Cerebral Microbleeds (CMBs) are chronic deposits of small blood products in the brain tissues, which have explicit relation to various cerebrovascular diseases depending on their anatomical location, including cognitive decline, intracerebral hemorrhage, and cerebral infarction. However, manual detection of CMBs is a time consuming and error-prone process because of their sparse and tiny structural properties. The detection of CMBs is commonly affected by the presence of many CMB mimics that cause a high false-positive rate (FPR), such as calcifications and pial vessels. This paper proposes a novel 3D deep learning framework that not only detects CMBs but also identifies their anatomical location in the brain (i.e., lobar, deep, and infratentorial regions). For the CMBs detection task, we propose a single end-to-end model by leveraging the 3D U-Net as a backbone with Region Proposal Network (RPN). To significantly reduce the false positives within the same single model, we develop a new scheme, containing Feature Fusion Module (FFM) that detects small candidates utilizing contextual information and Hard Sample Prototype Learning (HSPL) that mines CMB mimics and generates additional loss term called concentration loss using Convolutional Prototype Learning (CPL). For the anatomical localization task, we exploit the 3D U-Net segmentation network to segment anatomical structures of the brain. This task not only identifies to which region the CMBs belong but also eliminates some false positives from the detection task by leveraging anatomical information. We utilize Susceptibility-Weighted Imaging (SWI) and phase images as 3D input to efficiently capture 3D information. The results show that the proposed RPN that utilizes the FFM and HSPL outperforms the baseline RPN and achieves a sensitivity of 94.66 % vs. 93.33 % and an average number of false positives per subject (FPavg) of 0.86 vs. 14.73. Furthermore, the anatomical localization task enhances the detection performance by reducing the FPavg to 0.56 while maintaining the sensitivity of 94.66 %.

中文翻译：

---

使用深度学习通过解剖尺度定位实现微出血的自动检测


脑微出血 （CMB） 是脑组织中小血制品的慢性沉积，根据其解剖位置，它与各种脑血管疾病有明确的关系，包括认知能力下降、脑出血和脑梗塞。然而，由于 CMB 的结构特性稀疏且微小，手动检测 CMB 是一个耗时且容易出错的过程。CMB 的检测通常受到许多 CMB 模拟物的影响，这些模拟物会导致高假阳性率 （FPR），例如钙化和软脑膜血管。本文提出了一种新的 3D 深度学习框架，不仅可以检测 CMB，还可以识别它们在大脑中的解剖位置（即肺叶、深部和幕下区域）。对于 CMB 检测任务，我们利用 3D U-Net 作为区域建议网络 （RPN） 的主干，提出了一个单一的端到端模型。为了显着减少同一单个模型中的误报，我们开发了一种新方案，其中包含特征融合模块 （FFM），它利用上下文信息检测小候选者，以及硬样本原型学习 （HSPL），它挖掘 CMB 模拟并使用卷积原型学习 （CPL） 生成额外的损失项，称为集中损失。对于解剖定位任务，我们利用 3D U-Net 分割网络来分割大脑的解剖结构。该任务不仅可以识别 CMB 属于哪个区域，还可以通过利用解剖信息消除检测任务中的一些假阳性。我们利用磁化率加权成像 （SWI） 和相位图像作为 3D 输入来高效捕获 3D 信息。 结果表明，利用 FFM 和 HSPL 的拟议 RPN 优于基线 RPN，灵敏度为 94.66 % 对 93.33 %，每个受试者的平均假阳性数 （FPavg） 为 0.86 对 14.73。此外，解剖定位任务通过将 FPavg 降低到 0.56 而同时保持 94.66 % 的灵敏度来提高检测性能。