文献速递小儿神经外科与脑积水

人工智能自动分析特发性正常压力脑积水患者分流术前后计算机断层扫描脑影像

Artificial Intelligence for Automatic Analysis of Shunt Treatment in Presurgery and Postsurgery Computed Tomography Brain Scans of Patients With Idiopathic Normal Pressure Hydrocephalus.
PubMed 文献 · Neurosurgery · 2024-06-06

研究纳入15例特发性正常压力脑积水(iNPH)患者共47次纵向CT扫描,采用基于UNet的全自动模型量化分流术前后脑室体积变化,并分析其与步态、平衡、认知和膀胱控制等临床症状改善的相关性。结果显示术后中央脑室体积减少6-33立方厘米(均值20,标准差9),同时临床症状改善,人工智能指标及图形界面可辅助量化分析。

要点

  • 15例iNPH患者共47次纵向CT扫描,术后扫描采集于1至45个月。
  • 术后中央脑室体积减少范围为6至33立方厘米(均值20,标准差9)。
  • 仅改善一或两种症状的2例患者引流量小于4立方厘米脑脊液。

核心结论

  • 所提出的指标可量化iNPH患者分流术前后脑室体积变化,作为自动且有效的影像学标志物用于判断分流管功能。

研究设计与样本

  • 研究纳入15例iNPH患者,共47次分流术前后纵向CT扫描,术后扫描采集于1至45个月。
  • 采用基于UNet的模型开发全自动指标,使用最能代表脑室体积的扫描中心层面(80%)。

主要发现

  • 15例iNPH患者术后脑室体积(按所提指标)减少,同时iNPH症状临床改善。
  • 在步态、膀胱控制和认知改善的患者中,术后中央脑室体积减少范围为6至33立方厘米(均值20,标准差9)。
  • 仅改善一或两种症状的2例患者引流量小于4立方厘米脑脊液。

关键数值与推荐

  • 术后中央脑室体积减少6至33立方厘米(均值20,标准差9)见于步态、膀胱控制和认知改善的患者。
  • 仅改善一或两种症状的2例患者引流量小于4立方厘米脑脊液。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND AND OBJECTIVES: Ventriculo-peritoneal shunt procedures can improve idiopathic normal pressure hydrocephalus (iNPH) symptoms. However, there are no automated methods that quantify the presurgery and postsurgery changes in the ventricular volume for computed tomography scans. Hence, the main goal of this research was to quantify longitudinal changes in the ventricular volume and its correlation with clinical improvement in iNPH symptoms. Furthermore, our objective was to develop an end-to-end graphical interface where surgeons can directly drag-drop a brain scan for quantified analysis. METHODS: A total of 15 patients with 47 longitudinal computed tomography scans were taken before and after shunt surgery. Postoperative scans were collected between 1 and 45 months. We use a UNet-based model to develop a fully automated metric. Center slices of the scan that are most representative (80%) of the ventricular volume of the brain are used. Clinical symptoms of gait, balance, cognition, and bladder continence are studied with respect to the proposed metric. RESULTS: Fifteen patients with iNPH demonstrate a decrease in ventricular volume (as shown by our metric) postsurgery and a concurrent clinical improvement in their iNPH symptomatology. The decrease in postoperative central ventricular volume varied between 6 cc and 33 cc (mean: 20, SD: 9) among patients who experienced improvements in gait, bladder continence, and cognition. Two patients who showed improvement in only one or two of these symptoms had <4 cc of cerebrospinal fluid drained. Our artificial intelligence-based metric and the graphical user interface facilitate this quantified analysis. CONCLUSION: Proposed metric quantifies changes in ventricular volume before and after shunt surgery for patients with iNPH, serving as an automated and effective radiographic marker for a functioning shunt in a patient with iNPH.

来源:Neurosurgery,查看原文。版权归原作者所有。

引用

  1. Shailja S, Nguyen C, Thanigaivelan K, et al. Artificial Intelligence for Automatic Analysis of Shunt Treatment in Presurgery and Postsurgery Computed Tomography Brain Scans of Patients With Idiopathic Normal Pressure Hydrocephalus. Neurosurgery. 2024. PMID: 38842320. doi:10.1227/neu.0000000000003015

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。