机器学习支持的纹理分析对腰椎管狭窄定性分级与定量分级的比较——来自 LSOS 研究队列的经验
基于 LSOS 注册研究 82 例患者 343 幅轴位 T2 加权图像,比较定性评级与定量纹理分析(TA)在腰椎管狭窄检出和分级中的可重复性与准确性。定性评级在两种分级系统下仅呈中等可重复性,但与严重狭窄的横截面积阈值(CSA<130mm²)高度相关;定量 TA 结合机器学习决策树分类器在狭窄分级上表现优于基于 CSA 参考阈值的定性评估。
要点
- 定性 LSS 分级无论采用四点法还是八点 Schizas 法,可重复性均仅为中等。
- 定性评级与严重狭窄的 CSA<130mm² 阈值高度相关。
- 定量 TA 结合机器学习对严重 LSS 检出的准确性高于定性评估。
核心结论
- 不依赖分级系统的定性 LSS 分级仅呈中等可重复性。
- 纹理分析结合机器学习提供高度可重复的定量参数,提高严重 LSS 检出准确性,且受分级评分和 CSA 边界定义影响较小。
研究设计与样本
- 研究类型为基于全国性多中心多学科腰椎狭窄结局研究(LSOS)注册队列的影像学研究,共纳入 82 例因临床提示脊髓性跛行而行腰椎 MR 扫描、且存在单节段中央型或侧方型严重 LSS 的患者。
- 共纳入 343 幅腰椎轴位 T2 加权图像,每例患者涵盖 1 至 5 个节段(L1 至 S1)。
- 由一名专家放射科医师作为参考标准,按标准四点法(正常至严重)及八点 Schizas 分级量表评定 LSS 等级。
- DICOM 数据重缩放至规定像素尺寸后,两名独立阅片者进行与专家阅片者类似的定性评级,并对椎管行纹理分析,每幅图像手动放置两个感兴趣区(ROI):仅硬膜囊、以及包括硬膜外脂肪和双侧侧隐窝的椎管内轮廓。
- 定性参数与定量参数阅片者间一致性分别采用 Cohen's Kappa(κ)和组内相关系数(ICC)评估;纹理分析特征通过 ICC 阈值 >0.75 进行降维,剩余特征采用机器学习算法(Weka 3 工具)以 10 折交叉验证分析与 LSS 等级的相关性。
诊断标准与关键数值
- 参考标准为专家放射科医师按标准四点法(正常至严重)及八点 Schizas 分级量表评定的 LSS 等级。
- 严重腰椎狭窄的横截面积(CSA)截断值为 <130mm²。
- 定性评级与 CSA<130mm² 的严重狭窄阈值高度相关,但两种 LSS 分类系统的可重复性均仅为中等。
- 定量纹理分析两个 ROI 的机器学习决策树分类器在 LSS 分级上的表现高于使用参考 CSA 截断值的定性评估。
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)。
英文原文(摘要)· 点击展开
PURPOSE: To investigate and compare the reproducibility and accuracy of qualitative ratings and quantitative texture analysis (TA) in detection and grading of lumbar spinal stenosis (LSS) in magnetic resonance imaging (MR) scans of the lumbar spine.
MATERIALS AND METHODS: From a nationwide multicenter and multidisciplinary lumbar stenosis outcome study (LSOS) register 82 patients, undergoing MR scans of the lumbar spine due to clinical indication of spinal claudication, with a single level central or lateral severe LSS were included. In total 343 transaxial T2-weighted images of the lumbar spine were included from one to five levels (L1 to S1) per patient. One expert radiologist serving as reference standard rated LSS grade according to a standard four-point (normal to severe) as well as to an eight-point Schizas grading scale. DICOM data were then rescaled to a defined pixel size. Two independent readers performed qualitative ratings analogous to expert reader in addition to TA of spinal canals by manually placing two regions of interest (ROI) per image reflecting qualitative scales: (1) dural sac only (2) inner contour of the spinal canal including epidural fat and bilateral recesses. Interreader agreements of qualitative and quantitative parameters were assessed by Cohen's Kappa (κ) and intraclass correlation (ICC), respectively. TA feature reduction was performed by ICC threshold > 0.75. Remaining features were analyzed with machine learning algorithms (Weka 3 tool) for correlation with LSS grades using 10-fold cross validation.
RESULTS: Qualitative ratings showed only moderate reproducibility for both LSS classification systems but high correlation with cut-off cross-sectional area (CSA) <130mm² for severe spinal stenosis. In quantitative TA of both ROIs, machine learning analysis with a decision tree classifier revealed higher performances for LSS grading compared to qualitative assessments using the reference CSA cut-off, respectively.
CONCLUSION: Qualitative LSS grading independent of classification system shows moderate reproducibility. TA with machine learning offers highly reproducible quantitative parameters that increase accuracy for severe LSS detection with minor impact of grading score and CSA border definition.
引用
- Huber FA, Stutz S, Vittoria de Martini I, et al. Qualitative versus quantitative lumbar spinal stenosis grading by machine learning supported texture analysis-Experience from the LSOS study cohort. Eur J Radiol. 2019. PMID: 31005175. doi:10.1016/j.ejrad.2019.02.023
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。