Taylor Jonathan Christopher, Fenner John Wesley
Nuclear Medicine, Sheffield Teaching Hospitals NHS Foundation Trust, I-floor, Royal Hallamshire Hospital, Glossop road, Sheffield, S10 2JF, UK.
Insigneo, IICD, University of Sheffield, O-floor, Royal Hallamshire Hospital, Glossop Road, Sheffield, S10 2JF, UK.
EJNMMI Phys. 2017 Nov 29;4(1):29. doi: 10.1186/s40658-017-0196-1.
Semi-quantification methods are well established in the clinic for assisted reporting of (I123) Ioflupane images. Arguably, these are limited diagnostic tools. Recent research has demonstrated the potential for improved classification performance offered by machine learning algorithms. A direct comparison between methods is required to establish whether a move towards widespread clinical adoption of machine learning algorithms is justified. This study compared three machine learning algorithms with that of a range of semi-quantification methods, using the Parkinson's Progression Markers Initiative (PPMI) research database and a locally derived clinical database for validation. Machine learning algorithms were based on support vector machine classifiers with three different sets of features: Voxel intensities Principal components of image voxel intensities Striatal binding radios from the putamen and caudate. Semi-quantification methods were based on striatal binding ratios (SBRs) from both putamina, with and without consideration of the caudates. Normal limits for the SBRs were defined through four different methods: Minimum of age-matched controls Mean minus 1/1.5/2 standard deviations from age-matched controls Linear regression of normal patient data against age (minus 1/1.5/2 standard errors) Selection of the optimum operating point on the receiver operator characteristic curve from normal and abnormal training data Each machine learning and semi-quantification technique was evaluated with stratified, nested 10-fold cross-validation, repeated 10 times.
The mean accuracy of the semi-quantitative methods for classification of local data into Parkinsonian and non-Parkinsonian groups varied from 0.78 to 0.87, contrasting with 0.89 to 0.95 for classifying PPMI data into healthy controls and Parkinson's disease groups. The machine learning algorithms gave mean accuracies between 0.88 to 0.92 and 0.95 to 0.97 for local and PPMI data respectively.
Classification performance was lower for the local database than the research database for both semi-quantitative and machine learning algorithms. However, for both databases, the machine learning methods generated equal or higher mean accuracies (with lower variance) than any of the semi-quantification approaches. The gain in performance from using machine learning algorithms as compared to semi-quantification was relatively small and may be insufficient, when considered in isolation, to offer significant advantages in the clinical context.
在临床中，半定量方法已广泛用于辅助报告（I123）碘氟烷图像。可以说，这些是有限的诊断工具。最近的研究表明，机器学习算法具有提高分类性能的潜力。需要对这些方法进行直接比较，以确定机器学习算法在临床上广泛应用是否合理。本研究使用帕金森病进展标志物倡议（PPMI）研究数据库和本地获取的临床数据库进行验证，将三种机器学习算法与一系列半定量方法进行了比较。机器学习算法基于支持向量机分类器，具有三组不同的特征：体素强度、图像体素强度的主成分、壳核和尾状核的纹状体结合放射性。半定量方法基于双侧壳核的纹状体结合率（SBR），同时考虑或不考虑尾状核。SBR的正常范围通过四种不同方法定义：年龄匹配对照的最小值、年龄匹配对照的均值减去1/1.5/2个标准差；正常患者数据与年龄的线性回归（减去1/1.5/2个标准误）；从正常和异常训练数据的接收者操作特征曲线上选择最佳操作点。每种机器学习和半定量技术均采用分层嵌套10折交叉验证进行评估，重复10次。
将本地数据分类为帕金森病组和非帕金森病组的半定量方法的平均准确率在0.78至0.87之间，而将PPMI数据分类为健康对照和帕金森病组的准确率为0.89至0.95。机器学习算法对本地数据和PPMI数据的平均准确率分别在0.88至0.92和0.95至0.97之间。
对于半定量和机器学习算法，本地数据库的分类性能低于研究数据库。然而，对于两个数据库而言，机器学习方法产生的平均准确率等于或高于任何半定量方法（方差更低）。与半定量方法相比，使用机器学习算法在性能上的提升相对较小，单独考虑时，可能不足以在临床环境中提供显著优势。
