving an overall sensitivity of 86.05% on the DeepLesion dataset, which comprises of approximately 32K CT-scans with lesions annotated across various body organs.
