Automated diagnosis of Age-related Macular Degeneration using greyscale features from digital fundus images

Age-related Macular Degeneration (AMD) is one of the major causes of vision loss and blindness in ageing population. Currently, there is no cure for AMD, however early detection and subsequent treatment may prevent the severe vision loss or slow the progression of the disease. AMD can be classified into two types: dry and wet AMDs. The people with macular degeneration are mostly affected by dry AMD. Early symptoms of AMD are formation of drusen and yellow pigmentation. These lesions are identified by manual inspection of fundus images by the ophthalmologists. It is a time consuming, tiresome process, and hence an automated diagnosis of AMD screening tool can aid clinicians in their diagnosis significantly. This study proposes an automated dry AMD detection system using various entropies (Shannon, Kapur, Renyi and Yager), Higher Order Spectra (HOS) bispectra features, Fractional Dimension (FD), and Gabor wavelet features extracted from greyscale fundus images. The features are ranked using t-test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance (CBBD), Receiver Operating Characteristics (ROC) curve-based and Wilcoxon ranking methods in order to select optimum features and classified into normal and AMD classes using Naive Bayes (NB), k-Nearest Neighbour (k-NN), Probabilistic Neural Network (PNN), Decision Tree (DT) and Support Vector Machine (SVM) classifiers. The performance of the proposed system is evaluated using private (Kasturba Medical Hospital, Manipal, India), Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) datasets. The proposed system yielded the highest average classification accuracies of 90.19%, 95.07% and 95% with 42, 54 and 38 optimal ranked features using SVM classifier for private, ARIA and STARE datasets respectively. This automated AMD detection system can be used for mass fundus image screening and aid clinicians by making better use of their expertise on selected images that require further examination.

Decision support system for age-related macular degeneration using discrete wavelet transform

Age-related macular degeneration (AMD) affects the central vision and subsequently may lead to visual loss in people over 60 years of age. There is no permanent cure for AMD, but early detection and successive treatment may improve the visual acuity. AMD is mainly classified into dry and wet type; however, dry AMD is more common in aging population. AMD is characterized by drusen, yellow pigmentation, and neovascularization. These lesions are examined through visual inspection of retinal fundus images by ophthalmologists. It is laborious, time-consuming, and resource-intensive. Hence, in this study, we have proposed an automated AMD detection system using discrete wavelet transform (DWT) and feature ranking strategies. The first four-order statistical moments (mean, variance, skewness, and kurtosis), energy, entropy, and Gini index-based features are extracted from DWT coefficients. We have used five (t test, Kullback–Lieber Divergence (KLD), Chernoff Bound and Bhattacharyya Distance, receiver operating characteristics curve-based, and Wilcoxon) feature ranking strategies to identify optimal feature set. A set of supervised classifiers namely support vector machine (SVM), decision tree, k -nearest neighbor ( k -NN), Naive Bayes, and probabilistic neural network were used to evaluate the highest performance measure using minimum number of features in classifying normal and dry AMD classes. The proposed framework obtained an average accuracy of 93.70 %, sensitivity of 91.11 %, and specificity of 96.30 % using KLD ranking and SVM classifier. We have also formulated an AMD Risk Index using selected features to classify the normal and dry AMD classes using one number. The proposed system can be used to assist the clinicians and also for mass AMD screening programs.

Age, physical inactivity, obesity, health conditions, and health-related quality of life among patients receiving conservative management for musculoskeletal disorders

Background Musculoskeletal conditions and insufficient physical activity have substantial personal and economic costs among contemporary aging societies. This study examined the age distribution, comorbid health conditions, body mass index (BMI), self-reported physical activity levels, and health-related quality of life of patients accessing ambulatory hospital clinics for musculoskeletal disorders. The study also investigated whether comorbidity, BMI, and self-reported physical activity were associated with patients’ health-related quality of life after adjusting for age as a potential confounder. Methods A cross-sectional survey was undertaken in three ambulatory hospital clinics for musculoskeletal disorders. Participants (n=224) reported their reason for referral, age, comorbid health conditions, BMI, physical activity levels (Active Australia Survey), and health-related quality of life (EQ-5D). Descriptive statistics and linear modeling were used to examine the associations between age, comorbidity, BMI, intensity and duration of physical activity, and health-related quality of life. Results The majority of patients (n=115, 51.3%) reported two or more comorbidities. In addition to other musculoskeletal conditions, common comorbidities included depression (n=41, 18.3%), hypertension (n=40, 17.9%), and diabetes (n=39, 17.4%). Approximately one-half of participants (n=110, 49.1%) self-reported insufficient physical activity to meet minimum recommended guidelines and 150 (67.0%) were overweight (n=56, 23.2%), obese (n=64, 28.6%), severely obese (n=16, 7.1%), or very severely obese (n=14, 6.3%), with a higher proportion of older patients affected. A generalized linear model indicated that, after adjusting for age, self-reported physical activity was positively associated (z=4.22, P<0.001), and comorbidities were negatively associated (z=-2.67, P<0.01) with patients’ health-related quality of life. Conclusion Older patients were more frequently affected by undesirable clinical attributes of comorbidity, obesity, and physical inactivity. However, findings from this investigation are compelling for the care of patients of all ages. Potential integration of physical activity behavior change or other effective lifestyle interventions into models of care for patients with musculoskeletal disorders is worthy of further investigation.

Minimizing the effects of overfitting and collinearity in construction cost estimation : a new hybird approach

Research problem: Overfitting and collinearity problems commonly exist in current construction cost estimation applications and obstruct researchers and practitioners in achieving better modelling results. Research objective and method: A hybrid approach of Akaike information criterion (AIC) stepwise regression and principal component regression (PCR) is proposed to help solve overfitting and collinearity problems. Utilization of this approach in linear regression is validated by comparing it with other commonly used approaches. The mean square error obtained by leave-one-out cross validation (MSELOOCV) is used in model selection in deciding predictive variables.

The use of correspondence analysis to compare major and trace elements for provenance studies of iron-age pottery from the Mngeni river area, South Africa

Provenance studies of iron-age pottery specimens originating from the Mngeni river area in South Africa was carried out by applying XRF spectrometry. A total of sixteen major and trace elements were analysed in a batch of 107 potsherds, excavated from four different archaeological sites in the aforementioned area. A multivariate statistical programme Correspondence Analysis was used in this study to obtain the relevant clustering patterns according to the similarity of the elemental distributions. Differences and similarities in the clusters obtained for the majors and trace elements are discussed.

Online Customer Experience : What is the Experience and how is it Difference for Frequent and Infrequent Purchasers, Age Cohorts and Gender Groups?

What do we know? • Customer Experience is increasingly becoming the new standard for differentiation in both offline and online retailing, and offers a sustainable competitive advantage. o The economic value of a company’s offering has been observed to increase when the customer has a fulfilling shopping experience (Pine & Gilmore, 1998) o Crafting engaging and customer experience is a known method of generating loyalty, advocacy and word of mouth (Tynan & McKechnie, 2009). o A good experience can entice consumers to shop for longer and spend more (Kim, 2001). • The customer’s experience is made up of diverse elements occurring before, during and after the purchase itself. (Discussed further on page 5). It is cumulative over time and can be influenced by touch points across multiple channels. What remains unclear? • How do Coles customers respond to the elements of online customer experience? • How does the online customer experience differ for frequent and infrequent purchasers? • Do differences between genders and age cohorts for online customer experience exist?

A study, by fire-assay and ICP-MS, of the distribution of rhodium, platinum, and gold in iron-age pottery

Forty-six archaeological specimens were treated by fire-assay and subsequently analysed by ICP-MS for selected precious metals: Ph, Pt and Au. The investigation was prompted by the possibility that archaeological samples could serve as "indicators" of the precious metal composition of the clays from the excavated sites. Therefore, the experimentally obtained concentrations were carefully studied to determine if there were anomalous levels of these precious metals in the deposits from which the specimens originated. Furthermore, the analytical data were used to establish if it was feasible to distinguish ancient potsherds based on precious metal concentrations, for employment as a basis in provenance studies.

Simulation-based density estimation for time series using covariate data

This paper proposes a simulation-based density estimation technique for time series that exploits information found in covariate data. The method can be paired with a large range of parametric models used in time series estimation. We derive asymptotic properties of the estimator and illustrate attractive finite sample properties for a range of well-known econometric and financial applications.

Obesity and hypertension have differing oxidant handling molecular pathways in age-related chronic kidney disease

Chronic kidney disease (CKD) in ageing is a burden on health systems worldwide. Rat models of age-related CKD linked with obesity and hypertension were used to investigate alterations in oxidant handling and energy metabolism to identify gene targets or markers for age-related CKD. Young adult (3 months) and old (21–24 months) spontaneously-hypertensive (SHR), normotensive Wistar-Kyoto (WKY) and Wistar rats (normotensive, obese in ageing) were compared for renal functional and physiological parameters, renal fibrosis and inflammation, oxidative stress (hemeoxygenase-1/HO-1), apoptosis and cell injury (including Bax:Bcl-2), phosphorylated and non-phosphorylated forms of oxidant and energy sensing proteins (p66Shc, AMPK), signal transduction proteins (ERK1/2, PKB), and transcription factors (NF-κB, FoxO1). All old rats were normoglycemic. Renal fibrosis, tubular epithelial apoptosis, interstitial macrophages and myofibroblasts (all p < 0.05), p66Shc/phospho-p66 (p < 0.05), Bax/Bcl-2 ratio (p < 0.05) and NF-κB expression (p < 0.01) were highest in old obese Wistars. Expression of phospho-FoxO/FoxO was elevated in old Wistars (p < 0.001) and WKYs (p < 0.01). SHRs had high levels in young and old rats. Expression of PKB, phospho-PKB, ERK1/2 and phospho-ERK1/2 were significantly elevated in all aged animals. These results suggest that obesity and hypertension have differing oxidant handling and signalling pathways that act in the pathogenesis of age-related CKD

Online estimation of Allan variance parameters

A new online method is presented for estimation of the angular randomwalk and rate randomwalk coefficients of inertial measurement unit gyros and accelerometers. In the online method, a state-space model is proposed, and recursive parameter estimators are proposed for quantities previously measured from offline data techniques such as the Allan variance method. The Allan variance method has large offline computational effort and data storage requirements. The technique proposed here requires no data storage and computational effort of approximately 100 calculations per data sample.