DeDA：深度有向累加器
DeDA: Deep Directed Accumulator
AI总结：
提出深度有向累加器（DeDA）操作，将领域特定先验注入神经网络以识别多发性硬化症 rim+ 病灶，在数据受限和高类别不平衡下显著提升了识别性能。
摘要：
慢性活动性多发性硬化症病灶（也称为 rim+ 病灶）可以通过定量磁化率图上病灶边缘的高信号环来表征。这些 rim+ 病灶表现出几何上简单的结构，其中病灶边缘的梯度呈径向分布，并且与 rim-（非 rim+）病灶相比具有更大的梯度幅度。然而，最近的研究表明，由于数据量有限和类别高度不平衡，此类病灶的识别性能仍然不令人满意。在本文中，我们提出了一种简单而有效的图像处理操作，即深度有向累加器（DeDA），它为将领域特定的归纳偏置（先验）注入神经网络以进行 rim+ 病灶识别提供了新的视角。给定特征图和一组采样网格，DeDA 创建一个累加器空间并将其量化为有限区间，并相应地累积特征值。此 DeDA 操作是广义的离散 Radon 变换，也可以被视为前向-后向神经网络框架内网格采样的对称操作，该过程与顺序无关，并且可以使用原生 CUDA 编程高效实现。在一个包含 177 个 rim+ 和 3986 个 rim- 病灶的数据集上的实验结果表明，与其他最先进的方法相比，在受试者工作特征曲线下部分（假阳性率<0.1）面积（pROC AUC）上可分别实现 10.1% 的提升，在精确率-召回率曲线下面积（PR AUC）上可实现 10.2% 的提升。源代码可在 https://github.com/tinymilky/DeDA 上获取。
英文摘要：
Chronic active multiple sclerosis lesions, also termed as rim+ lesions, can be characterized by a hyperintense rim at the edge of the lesion on quantitative susceptibility maps. These rim+ lesions exhibit a geometrically simple structure, where gradients at the lesion edge are radially oriented and a greater magnitude of gradients is observed in contrast to rim- (non rim+) lesions. However, recent studies have shown that the identification performance of such lesions remains unsatisfied due to the limited amount of data and high class imbalance. In this paper, we propose a simple yet effective image processing operation, deep directed accumulator (DeDA), that provides a new perspective for injecting domain-specific inductive biases (priors) into neural networks for rim+ lesion identification. Given a feature map and a set of sampling grids, DeDA creates and quantizes an accumulator space into finite intervals, and accumulates feature values accordingly. This DeDA operation is a generalized discrete Radon transform and can also be regarded as a symmetric operation to the grid sampling within the forward-backward neural network framework, the process of which is order-agnostic, and can be efficiently implemented with the native CUDA programming. Experimental results on a dataset with 177 rim+ and 3986 rim- lesions show that 10.1% of improvement in a partial (false positive rate<0.1) area under the receiver operating characteristic curve (pROC AUC) and 10.2% of improvement in an area under the precision recall curve (PR AUC) can be achieved respectively comparing to other state-of-the-art methods. The source code is available online at https://github.com/tinymilky/DeDA
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
