Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes
Bayesian machine learning classifiers for combining structural and functional measurements to classify healthy and glaucomatous eyes
复制标题
DOI：
10.1167/iovs.07-1083
复制
发表时间：
2008-03-01
影响因子：
4.4
通讯作者：
Goldbaum, Michael H.
中科院分区：
文献类型：
--
作者：
Bowd, Christopher;Hao, Jiucang;Goldbaum, Michael H.
目的.为了确定与单独使用每种测量方法相比，将结构（光学相干断层扫描，OCT）和功能（标准自动视野检查，SAP）测量组合作为机器学习分类器（MLC;相关向量机，RVM;和高斯子空间混合，SSMoG）的输入是否提高了检测青光眼的诊断准确性。69例健康对照者的69只眼（平均年龄62.0岁，标准差9.7岁;视野平均偏差[MD]，-0.70，标准差1.41 dB）和156例青光眼患者的156只眼（平均年龄，66.4岁，SD 10.2岁;视野MD，-3.12，SD 3.43 dB）用OCT（Stratus OCT，Carl Zeiss Meditec，Inc.，都柏林，CA），并用SAP（Humphrey Field Analyzer II with Swedish Interactive Holding Algorithm，SITA; Carl Zeiss Meditec，Inc.）在三个月之内。RVM和SSMoG MLC在OCT确定的RNFL厚度测量值上进行训练和测试，这些测量值来自在仪器定义的测量椭圆下的视乳头周围区域中获得的32个扇区（每个扇区类似于11.25度）和来自24-2网格的52个点的SAP模式偏差值，独立地和组合地。十倍交叉验证用于在完整的225只眼睛数据集的独特子集上训练和测试分类器，并生成用于测试集中眼睛分类的受试者工作特征曲线下面积（AUROC）。比较了单独在OCT和SAP上训练的分类器的AUROC结果以及在OCT和SAP组合上训练的分类器的AUROC结果。此外，将这些结果与当前可用的OCT测量值（平均视网膜神经纤维层[RNFL]厚度、下RNFL厚度和上级RNFL厚度）和SAP指数（MD和模式标准差[PSD]）进行比较。单独使用OCT参数、单独使用SAP参数以及OCT和SAP参数组合训练的RVM的AUROC分别为0.809、0.815和0.845。单独使用OCT参数、单独使用SAP参数以及OCT和SAP参数组合训练的SSMoG的AUROC分别为0.817、0.841和0.869。使用RVM和SSMoG的组合技术显著改善了OCT的MLC分析，但单独测量SAP没有改善。使用RVM和SSMoG的分类性能在统计学上相似。在OCT和SAP数据上训练的RVM和SSMoG贝叶斯MLC可以成功区分健康和早期青光眼。与单独使用每种技术获得的数据的MLC分析相比，使用RVM和SSMoG组合OCT和SAP测量略微提高了诊断性能。
PURPOSE. To determine whether combining structural (optical coherence tomography, OCT) and functional (standard automated perimetry, SAP) measurements as input for machine learning classifiers (MLCs; relevance vector machine, RVM; and subspace mixture of Gaussians, SSMoG) improves diagnostic accuracy for detecting glaucomatous eyes compared with using each measurement method alone.METHODS. Sixty-nine eyes of 69 healthy control subjects (average age, 62.0, SD 9.7 years; visual field mean deviation [MD], -0.70, SD 1.41 dB) and 156 eyes of 156 patients with glaucoma (average age, 66.4, SD 10.2 years; visual field MD, -3.12, SD 3.43 dB) were imaged with OCT (Stratus OCT, Carl Zeiss Meditec, Inc., Dublin, CA) and tested with SAP (Humphrey Field Analyzer II with Swedish Interactive Thresholding Algorithm, SITA; Carl Zeiss Meditec, Inc.) within 3 months of each other. RVM and SSMoG MLCs were trained and tested on OCT-determined RNFL thickness measurements from 32 sectors (similar to 11.25 degrees each) obtained in the circumpapillary area under the instrument-defined measurement ellipse and SAP pattern deviation values from 52 points from the 24-2 grid, independently and in combination. Tenfold cross-validation was used to train and test classifiers on unique subsets of the full 225-eye data set, and areas under the receiver operating characteristic curve (AUROC) for the classification of eyes in the test set were generated. AUROC results from classifiers trained on OCT and SAP alone and those trained on OCT and SAP in combination were compared. In addition, these results were compared to currently available OCT measurements (mean retinal nerve fiber layer [RNFL] thickness, inferior RNFL thickness, and superior RNFL thickness) and SAP indices (MD and pattern standard deviation [PSD]).RESULTS. The AUROCs for RVM trained on OCT parameters alone, SAP parameters alone and OCT and SAP parameters combined were 0.809, 0.815, and 0.845, respectively. The AUROCs for SSMoG trained on OCT parameters alone, SAP parameters alone, and OCT and SAP parameters combined were 0.817, 0.841, and 0.869, respectively. Combining techniques using both RVM and SSMoG significantly improved on MLC analysis of OCT, but not SAP, measurements alone. Classification performance using RVM and SSMoG was statistically similar.CONCLUSIONS. RVM and SSMoG Bayesian MLCs trained on OCT and SAP data can successfully discriminate between healthy and early glaucomatous eyes. Combining OCT and SAP measurements using RVM and SSMoG increased diagnostic performance marginally compared with MLC analysis of data obtained using each technology alone.