Andrew P. Bradley

Perceptual quality metrics applied to still image compression

We present a review of perceptual image quality metrics and their application to still image compression. The review describes how image quality metrics can be used to guide an image compression scheme and outlines the advantages, disadvantages and limitations of a number of quality metrics. We examine a broad range of metrics ranging from simple mathematical measures to those which incorporate full perceptual models. We highlight some variation in the models for luminance adaptation and the contrast sensitivity function and discuss what appears to be a lack of a general consensus regarding the models which best describe contrast masking and error summation. We identify how the various perceptual components have been incorporated in quality metrics, and identify a number of psychophysical testing techniques that can be used to validate the metrics. We conclude by illustrating some of the issues discussed throughout the paper with a simple demonstration.

A wavelet visible difference predictor

In this paper, we describe a model of the human visual system (HVS) based on the wavelet transform. This model is largely based on a previously proposed model, but has a number of modifications that make it more amenable to potential integration into a wavelet based image compression scheme. These modifications include the use of a separable wavelet transform instead of the cortex transform, the application of a wavelet contrast sensitivity function (CSF), and a simplified definition of subband contrast that allows one to predict the noise visibility directly from the wavelet coefficients. Initially, we outline the luminance, frequency, and masking sensitivities of the HVS and discuss how these can be incorporated into the wavelet transform. We then outline a number of limitations of the wavelet transform as a model of the HVS, namely the lack of translational invariance and poor orientation sensitivity. In order to investigate the efficacy of this wavelet based model, a wavelet visible difference predictor (WVDP) is described. The WVDP is then used to predict visible differences between an original and compressed (or noisy) image. Results are presented to emphasize the limitations of commonly used measures of image quality and to demonstrate the performance of the WVDP. The paper concludes with suggestions on how the WVDP can be used to determine a visually optimal quantization strategy for wavelet coefficients and produce a quantitative measure of image quality.

Intelligible Support Vector Machines for Diagnosis of Diabetes Mellitus

Diabetes mellitus is a chronic disease and a major public health challenge worldwide. According to the International Diabetes Federation, there are currently 246 million diabetic people worldwide, and this number is expected to rise to 380 million by 2025. Furthermore, 3.8 million deaths are attributable to diabetes complications each year. It has been shown that 80% of type 2 diabetes complications can be prevented or delayed by early identification of people at risk. In this context, several data mining and machine learning methods have been used for the diagnosis, prognosis, and management of diabetes. In this paper, we propose utilizing support vector machines (SVMs) for the diagnosis of diabetes. In particular, we use an additional explanation module, which turns the “black box” model of an SVM into an intelligible representation of the SVMs diagnostic (classification) decision. Results on a real-life diabetes dataset show that intelligible SVMs provide a promising tool for the prediction of diabetes, where a comprehensible ruleset have been generated, with prediction accuracy of 94%, sensitivity of 93%, and specificity of 94%. Furthermore, the extracted rules are medically sound and agree with the outcome of relevant medical studies.

Rule Extraction from Support Vector Machines: A Sequential Covering Approach

In this paper, we propose a novel algorithm for rule extraction from support vector machines (SVMs), termed SQRex-SVM. The proposed method extracts rules directly from the support vectors (SVs) of a trained SVM using a modified sequential covering algorithm. Rules are generated based on an ordered search of the most discriminative features, as measured by interclass separation. Rule performance is then evaluated using measured rates of true and false positives and the area under the receiver operating characteristic (ROC) curve (AUC). Results are presented on a number of commonly used data sets that show the rules produced by SQRex-SVM exhibit both improved generalization performance and smaller more comprehensible rule sets compared to both other SVM rule extraction techniques and direct rule learning techniques.

On wavelet analysis of auditory evoked potentials

OBJECTIVE To determine a preferred wavelet transform (WT) procedure for multi-resolution analysis (MRA) of auditory evoked potentials (AEP). METHODS A number of WT algorithms, mother wavelets, and pre-processing techniques were examined by way of critical theoretical discussion followed by experimental testing of key points using real and simulated auditory brain-stem response (ABR) waveforms. Conclusions from these examinations were then tested on a normative ABR dataset. RESULTS The results of the various experiments are reported in detail. CONCLUSIONS Optimal AEP WT MRA is most likely to occur when an over-sampled discrete wavelet transformation (DWT) is used, utilising a smooth (regularity >or=3) and symmetrical (linear phase) mother wavelet, and a reflection boundary extension policy. SIGNIFICANCE This study demonstrates the practical importance of, and explains how to minimize potential artefacts due to, 4 inter-related issues relevant to AEP WT MRA, namely shift variance, phase distortion, reconstruction smoothness, and boundary artefacts.

Precision-recall operating characteristic (P-ROC) curves in imprecise environments

Traditionally, machine learning algorithms have been evaluated in applications where assumptions can be reliably made about class priors and/or misclassification costs. In this paper, we consider the case of imprecise environments, where little may be known about these factors and they may well vary significantly when the system is applied. Specifically, the use of precision-recall analysis is investigated and compared to the more well known performance measures such as error-rate and the receiver operating characteristic (ROC). We argue that while ROC analysis is invariant to variations in class priors, this invariance in fact hides an important factor of the evaluation in imprecise environments. Therefore, we develop a generalised precision-recall analysis methodology in which variation due to prior class probabilities is incorporated into a multi-way analysis of variance (ANOVA). The increased sensitivity and reliability of this approach is demonstrated in a remote sensing application

Denoising of Dynamic Contrast-Enhanced MR Images Using Dynamic Nonlocal Means

This paper presents a new algorithm for denoising dynamic contrast-enhanced (DCE) MR images. It is a novel variation on the nonlocal means (NLM) algorithm. The algorithm, called dynamic nonlocal means (DNLM), exploits the redundancy of information in the temporal sequence of images. Empirical evaluations of the performance of the DNLM algorithm relative to seven other denoising methods-simple Gaussian filtering, the original NLM algorithm, a trivial extension of NLM to include the temporal dimension, bilateral filtering, anisotropic diffusion filtering, wavelet adaptive multiscale products threshold, and traditional wavelet thresholding-are presented. The evaluations include quantitative evaluations using simulated data and real data (20 DCE-MRI data sets from routine clinical breast MRI examinations) as well as qualitative evaluations using the same real data (24 observers: 14 image/signal-processing specialists, 10 clinical breast MRI radiographers). The results of the quantitative evaluation using the simulated data show that the DNLM algorithm consistently yields the smallest MSE between the denoised image and its corresponding original noiseless version. The results of the quantitative evaluation using the real data provide evidence, at the ¿ = 0.05 level of significance, that the DNLM algorithm yields the smallest MSE between the denoised image and its corresponding original noiseless version. The results of the qualitative evaluation provide evidence, at the ¿ = 0.05 level of significance, that the DNLM algorithm performs visually better than all of the other algorithms. Collectively the qualitative and quantitative results suggest that the DNLM algorithm more effectively attenuates noise in DCE MR images than any of the other algorithms.

An Improved Joint Optimization of Multiple Level Set Functions for the Segmentation of Overlapping Cervical Cells

In this paper, we present an improved algorithm for the segmentation of cytoplasm and nuclei from clumps of overlapping cervical cells. This problem is notoriously difficult because of the degree of overlap among cells, the poor contrast of cell cytoplasm and the presence of mucus, blood, and inflammatory cells. Our methodology addresses these issues by utilizing a joint optimization of multiple level set functions, where each function represents a cell within a clump, that have both unary (intracell) and pairwise (intercell) constraints. The unary constraints are based on contour length, edge strength, and cell shape, while the pairwise constraint is computed based on the area of the overlapping regions. In this way, our methodology enables the analysis of nuclei and cytoplasm from both free-lying and overlapping cells. We provide a systematic evaluation of our methodology using a database of over 900 images generated by synthetically overlapping images of free-lying cervical cells, where the number of cells within a clump is varied from 2 to 10 and the overlap coefficient between pairs of cells from 0.1 to 0.5. This quantitative assessment demonstrates that our methodology can successfully segment clumps of up to 10 cells, provided the overlap between pairs of cells is <;0.2. Moreover, if the clump consists of three or fewer cells, then our methodology can successfully segment individual cells even when the overlap is ~0.5. We also evaluate our approach quantitatively and qualitatively on a set of 16 extended depth of field images, where we are able to segment a total of 645 cells, of which only ~10% are free-lying. Finally, we demonstrate that our method of cell nuclei segmentation is competitive when compared with the current state of the art.

Unregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models

We show two important findings on the use of deep convolutional neural networks (CNN) in medical image analysis. First, we show that CNN models that are pre-trained using computer vision databases (e.g., Imagenet) are useful in medical image applications, despite the significant differences in image appearance. Second, we show that multiview classification is possible without the pre-registration of the input images. Rather, we use the high-level features produced by the CNNs trained in each view separately. Focusing on the classification of mammograms using craniocaudal (CC) and mediolateral oblique (MLO) views and their respective mass and micro-calcification segmentations of the same breast, we initially train a separate CNN model for each view and each segmentation map using an Imagenet pre-trained model. Then, using the features learned from each segmentation map and unregistered views, we train a final CNN classifier that estimates the patient’s risk of developing breast cancer using the Breast Imaging-Reporting and Data System (BI-RADS) score. We test our methodology in two publicly available datasets (InBreast and DDSM), containing hundreds of cases, and show that it produces a volume under ROC surface of over 0.9 and an area under ROC curve (for a 2-class problem - benign and malignant) of over 0.9. In general, our approach shows state-of-the-art classification results and demonstrates a new comprehensive way of addressing this challenging classification problem.

Stimulus specificity of a steady-state visual-evoked potential-based brain-computer interface.

The mechanisms of neural excitation and inhibition when given a visual stimulus are well studied. It has been established that changing stimulus specificity such as luminance contrast or spatial frequency can alter the neuronal activity and thus modulate the visual-evoked response. In this paper, we study the effect that stimulus specificity has on the classification performance of a steady-state visual-evoked potential-based brain-computer interface (SSVEP-BCI). For example, we investigate how closely two visual stimuli can be placed before they compete for neural representation in the cortex and thus influence BCI classification accuracy. We characterize stimulus specificity using the four stimulus parameters commonly encountered in SSVEP-BCI design: temporal frequency, spatial size, number of simultaneously displayed stimuli and their spatial proximity. By varying these quantities and measuring the SSVEP-BCI classification accuracy, we are able to determine the parameters that provide optimal performance. Our results show that superior SSVEP-BCI accuracy is attained when stimuli are placed spatially more than 5° apart, with size that subtends at least 2° of visual angle, when using a tagging frequency of between high alpha and beta band. These findings may assist in deciding the stimulus parameters for optimal SSVEP-BCI design.