大脑小血管疾病病变细分方法:系统性审查
Jolene Phelps1,2,3, Manpreet Singh4,5,6,7, Cheryl R McCreary1,8,9
1Department of Clinical Neurosciences, University of Calgary, Calgary, Canada.
Cerebral circulation - cognition and behavior
|October 13, 2025
概括
自动机器学习工具可以对脑小血管疾病 (CSVD) 的脑病变进行细分,例如白质超强度 (WMH) 和脑微血 (CMB). 对于WMH存在高质量的工具,但对于其他CSVD类型的可用工具较少.
科学领域:
- 神经学 神经学
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 大脑小血管疾病 (CSVD) 涉及通过MRI检测到的大脑病变,影响大脑健康和痴呆风险.
- 这些病变的手动细分 (WMH,CMB,PVS,缺口,RSSI) 是耗时的研究.
- 正在开发自动机器学习方法,以实现高效准确的CSVD病变细分.
研究的目的:
- 系统地审查过去十年开发的新型自动化方法来细分CSVD病变.
- 评估这些方法在CSVD风险人群中的验证性.
- 确定公开可用的工具和代码,用于CSVD损伤细分.
主要方法:
- 在Web of Science和PubMed.com上进行系统的文献搜索.
- 对2764项获取的研究进行了选和全文审查.
- 根据细分的CSVD病变类型 (WMH,CMB,PVS,缺口,RSSI) 分类自动化方法的分类.
主要成果:
- 89项研究符合纳入标准,重点是CSVD病变的自动细分.
- 大多数方法都针对白质超强度 (59项研究),其次是脑微型血流 (23项研究).
- 对于周血管空间,缺口和最近的小皮下心脏病发作,可用的自动化工具较少.
- 代码或预训练模型可用于30项研究,主要用于WMH和CMB细分.
结论:
- 高质量的自动化工具可用于CSVD中的白质超强度细分.
- 需要更有效的自动化工具来对其他CSVD病变类型进行细分.
- 自动化细分工具的开发显示出对推进CSVD研究和痴呆症预防的前景.
相关概念视频
Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation
Clinical manifestationsPeripheral Arterial Disease (PAD) manifests through a range of symptoms, from the characteristic intermittent claudication to atypical presentations and severe complications in advanced stages. Intermittent claudication, a hallmark symptom of PAD, presents as exercise-induced muscle pain that typically resolves within minutes of rest. This pain is reproducible and stems from inadequate blood flow, leading to the accumulation of lactic acid produced during anaerobic...
Hemorrhagic Stroke l: Introduction
A hemorrhagic stroke is an acute neurological event that occurs when a weakened cerebral blood vessel ruptures, allowing blood to accumulate within or around the brain. The sudden release of blood forms a focal hematoma that increases intracranial pressure, displaces neural tissue, and can obstruct cerebrospinal fluid pathways. These effects may be compounded by intraventricular extension of the hemorrhage, cerebral edema, or compression of adjacent structures, all of which contribute to...


