No abstract

No abstract

Optic disc (OD), especially its diameter together with optic cup diameter can be used as a feature to diagnose glaucoma. This study contains two main steps for optic disc localisation, i.e. OD centre point detection and OD diameter determination. Centre point of OD is obtained by finding brightness pixel value based on average filtering. After that, OD diameter is measured from the detected optic disc boundary. The proposed scheme is validated on 30 healthy and glaucoma retinal fundus images from HRF database. The results are compared to the ground truth images. The proposed scheme obtains evaluation result (E) for healthy and glaucoma images is 0.23 and 0.21, respectively. Evaluation result (E) shows the ratio between the average distance of OD centre point obtained by proposed method and that of the ground truth divided by average difference between OD diameter by proposed method and that of the ground truth. The lesser the value of E the better the performance of the method in detecting OD centre point and determining the OD diameter. Therefore, these results indicate successful implementation of automated OD localisation by detecting OD centre point and determining OD diameter in healthy and glaucoma images. Moreover, this scheme has a potential to be implemented in the development of a computerised glaucoma diagnosis system.

Stroop-task is one of the most popular studies to check the ability of decision-making and cognitive process during high interference activity in the brain. In the incongruent Stroop-task, the difference between the colour that we read and the colour that we see produces high interference activities in the brain. This research aims to analyse the activity differences in each part of the brain during colour-task and word-task. This study investigates how well the ability of decision-making and cognitive process during high interference activities that occur in the brain. Electroencephalography (EEG) can record brain activities by recording the brain waves. The results show that recognising the colour is more difficult than that of the written words in the Stroop-task as indicated by statistical test with t-value greater than threshold value (t>2.0027) and significant level of 0.05. This study concludes that the colour-task gives more interference effect than the word-task. The more interference effect is produced, the more wrong decision-making is obtained.

The World Health Organization (WHO) has predicted 300 million peoples will suffer from diabetes in 2025. Long-term diabetes can lead to diabetic retinopathy that can cause blindness in developing countries. One of the abnormalities of diabetic retinopathy is exudate. This paper proposes texture-based extraction of features from retinal images for distinguishing exudates from non-exudates. The green channel of the original retinal image is enhanced using contrastlimited adaptive histogram equalization (CLAHE). Meanwhile, in the red channel, median filtering and thresholding are conducted to detect and remove the optic disc. The enhanced green channel is multiplied by the segmented optic disc of red channel. The resulting image is then segmented based on clustering to obtain the region of interest for exudates. Feature extraction based on texture is conducted using a gray-level co-occurrence matrix (GLCM) and lacunarity. The results show that classification based on the "naïve" Bayes algorithm achieves accuracy, specificity and sensitivity of 92.13%, 96% and 87.18%, respectively.