Failure on clinical image quality criteria in digital mammography: how can radiographers do better?

Purpose: To assess image quality using PGMI (perfect, good, moderate, inadequate) scale in digital mammography examinations acquired in DR systems. Identify the main failures and propose corrective actions. Evaluate the most typical breast density. Methods and Materials: Clinical image quality criteria were evaluated considering mammograms acquired in 13 DR systems and classified according to PGMI scale using the criteria described in European Commission guidelines for radiographers. The breast density was assessed according to ACR recommendations. The data were collected on the acquisition system monitor to reproduce the daily practice of the radiographer. Results: The image quality criteria were evaluated in 3044 images. The criteria were fully achieved in 41% of the images that were classified as P (perfect), 31 % of the images were classified as M (moderate), 20% G (good) and 9% I (inadequate). The main cause of inadequate image quality was absence of all breast tissue in the image, skin folders in the pectoral muscle and in the infra-mammary angle. The higher number of failures occurred in MLO projections (809 out of 1022). The most represented (36%) breast type was type 2 (25-50% glandular tissue). Conclusion: Incorrect radiographic technique was frequently detected suggesting potential training needs and poor communication between the team members (radiographer and radiologists). Further correlations are necessary to identify the main causes for the failures, namely specific education and training in digital mammography and workload.

The impact of Sinogram-Affirmed Iterative Reconstruction on patient dose and image quality compared to filtered back projection: a narrative review

Objective: Summarize all relevant findings in published literature regarding the potential dose reduction related to image quality using Sinogram-Affirmed Iterative Reconstruction (SAFIRE) compared to Filtered Back Projection (FBP). Background: Computed Tomography (CT) is one of the most used radiographic modalities in clinical practice providing high spatial and contrast resolution. However it also delivers a relatively high radiation dose to the patient. Reconstructing raw-data using Iterative Reconstruction (IR) algorithms has the potential to iteratively reduce image noise while maintaining or improving image quality of low dose standard FBP reconstructions. Nevertheless, long reconstruction times made IR unpractical for clinical use until recently. Siemens Medical developed a new IR algorithm called SAFIRE, which uses up to 5 different strength levels, and poses an alternative to the conventional IR with a significant reconstruction time reduction. Methods: MEDLINE, ScienceDirect and CINAHL databases were used for gathering literature. Eleven articles were included in this review (from 2012 to July 2014). Discussion: This narrative review summarizes the results of eleven articles (using studies on both patients and phantoms) and describes SAFIRE strengths for noise reduction in low dose acquisitions while providing acceptable image quality. Conclusion: Even though the results differ slightly, the literature gathered for this review suggests that the dose in current CT protocols can be reduced at least 50% while maintaining or improving image quality. There is however a lack of literature concerning paediatric population (with increased radiation sensitivity). Further studies should also assess the impact of SAFIRE on diagnostic accuracy.

A comparison of Sinogram Affirmed Iterative Reconstruction and filtered back projection on image quality and dose reduction in paediatric head CT: a phantom study

Background: Computed tomography (CT) is one of the most used modalities for diagnostics in paediatric populations, which is a concern as it also delivers a high patient dose. Research has focused on developing computer algorithms that provide better image quality at lower dose. The iterative reconstruction algorithm Sinogram-Affirmed Iterative Reconstruction (SAFIRE) was introduced as a new technique that reduces noise to increase image quality. Purpose: The aim of this study is to compare SAFIRE with the current gold standard, Filtered Back Projection (FBP), and assess whether SAFIRE alone permits a reduction in dose while maintaining image quality in paediatric head CT. Methods: Images were collected using a paediatric head phantom using a SIEMENS SOMATOM PERSPECTIVE 128 modulated acquisition. 54 images were reconstructed using FBP and 5 different strengths of SAFIRE. Objective measures of image quality were determined by measuring SNR and CNR. Visual measures of image quality were determined by 17 observers with different radiographic experiences. Images were randomized and displayed using 2AFC; observers scored the images answering 5 questions using a Likert scale. Results: At different dose levels, SAFIRE significantly increased SNR (up to 54%) in the acquired images compared to FBP at 80kVp (5.2-8.4), 110kVp (8.2-12.3), 130kVp (8.8-13.1). Visual image quality was higher with increasing SAFIRE strength. The highest image quality was scored with SAFIRE level 3 and higher. Conclusion: The SAFIRE algorithm is suitable for image noise reduction in paediatric head CT. Our data demonstrates that SAFIRE enhances SNR while reducing noise with a possible reduction of dose of 68%.

Global localization with non-quantized local image features

In the field of appearance-based robot localization, the mainstream approach uses a quantized representation of local image features. An alternative strategy is the exploitation of raw feature descriptors, thus avoiding approximations due to quantization. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity, in the context of the robot global localization problem. Having demonstrated the advantages of the non-quantized representation, the paper proposes mechanisms to reduce the computational burden this approach would carry, when applied in its simplest form. This reduction is achieved through a hierarchical strategy which gradually discards candidate locations and by exploring two simplifying assumptions about the training data. The potential of the non-quantized representation is exploited by resorting to the entropy-discriminativity relation. The idea behind this approach is that the non-quantized representation facilitates the assessment of the distinctiveness of features, through the entropy measure. Building on this finding, the robustness of the localization system is enhanced by modulating the importance of features according to the entropy measure. Experimental results support the effectiveness of this approach, as well as the validity of the proposed computation reduction methods.

In-plane displacement and strain image analysis

Measurements in civil engineering load tests usually require considerable time and complex procedures. Therefore, measurements are usually constrained by the number of sensors resulting in a restricted monitored area. Image processing analysis is an alternative way that enables the measurement of the complete area of interest with a simple and effective setup. In this article photo sequences taken during load displacement tests were captured by a digital camera and processed with image correlation algorithms. Three different image processing algorithms were used with real images taken from tests using specimens of PVC and Plexiglas. The data obtained from the image processing algorithms were also compared with the data from physical sensors. A complete displacement and strain map were obtained. Results show that the accuracy of the measurements obtained by photogrammetry is equivalent to that from the physical sensors but with much less equipment and fewer setup requirements. © 2015Computer-Aided Civil and Infrastructure Engineering.

Exploiting the bin-class histograms for feature selection on discrete data

In machine learning and pattern recognition tasks, the use of feature discretization techniques may have several advantages. The discretized features may hold enough information for the learning task at hand, while ignoring minor fluctuations that are irrelevant or harmful for that task. The discretized features have more compact representations that may yield both better accuracy and lower training time, as compared to the use of the original features. However, in many cases, mainly with medium and high-dimensional data, the large number of features usually implies that there is some redundancy among them. Thus, we may further apply feature selection (FS) techniques on the discrete data, keeping the most relevant features, while discarding the irrelevant and redundant ones. In this paper, we propose relevance and redundancy criteria for supervised feature selection techniques on discrete data. These criteria are applied to the bin-class histograms of the discrete features. The experimental results, on public benchmark data, show that the proposed criteria can achieve better accuracy than widely used relevance and redundancy criteria, such as mutual information and the Fisher ratio.

Estimation of signal subspace on hyperspectral data

Dimensionality reduction plays a crucial role in many hyperspectral data processing and analysis algorithms. This paper proposes a new mean squared error based approach to determine the signal subspace in hyperspectral imagery. The method first estimates the signal and noise correlations matrices, then it selects the subset of eigenvalues that best represents the signal subspace in the least square sense. The effectiveness of the proposed method is illustrated using simulated and real hyperspectral images.

A toolbox for hyperspectral image analysis

This paper introduces a new toolbox for hyperspectral imagery, developed under the MATLAB environment. This toolbox provides easy access to different supervised and unsupervised classification methods. This new application is also versatile and fully dynamic since the user can embody their own methods, that can be reused and shared. This toolbox, while extends the potentiality of MATLAB environment, it also provides a user-friendly platform to assess the results of different methodologies. In this paper it is also presented, under the new application, a study of several different supervised and unsupervised classification methods on real hyperspectral data.

Vertex component analysis: a geometric-based approach to unmix hyperspectral data

Hyperspectral remote sensing exploits the electromagnetic scattering patterns of the different materials at specific wavelengths [2, 3]. Hyperspectral sensors have been developed to sample the scattered portion of the electromagnetic spectrum extending from the visible region through the near-infrared and mid-infrared, in hundreds of narrow contiguous bands [4, 5]. The number and variety of potential civilian and military applications of hyperspectral remote sensing is enormous [6, 7]. Very often, the resolution cell corresponding to a single pixel in an image contains several substances (endmembers) [4]. In this situation, the scattered energy is a mixing of the endmember spectra. A challenging task underlying many hyperspectral imagery applications is then decomposing a mixed pixel into a collection of reflectance spectra, called endmember signatures, and the corresponding abundance fractions [8–10]. Depending on the mixing scales at each pixel, the observed mixture is either linear or nonlinear [11, 12]. Linear mixing model holds approximately when the mixing scale is macroscopic [13] and there is negligible interaction among distinct endmembers [3, 14]. If, however, the mixing scale is microscopic (or intimate mixtures) [15, 16] and the incident solar radiation is scattered by the scene through multiple bounces involving several endmembers [17], the linear model is no longer accurate. Linear spectral unmixing has been intensively researched in the last years [9, 10, 12, 18–21]. It considers that a mixed pixel is a linear combination of endmember signatures weighted by the correspondent abundance fractions. Under this model, and assuming that the number of substances and their reflectance spectra are known, hyperspectral unmixing is a linear problem for which many solutions have been proposed (e.g., maximum likelihood estimation [8], spectral signature matching [22], spectral angle mapper [23], subspace projection methods [24,25], and constrained least squares [26]). In most cases, the number of substances and their reflectances are not known and, then, hyperspectral unmixing falls into the class of blind source separation problems [27]. Independent component analysis (ICA) has recently been proposed as a tool to blindly unmix hyperspectral data [28–31]. ICA is based on the assumption of mutually independent sources (abundance fractions), which is not the case of hyperspectral data, since the sum of abundance fractions is constant, implying statistical dependence among them. This dependence compromises ICA applicability to hyperspectral images as shown in Refs. [21, 32]. In fact, ICA finds the endmember signatures by multiplying the spectral vectors with an unmixing matrix, which minimizes the mutual information among sources. If sources are independent, ICA provides the correct unmixing, since the minimum of the mutual information is obtained only when sources are independent. This is no longer true for dependent abundance fractions. Nevertheless, some endmembers may be approximately unmixed. These aspects are addressed in Ref. [33]. Under the linear mixing model, the observations from a scene are in a simplex whose vertices correspond to the endmembers. Several approaches [34–36] have exploited this geometric feature of hyperspectral mixtures [35]. Minimum volume transform (MVT) algorithm [36] determines the simplex of minimum volume containing the data. The method presented in Ref. [37] is also of MVT type but, by introducing the notion of bundles, it takes into account the endmember variability usually present in hyperspectral mixtures. The MVT type approaches are complex from the computational point of view. Usually, these algorithms find in the first place the convex hull defined by the observed data and then fit a minimum volume simplex to it. For example, the gift wrapping algorithm [38] computes the convex hull of n data points in a d-dimensional space with a computational complexity of O(nbd=2cþ1), where bxc is the highest integer lower or equal than x and n is the number of samples. The complexity of the method presented in Ref. [37] is even higher, since the temperature of the simulated annealing algorithm used shall follow a log( ) law [39] to assure convergence (in probability) to the desired solution. Aiming at a lower computational complexity, some algorithms such as the pixel purity index (PPI) [35] and the N-FINDR [40] still find the minimum volume simplex containing the data cloud, but they assume the presence of at least one pure pixel of each endmember in the data. This is a strong requisite that may not hold in some data sets. In any case, these algorithms find the set of most pure pixels in the data. PPI algorithm uses the minimum noise fraction (MNF) [41] as a preprocessing step to reduce dimensionality and to improve the signal-to-noise ratio (SNR). The algorithm then projects every spectral vector onto skewers (large number of random vectors) [35, 42,43]. The points corresponding to extremes, for each skewer direction, are stored. A cumulative account records the number of times each pixel (i.e., a given spectral vector) is found to be an extreme. The pixels with the highest scores are the purest ones. N-FINDR algorithm [40] is based on the fact that in p spectral dimensions, the p-volume defined by a simplex formed by the purest pixels is larger than any other volume defined by any other combination of pixels. This algorithm finds the set of pixels defining the largest volume by inflating a simplex inside the data. ORA SIS [44, 45] is a hyperspectral framework developed by the U.S. Naval Research Laboratory consisting of several algorithms organized in six modules: exemplar selector, adaptative learner, demixer, knowledge base or spectral library, and spatial postrocessor. The first step consists in flat-fielding the spectra. Next, the exemplar selection module is used to select spectral vectors that best represent the smaller convex cone containing the data. The other pixels are rejected when the spectral angle distance (SAD) is less than a given thresh old. The procedure finds the basis for a subspace of a lower dimension using a modified Gram–Schmidt orthogonalizati on. The selected vectors are then projected onto this subspace and a simplex is found by an MV T pro cess. ORA SIS is oriented to real-time target detection from uncrewed air vehicles using hyperspectral data [46]. In this chapter we develop a new algorithm to unmix linear mixtures of endmember spectra. First, the algorithm determines the number of endmembers and the signal subspace using a newly developed concept [47, 48]. Second, the algorithm extracts the most pure pixels present in the data. Unlike other methods, this algorithm is completely automatic and unsupervised. To estimate the number of endmembers and the signal subspace in hyperspectral linear mixtures, the proposed scheme begins by estimating sign al and noise correlation matrices. The latter is based on multiple regression theory. The signal subspace is then identified by selectin g the set of signal eigenvalue s that best represents the data, in the least-square sense [48,49 ], we note, however, that VCA works with projected and with unprojected data. The extraction of the end members exploits two facts: (1) the endmembers are the vertices of a simplex and (2) the affine transformation of a simplex is also a simplex. As PPI and N-FIND R algorithms, VCA also assumes the presence of pure pixels in the data. The algorithm iteratively projects data on to a direction orthogonal to the subspace spanned by the endmembers already determined. The new end member signature corresponds to the extreme of the projection. The algorithm iterates until all end members are exhausted. VCA performs much better than PPI and better than or comparable to N-FI NDR; yet it has a computational complexity between on e and two orders of magnitude lower than N-FINDR. The chapter is structure d as follows. Section 19.2 describes the fundamentals of the proposed method. Section 19.3 and Section 19.4 evaluate the proposed algorithm using simulated and real data, respectively. Section 19.5 presents some concluding remarks.

Fast unsupervised extraction of endmembers spectra from hyperspectral data

Linear unmixing decomposes an hyperspectral image into a collection of re ectance spectra, called endmember signatures, and a set corresponding abundance fractions from the respective spatial coverage. This paper introduces vertex component analysis, an unsupervised algorithm to unmix linear mixtures of hyperpsectral data. VCA exploits the fact that endmembers occupy vertices of a simplex, and assumes the presence of pure pixels in data. VCA performance is illustrated using simulated and real data. VCA competes with state-of-the-art methods with much lower computational complexity.

Spatial metrics and Landsat data for urban landuse change detection: case of Addis Ababa, Ethiopia.

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Automated image tagging through tag propagation

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial Para obtenção do grau de Mestre em Engenharia Informática

Spatio-Temporal data modeling in response to deforestation monitoring (a case study of small region in Riau Province, Indonesia)

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Microscopy image segmentation by active contour models

In this thesis a semi-automated cell analysis system is described through image processing. To achieve this, an image processing algorithm was studied in order to segment cells in a semi-automatic way. The main goal of this analysis is to increase the performance of cell image segmentation process, without affecting the results in a significant way. Even though, a totally manual system has the ability of producing the best results, it has the disadvantage of taking too long and being repetitive, when a large number of images need to be processed. An active contour algorithm was tested in a sequence of images taken by a microscope. This algorithm, more commonly known as snakes, allowed the user to define an initial region in which the cell was incorporated. Then, the algorithm would run several times, making the initial region contours to converge to the cell boundaries. With the final contour, it was possible to extract region properties and produce statistical data. This data allowed to say that this algorithm produces similar results to a purely manual system but at a faster rate. On the other hand, it is slower than a purely automatic way but it allows the user to adjust the contour, making it more versatile and tolerant to image variations.

Optimization of breast tomosynthesis image reconstruction using parallel computing

Breast cancer is the most common cancer among women, being a major public health problem. Worldwide, X-ray mammography is the current gold-standard for medical imaging of breast cancer. However, it has associated some well-known limitations. The false-negative rates, up to 66% in symptomatic women, and the false-positive rates, up to 60%, are a continued source of concern and debate. These drawbacks prompt the development of other imaging techniques for breast cancer detection, in which Digital Breast Tomosynthesis (DBT) is included. DBT is a 3D radiographic technique that reduces the obscuring effect of tissue overlap and appears to address both issues of false-negative and false-positive rates. The 3D images in DBT are only achieved through image reconstruction methods. These methods play an important role in a clinical setting since there is a need to implement a reconstruction process that is both accurate and fast. This dissertation deals with the optimization of iterative algorithms, with parallel computing through an implementation on Graphics Processing Units (GPUs) to make the 3D reconstruction faster using Compute Unified Device Architecture (CUDA). Iterative algorithms have shown to produce the highest quality DBT images, but since they are computationally intensive, their clinical use is currently rejected. These algorithms have the potential to reduce patient dose in DBT scans. A method of integrating CUDA in Interactive Data Language (IDL) is proposed in order to accelerate the DBT image reconstructions. This method has never been attempted before for DBT. In this work the system matrix calculation, the most computationally expensive part of iterative algorithms, is accelerated. A speedup of 1.6 is achieved proving the fact that GPUs can accelerate the IDL implementation.