Kim Jun-Ho, Noh Young, Lee Haejoon, Lee Seul, Kim Woo-Ram, Kang Koung Mi, Kim Eung Yeop, Al-Masni Mohammed A, Kim Dong-Hyun
Department of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul, Republic of Korea.
Neuroscience Research Institute, Gachon University, Incheon, Republic of Korea; Department of Neurology, Gachon University College of Medicine, Gil Medical Center, Incheon, Republic of Korea.
Med Image Anal. 2025 Apr;101:103415. doi: 10.1016/j.media.2024.103415. Epub 2024 Nov 30.
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 (FP) of 0.86 vs. 14.73. Furthermore, the anatomical localization task enhances the detection performance by reducing the FP to 0.56 while maintaining the sensitivity of 94.66 %.
脑微出血（CMBs）是脑组织中小的血液产物的慢性沉积，根据其解剖位置与各种脑血管疾病有明确关联，包括认知衰退、脑出血和脑梗死。然而，由于CMBs稀疏且微小的结构特性，手动检测CMBs既耗时又容易出错。CMBs的检测通常受到许多类似CMBs的因素的影响，这些因素会导致高假阳性率（FPR），例如钙化和软脑膜血管。本文提出了一种新颖的3D深度学习框架，该框架不仅可以检测CMBs，还可以识别它们在大脑中的解剖位置（即脑叶、深部和幕下区域）。对于CMBs检测任务，我们通过利用3D U-Net作为骨干网络并结合区域提议网络（RPN）提出了一个单端到端模型。为了在同一个单一模型中显著减少假阳性，我们开发了一种新方案，其中包括利用上下文信息检测小候选物的特征融合模块（FFM）和挖掘CMBs模拟物并使用卷积原型学习（CPL）生成称为浓度损失的额外损失项的硬样本原型学习（HSPL）。对于解剖定位任务，我们利用3D U-Net分割网络对大脑的解剖结构进行分割。该任务不仅可以识别CMBs所属的区域，还可以通过利用解剖信息从检测任务中消除一些假阳性。我们使用磁敏感加权成像（SWI）和相位图像作为3D输入，以有效地捕获3D信息。结果表明，所提出的利用FFM和HSPL的RPN优于基线RPN，灵敏度达到94.66%，而基线RPN为93.33%，每个受试者的平均假阳性数（FP）为0.86，而基线为14.73。此外，解剖定位任务通过将FP减少到0.56同时保持94.66%的灵敏度来提高检测性能。
IEEE Trans Med Imaging. 2016-2-11
Annu Int Conf IEEE Eng Med Biol Soc. 2020-7
Neuroimage Clin. 2016-7-2
Acta Neurochir (Wien). 2024-9-26
Comput Biol Med. 2022-12
Neuroimage Clin. 2025-8-27
Zotero 插件