Computing and evaluating factor scores.

A variety of methods for computing factor scores can be found in the psychological literature. These methods grew out of a historic debate regarding the indeterminate nature of the common factor model. Unfortunately, most researchers are unaware of the indeterminacy issue and the problems associated with a number of the factor scoring procedures. This article reviews the history and nature of factor score indeterminacy. Novel computer programs for assessing the degree of indeterminacy in a given analysis, as well as for computing and evaluating different types of factor scores, are then presented and demonstrated using data from the Wechsler Intelligence Scale for Children--Third Edition. It is argued that factor score indeterminacy should be routinely assessed and reported as part of any exploratory factor analysis and that factor scores should be thoroughly evaluated before they are reported or used in subsequent statistical analyses. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Application of artificial neural networks for quantitative analysis of image data in chest radiographs for detection of interstitial lung disease

The authors have developed an automated computeraided diagnostic (CAD) scheme by using artificial neural networks (ANNs) on quantitative analysis of image data. Three separate ANNs were applied for detection of interstitial disease on digitized chest images. The first ANN was trained with horizontal profiles in regions of interest (ROIs) selected from normal and abnormal chest radiographs for distinguishing between normal and abnormal patterns. For training and testing of the second ANN, the vertical output patterns obtained from the 1st ANN were used for each ROI. The output value of the second ANN was used to distinguish between normal and abnormal ROIs with interstitial infiltrates. If the ratio of the number of abnormal ROIs to the total number of all ROIs in a chest image was greater than a specified threshold level, the image was classified as abnormal. In addition, the third ANN was applied to distinguish between normal and abnormal chest images. The combination of the rule-based method and the third ANN also was applied to the classification between normal and abnormal chest images. The performance of the ANNs was evaluated by means of receiver operating characteristic (ROC) analysis. The average Az value (area under the ROC curve) for distinguishing between normal and abnormal cases was 0.976 +/- 0.012 for 100 chest radiographs that were not used in training of ANNs. The results indicate that the ANN trained with image data can learn some statistical properties associated with interstitial infiltrates in chest radiographs.     

A new, more powerful approach to multitrait-multimethod analyses: Application of second-order confirmatory factor analysis.

The advantages of applying confirmatory factor analysis (CFA) to multitrait–multimethod (MTMM) data are widely recognized. However, because CFA, as traditionally applied to MTMM data, incorporates single indicators of each scale (i.e., each trait–method combination), important weaknesses are the failure to (a) correct appropriately for measurement error in scale scores, (b) separate error due to low internal consistency from uniqueness due to weak trait or method effects, (c) test whether items or subscales accurately reflect the intended factor structure, and (d) test for correlated uniquenesses. However, when the analysis begins with multiple indicators of each scale (i.e., items or subscales), second-order factor analysis can be used to address each of these problems. In this approach, first-order factors defined by multiple items or subscales are posited for each scale, and the method and trait factors are posited as second-order factors. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An attenuation measurement technique for rotating planar detector positron tomographs

This paper presents a new attenuation measurement technique suitable for rotating planar detector positron tomographs. Transmission measurements are made using two unshielded positron-emitting line sources, one attached to the front face of each detector. Many of the scattered and accidental coincidences are rejected by including only those coincidences that form a vector passing within a predetermined distance of either line source. Some scattered and accidental coincidences are still included, which reduces the measured linear attenuation: in principle their contribution can be accurately estimated and subtracted, but in practice, when limited statistics are available (as is the case with the multi-wire Birmingham positron camera), this background subtraction unacceptably increases the noise. Instead an attenuation image having the correct features can be reconstructed from the measured projections. For objects containing only a few discrete linear attenuation coefficients, segmentation of this attenuation image reduces noise and allows the correct linear attenuation coefficients to be restored by renormalization. Reprojection through the segmented image may then provide quantitatively correct attenuation correction factors of sufficient statistical quality to correct for attenuation in PET emission images.     

图像分割评估方法在显微图像分析中的应用

图像分割是计算机视觉领域中的重要分支,旨在将图像分成若干个特定的、具有独特性质的区域。随着计算机硬件计算能力的提高和计算方法的进步,大量基于不同理论的图像分割算法获得了长足的发展。因而选择合适的评估方法对分割结果的准确性和适用性进行综合评估,从而选择最优分割算法,成为图像分割研究中的必要环节。在综述14种图像分割评估指标的基础上,将其分成基于像素的评估方法、基于类内重合度的评估方法、基于边界的评估方法、基于聚类的评估方法和基于实例的评估方法五大类。在材料显微图像分析的应用背景下,通过实验讨论了不同分割方法和不同典型噪声在不同评估方法中的表现。最终,讨论了各种评估方法的优势和适用性。      

Wavelet image extension for analysis and classification of infarcted myocardial tissue

Some computer applications for tissue characterization in medicine and biology, such as analysis of the myocardium or cancer recognition, operate with tissue samples taken from very small areas of interest. In order to perform texture characterization in such an application, only a few texture operators can be employed: the operators should be insensitive to noise and image distortion and yet be reliable in order to estimate texture quality from the small number of image points available. In order to describe the quality of infarcted myocardial tissue, we propose a new wavelet-based approach for analysis and classification of texture samples with small dimensions. The main idea of this method is to decompose the given image with a filter bank derived from an orthonormal wavelet basis and to form an image approximation with higher resolution. Texture energy measures calculated at each output of the filter bank as well as energies of synthesized images are used as texture features in a classification procedure. We propose an unsupervised classification technique based on a modified statistical t-test. The method is tested with clinical data, and the classification results obtained are very promising. The performance of the new method is compared with the performance of several other transform-based methods. The new algorithm has advantages in classification of small and noisy input samples, and it represents a step toward structural analysis of weak textures.     

History of the West of Scotland Plastic Surgery Unit: 1940-1986

In this study a comparison is made between intraoral and extraoral radiographical techniques for quantitative measurements of bone density in the edentulous mandible. A phantom model, composed of a dry mandible surrounded by a soft tissue substitute was used. Radiographs were made of aluminium implants of known volumes. Intra- and extraorally placed reference wedges of aluminium or a combination of aluminium and plexiglas were used for the measurement of the aluminium volume of the above-mentioned implants and compared with the real volume. The IBAS image analysis system was used for image processing and measurements. A systematic deficit in the measured volume of 15 to 29% was found. This error was irrespective of the radiographical technique and indicates a constant underestimation of the aluminium volumes. The differential influence of the secondary radiation on the images of the jaw and the wedge is proposed to be a possible cause of this constant underestimation. The intraoral and extraoral techniques do not display significant statistical differences in the levels of validity or accuracy. Obtaining serial intraoral radiographs of adequate quality in the atrophic edentulous mandible can be problematic. It is concluded from this in vitro study that in these cases Oblique Lateral Cephalometric Radiographs may provide a valuable alternative for quantitative image analysis.     

Tests for comparing images based on randomization and permutation methods

Tests comparing image sets can play a critical role in PET research, providing a yes-no answer to the question "Are two image sets different?" The statistical goal is to determine how often observed differences would occur by chance alone. We examined randomization methods to provide several omnibus test for PET images and compared these tests with two currently used methods. In the first series of analyses, normally distributed image data were simulated fulfilling the requirements of standard statistical tests. These analyses generated power estimates and compared the various test statistics under optimal conditions. Varying whether the standard deviations were local or pooled estimates provided an assessment of a distinguishing feature between the SPM and Montreal methods. In a second series of analyses, we more closely simulated current PET acquisition and analysis techniques. Finally, PET images from normal subjects were used as an example of randomization. Randomization proved to be a highly flexible and powerful statistical procedure. Furthermore, the randomization test does not require extensive and unrealistic statistical assumptions made by standard procedures currently in use.     

A multimethod factor analysis of behavioral and objective measures of psychopathology.

Evaluated the extent to which certain objective tests, ward behavior ratings, recorded verbalization scores, and interview behavior ratings possessed convergent and discriminant validity for 10 psychotic syndromes in a varied group of 125 psychotics drawn from 5 hospitals. A multimethod factor analysis was made of the 10 interview behavior and 12 ward behavior syndrome scores, and a similar analysis made of the entire set of 48 variables. The 1st analysis yielded 10 multimethod factors that corresponded closely to the original 10 interview syndromes. In the 2nd analysis, 12 interpretable factors were obtained, all of which exhibited convergent validity for 2 or 3 method sources. 1 or more objective test variables were meaningfully associated with each of the factors except 1. It is concluded that the convergent and discriminant validity of the syndromes is strongly supported. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Applications of standard error estimates in unrestricted factor analysis: Significance tests for factor loadings and correlations.

Estimates of standard errors of factor loadings and factor correlations in the unrestricted factor analysis model can be computed for oblique or orthogonal solutions under maximum likelihood. This information can be used to test individual coefficients for significance, to evaluate whether an orthogonal or oblique structure is most consistent with sample data, or to compute confidence intervals for single parameters or confidence regions for arbitrary groups of coefficients. Because the number of parameters estimated in factor analysis is approximately the product of number of variables multiplied by number of factors, a Bonferroni correction for the critical point of the individual test statistics is recommended to control the probability of a Type I error. Several examples are presented. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Genetic and environmental contributions to size, color, shape, and other characteristics of melanocytic naevi in a sample of adolescent twins

The presence of melanocytic naevi is the strongest known risk factor for malignant melanoma. We have developed a computer imaging system with which it is possible to make quantitative measures of the size, color, and shape of pigmented lesions. The objective of this study was to examine the genetic and environmental contributions to these characteristics of naevi as measured by computer image analysis in a sample of adolescent twins. We captured video images of the 5 most atypical pigmented skin lesions (i.e., the largest, darkest, or most irregularly shaped) on each individual from 322 Australian adolescent twin pairs. Features extracted by computer image analysis for each lesion included color, size, symmetry, elongation, boundary irregularity, and edge distinctness. We found major genetic influences on the color and size of lesions accounting for between 40 and 80% of total variance. There were significant components of shared environmental influence (22-45% of total variance) for the color variables, with sun exposure the most obvious explanation. Differences between individuals in naevus color and size are largely genetic in origin although there are significant environmental contributions to color as well.     

Note of caution on the factor analysis of the MMPI.

Although the dangers associated with factoring test scales containing overlapping items (items used on more than 1 scale) have been pointed out by Guilford (1952), factor studies of scales embodying item overlap continue. The present study explores the possibility that the neurotic triad and the psychotic triad or tetrad factors found in 4 studies derive from the existence of a methodological artifact associated with item overlap. To test this possibility, MMPI interscale common-element correlations (produced solely by item overlap) were factor analyzed. 2 of 3 factors extracted are highly similar to neurotic triad and psychotic triad or tetrad factors found for 4 samples. These 2 factors do not appear in a factor analysis of truncated (overlap items removed) MMPI scale scores. Since the overlap factors are based solely on the scale intercorrelations due to overlap items, these results appear to support Guilford's warning and open to question the legitimacy of these MMPI factors. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Potential advantage of flash echocardiography for digital subtraction of B-mode images acquired during myocardial contrast echocardiography

Optimal assessment of myocardial perfusion with contrast echocardiography by using B-mode imaging often requires image alignment and background subtraction, which are time consuming and need extensive expertise. Flash echocardiography is a new technique in which primary images are gated to the electrocardiogram and secondary images are obtained by transmitting ultrasound pulses in rapid succession after each primary image. Myocardial opacification is seen in the primary image and not in the secondary images because of ultrasound-induced bubble destruction. Because the interval between the primary and first few secondary images is very short, cardiac motion between these images should be minimal. Therefore we hypothesized that 1 or more secondary images could be subtracted from the primary image without the need for image alignment. The ability of ultrasound to destroy microbubbles was assessed by varying the sampling rate, line density, and mechanical index in 6 open-chest dogs. The degree of translation between images was quantified in the x and y directions with the use of computer cross-correlation. At sampling rates of 158 Hz or less and a mechanical index of more than 0.6, videointensity rapidly declined to baseline levels by 25 ms. Significant translation between images was noted only at intervals of more than 112 ms. It is concluded that flash echocardiography can be used for digital subtraction of baseline from contrast-enhanced B-mode images without image alignment. Background subtraction is therefore feasible on-line, potentially eliminating the need for off-line image processing in the future.     

Clinical uses of mental imagery: Experimental foundations, theoretical misconceptions, and research issues.

Suggests that the growing use of mental imagery in clinical settings has been hampered by major theoretical deficits, notably the virtual absence of interdisciplinary models not constrained by a specific therapeutic orientation. Information-processing data pertaining to the functional and structural properties of imagery are reviewed to illustrate that images may be but incomplete pictures that also convey nonpictorial, abstract information. It is proposed that the imagery and verbal/symbolic processing systems are functionally discrete but comparably influential in image generation, elaboration, and appraisal, a property suggesting that clinical images comprise multiple representational events of a visual, verbal, and affective nature. The notion of the image as a mental photograph has only limited applicability. Methodological concerns associated with the study of clinical imagery are examined, pertinent literature is reviewed for each issue, and data are presented to demonstrate the significance of the problems confronting contemporary imagery researchers. (119 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Transfer factor in the age of molecular biology: a review

Current data suggests that the transferring of immunologically specific information by transfer factor molecules requires interaction with a cell that has been genetically programmed to be antigen reactive but at the time of interaction is unprimed. Contact with transfer factor molecules would allow a naive recipient, on a first encounter with antigen, to make a secondary rather than a primary immunological response. Transfer factor molecules for each and every antigenic determinant are thus necessary. Transfer factors made from animals or humans are capable of transferring antigen specificity across a species barrier. Even primitive species have cells from which one can make transfer factors. The molecules are, therefore, well conserved and it is reasonable to suggest that they are important for normal immunological functioning. Proposed mechanisms of action must explain the fact that transfer factors obtained from the cells of high responder animals are capable of transferring delayed hypersensitivity to low responder animals while the reverse is not true. Transfer factor molecules are likely to interact with the variable regions of the alpha and/or beta chain of T cell receptors to change their avidity and affinity for antigen in a way that otherwise would only occur after an encounter with antigen.     

Trends of twinning rates in ten countries, 1972-1996

The data quality and completeness of acquired images, which we refer to as integrity, is considered as the most important requirement in the image acquisition design of the Picture Archiving and Communication System (PACS). The Digital Imaging and Communications in Medicine (DICOM) standard significantly simplifies the task of acquiring radiological images from a DICOM compliant imaging system into the PACS. However, human interaction with the imaging system by changing the DICOM communication settings can result in missing images during the PACS image acquisition. A scheme based on the DICOM Query and Retrieve (Q/R) service class was developed to automatically identify and recover missing images. In addition, grouping sequential scanned images such as a CT and MR image series is another potential process that can miss images because of no indication of the end of series. Two methods are presented for determining the end of series and the pros and cons of each method are discussed in detail. Two experiments in a real clinical environment were conducted; one with and one without the Q/R implementation. The statistical results indicate two highlights from this work. First, the Q/R scheme faithfully recovered all missing images caused by human interaction with the DICOM compliant imaging system. Second, there was no single image slice missed when grouping slices into a series using the presented grouping algorithm in the two experimental periods.     

Synthetic 2-amino alcohol derivatives as chiral auxiliaries

This work describes both the concepts used in an Object Manager for storage of medical images as one more data type associated to objects, and a support system developed to offer this kind of tool to medical application developers. The purpose of this work is to support the retrieval of images through queries based on the graphical contents of the stored images. The usual approach uses icons and textual attributes stored with the images to specify the queries. This work uses a novel modeling technique to define the "image data type," by means of which it is possible to decide, before the query itself, the key data of each image that must be extracted from the image when it is stored in the database, so the search can be accelerated when queries are issued. This approach enables building of expansible systems, where new image processing algorithms can be added easily, using its syntactic representation stored through an Image Meta-schema into the application database schema. This work shows how such a system has been implemented, and also provides a query language used to refer and execute these algorithms from inside the database management system.