Analysis of intensity normalization for optimal segmentation performance of a fully convolutional neural network
Analysis of intensity normalization for optimal segmentation performance of a fully convolutional neural network
复制标题
DOI：
10.1016/j.zemedi.2018.11.004
复制
发表时间：
2019-01-01
影响因子：
2
通讯作者：
Guellmar, Daniel
中科院分区：
文献类型：
--
作者：
Jacobsen, Nina;Deistung, Andreas;Guellmar, Daniel
前言：近年来，卷积神经网络在医学图像分割中已经开始超越经典的基于统计和图谱的机器学习技术，在性能和速度上都被证明是优越的。然而，社区面临的一个主要挑战是训练和评估数据集内的可变性之间的不匹配，因此依赖于适当的数据预处理。亮度归一化是一种广泛应用的减小数据方差的技术，对于这种技术，有几种方法可用，从均匀变换到直方图均衡。分析了强度归一化对卷积神经网络(CNN)小脑分割性能的影响。方法：研究包括三个总体样本，共218个数据集，均包括3T采集的T1w MRI数据集和描绘小脑的基本事实分割。使用一个总体样本中的150个数据集训练了一个12层深的3D全卷积神经网络。分别采用四种不同的强度归一化方法对数据进行了预处理，并针对不同的归一化技术对CNN进行了四次训练。通过对所有四个CNN的Sorensen-Dice相似性系数(DSC)的评估，对分割性能进行了定量分析，以考察CNN的强度敏感性。结果：4种归一化方法均获得了良好的分割结果(平均DSC得分=0.96)，但在使用未知数据进行测试时，分割性能因应用的强度归一化方法的不同而不同，在这种情况下，直方图均衡方法的分割效果优于单位分布方法。对灰度操作的详细、系统的分析表明，输入强度的分布明显影响分割性能，并且对于每个输入数据集，存在导致最佳分割结果的线性强度修改(平移和缩放)。通过对每个归一化配置下的单个输入评价样本进行优化分析，进一步证明了这一点。讨论：研究结果表明，适当地准备评价数据比准确地选择归一化方法来准备训练数据更为关键。这项研究中测试的直方图均衡化方法被发现执行这一任务最好，但如优化分析所示，仍有进一步改进的空间。
Introduction: Convolutional neural networks have begun to surpass classical statistical- and atlas based machine learning techniques in medical image segmentation in recent years, proving to be superior in performance and speed. However, a major challenge that the community faces are mismatch between variability within training and evaluation datasets and therefore a dependency on proper data pre-processing. Intensity normalization is a widely applied technique for reducing the variance of the data for which there are several methods available ranging from uniformity transformation to histogram equalization. The current study analyses the influence of intensity normalization on cerebellum segmentation performance of a convolutional neural network (CNN).Method: The study included three population samples with a total number of 218 datasets, all including a T1w MRI data set acquired at 3T and a ground truth segmentation delineating the cerebellum. A 12 layer deep 3D fully convolutional neural network was trained using 150 datasets from one of the population samples. Four different intensity normalization methods were separately applied to pre-process the data, and the CNN was correspondingly trained four times with respect to the different normalization techniques. A quantitative analysis of the segmentation performance, assessed via the SOrensen-Dice similarity coefficient (DSC) of all four CNNs, was performed to investigate the intensity sensitivity of the CNNs. Additionally, the optimal network performance was determined by identifying the best parameter set for intensity normalization.Results: All four normalization methods led to excellent (mean DSC score = 0.96) segmentation results when evaluated using known data; however, the segmentation performance differed depending on the applied intensity normalization method when testing with formerly unseen data, in which case the histogram equalization methods outperformed the unit distribution methods. A detailed, systematic analysis of intensity manipulations revealed, that the distribution of input intensities clearly affected the segmentation performance and that for each input dataset a linear intensity modification (shifting and scaling) existed leading to optimal segmentation results. This was further proven by an optimization analysis to find the optimal adjustment for an individual input evaluation sample within each normalization configuration.Discussion: The findings suggest that proper preparation of the evaluation data is more crucial than the exact choice of normalization method to prepare the training data. The histogram equalization methods tested in this study were found to perform this task best, although leaving room for further improvements, as shown by the optimization analysis.