[Fast and accurate numerical method for principal components analysis dealing with large image data sets].

S Minoshima; R A Koeppe

Home/Archive/PubMed

PubMed · 8683883

[Fast and accurate numerical method for principal components analysis dealing with large image data sets].

S Minoshima·R A Koeppe

View original source ↗Export metadata ↓

Abstract

The principal components analysis has been applied to various imaging studies in nuclear medicine. This technical report describes a fast and accurate numerical method of calculating eigenvalues and eigenvectors in the principal components analysis dealing with larger image data sets. The method employs both data transformation and matrix transpose of original data sets to calculate a variance-covariance or correlation matrix. The method was tested on actual image data sets using a common workstation, confirming faster execution time and efficient accuracy in comparison to a standard method.

Explore related subjects

Image Processing, Computer-Assisted Nuclear Medicine Tomography, Emission-Computed English Abstract Journal Article

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

S Minoshima, R A Koeppe. 1996. [Fast and accurate numerical method for principal components analysis dealing with large image data sets].. https://pubmed.ncbi.nlm.nih.gov/8683883/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

Rapid and accurate measurement for phase-change optical recording bits.

Conducting atomic force microscopy (CAFM) and scanning surface potential microscopy (SSPM) have been used to image the phase-change optical recording bits. Commercially available digital versatile discs (DVD) + rewritable (RW) with initialization process were measured in experiments. Comparing the measurement results of both, the measurement resolution of CAFM is far superior to that of SSPM. With the DVD + RW disc rotating at a linear speed of 3.5 m/s, appropriate writing laser power range, may be precisely identified by CAFM as 10-15 mW. This is sufficient to verify the high-resolution recording bits research method. This new method may also be applied to the development of new types of phase-change recording materials.

Image Processing, Computer-Assisted↗

PubMed2007

Image analysis by pulse coupled neural networks (PCNN)--a novel approach in granule size characterization.

A biologically inspired spiking neural network model, the pulse coupled neural network (PCNN), has been applied for the first time in bulk particle characterization, and specifically in the characterization of pharmaceutical granule size distributions. The PCNN was trained on surface images of pharmaceutical granule beds, and the adjustable parameters (radius neuron interconnection, r0, linking weight coefficient, beta, local threshold potential, VTheta, and number of iterations) were successfully optimized using design of experiments. As demonstrated with size fractions of granules, it was found that the PCNN produced granule size-dependent signals. In general, a first highest and relatively narrow peak located in the region of two to twelve iterations corresponded to smaller particle size, while larger particles resulted in wider peaks and in highest (not first) peak at a range between 13 and 25 iterations. Better predictions, i.e. lower RMSEP (root mean squared error of prediction) values, were obtained using high beta value, low r0 and VTheta values, while the number of iterations had to exceed 110 and the optimized model (RMSEP lower than 5) corresponded to PCNN variables: r0=1, beta=0.4, VTheta=2, and number of iterations=150. The coefficient of determination (R2) of the model was 0.94 and the predicted variation (Q2) was 0.91, while the Pearson correlation coefficient between the predicted and the measured mean particle size by sieving for eight test batches was 0.98. These findings could be characterized as promising and encouraging for the further use of image analysis by PCNNs in pharmaceutical bulk particle size and shape characterization.

Image Processing, Computer-Assisted↗

PubMed2007

Production of siRNA- and cDNA-transfected cell arrays on noncoated chambered coverglass for high-content screening microscopy in living cells.

In this chapter, we provide a protocol for the production of transfected cell arrays in living mammalian cells on noncoated chambered coverglass for the systematic functional analyses of human genes by high-content screening microscopy. This method should facilitate drug target validation by small-interfering RNAs.

Image Processing, Computer-Assisted↗