Performance of Principal Component Analysis and Independent Component Analysis with Respect to Signal Extraction from Noisy Positron Emission Tomography Data - a Study on Computer Simulated Images

Abstract

Multivariate image analysis tools are used for analyzing dynamic or multidimensional Positron Emission Tomography, PET data with the aim of noise reduction, dimension reduction and signal separation. Principal Component Analysis is one of the most commonly used multivariate image analysis tools, applied on dynamic PET data. Independent Component Analysis is another multivariate image analysis tool used to extract and separate signals. Because of the presence of high and variable noise levels and correlation in the different PET images which may confound the multivariate analysis, it is essential to explore and investigate different types of pre-normalization (transformation) methods that need to be applied, prior to application of these tools. In this study, we explored the performance of Principal Component Analysis (PCA) and Independent Component Analysis (ICA) to extract signals and reduce noise, thereby increasing the Signal to Noise Ratio (SNR) in a dynamic sequence of PET images, where the features of the noise are different compared with some other medical imaging techniques. Applications on computer simulated PET images were explored and compared. Application of PCA generated relatively similar results, with some minor differences, on the images with different noise characteristics. However, clear differences were seen with respect to the type of pre-normalization. ICA on images normalized using two types of normalization methods also seemed to perform relatively well but did not reach the improvement in SNR as PCA. Furthermore ICA seems to have a tendency under some conditions to shift over information from IC1 to other independent components and to be more sensitive to the level of noise. PCA is a more stable technique than ICA and creates better results both qualitatively and quantitatively in the simulated PET images. PCA can extract the signals from the noise rather well and is not sensitive to type of noise, magnitude and correlation, when the input data are correctly handled by a proper pre-normalization. It is important to note that PCA as inherently a method to separate signal information into different components could still generate PC1 images with improved SNR as compared to mean images.

Multivariate hyperspectral data analytics across length scales to probe compositional, phase, and strain heterogeneities in electrode materials

“…Figures S11 and S12 show that this supervised approach, guided by standards to PCA and clustering, respectively, can successfully partition data based on spectral similarities to obtain a set of spectra ), even in the presence of Gaussian noise and energy misalignment in the modified dataset. 56 A combined PCA and k-means clustering approach thus represents a powerful means of determining of the spectral components based on statistical deconvolution of datasets. 50 , 52 , 57 , 58 Notably, the cluster analysis in Figure S12 delineates three distinct clusters despite the presence of only two Li x V 2 O 5 phases in the generated dataset.…”

On-line visualization of multicolor chemical images with stimulated Raman scattering spectral microscopy

“…This adverse effect is large, particularly when the signal-to-noise ratio of original data is low. 24 Third, ICA has advantages over PCA in the interpretation of the results. As shown later, the loading vectors for PCA are different from the Raman spectra, and hence it is difficult to assign chemical components directly from the loading vectors.…”