U. Rajendra Acharya

Computer-Based Identification of Diabetic Maculopathy Stages Using Fundus Images

Diabetes mellitus is a major cause of visual impairment and blindness. Almost all patients with type 1 diabetes and over 60% of patients with type 2 diabetes will develop some degree of retinopathy after having diabetes for 20 years. Prolonged presence of diabetic retinopathy will result in maculopathy, a condition in which the macula of the eye gets damaged. Depending on the extent of maculopathic damage, vision will become progressively impaired. This chapter presents an intelligent system that is capable of differentiating between fundus eye images belonging to normal eyes and those belonging to eyes affected by either of the two types of maculopathy – nonclinically significant macular edema (nonCSME) and clinically significant macular edema (CSME). In this proposed technique, characteristic features were extracted from the raw fundus images using morphological image processing techniques and fed to a feed-forward artificial neural network (ANN). Ninety subjects belonging to normal, nonCSME, and CSME categories were used for evaluating the proposed technique. Results showed that the p-values (obtained using the analysis of variance (ANOVA) test) of the selected features were less than 0.001, which indicates that the features are clinically significant and very discriminative. The ANN classifier resulted in a good accuracy of 96.67%, and sensitivity and specificity of 96.67 and 100%, respectively.

AUTOMATED CAROTID INTIMA MEDIA THICKNESS FOR PREDICTION OF SYNTAX SCORE IN JAPANESE CORONARY ARTERY DISEASE PATIENTS

Background: Atherosclerosis of the carotid artery represents one of the major causes of morbidity and mortality in developed countries. The SYNTAX score (SXscore), is an angiographic score that reflects coronary lesion complexity and it is used to predict clinical outcomes in patients with single or multivessel disease. The purpose of this study was evaluate whether the carotid intima media thickness (CIMT) measured by using an automated software (AtheroEdgeLink) could predict the SYNTAX score for coronary artery disease patients. Methods: We tested 370 consecutive patients (males 218, females 152; median age 69 years ± 11) who underwent carotid ultrasound and coronary angiography. The SXscore of the 370 patients was independently assessed by two experienced cardiologists, who calculated the SXscore by considering each coronary lesion producing ≥50% diameter stenosis in vessels ≥1.5 mm according to the algorithm available on the SYNTAX website. The CIMT values was measured by the automated system AtheroEdgeLink, which is based on a multi-resolution approach. Results: In our population we had 150 subjects (prevalence of 40.5%) with evidence of coronary artery disease and the SXscore was 8.1 ± 14.4, whereas the mean CIMT (obtained by averaging the left and right side) was 0.86 mm ± 0.23 mm. The Pearson correlation analysis showed a statistically significant correlation between the CIMT and SXscore (r value = 0.323 ; p value = 0.0001). Using the ROC analysis for presence/absence of coronary artery diseases versus CIMT, we observed that the presence of CIMT of 1 mm is associated with the presence Coronary Artery Disease with a specificity of 90.52%. Conclusions: Results: of our study using the fully automated AtheroEdgeLink algorithm showed a statistical significant association between CIMT and SXscore. This association was demonstrated by applying an automated strategy to an image database of patients with different risk factors. From a clinical point of view, results indicate that automatically measured CIMT may be considered a reliable parameter to predict the SXscore.

Radiofrequency Ablation of Breast Neoplasms

Breast surgery maintains a central role in achieving local disease control in the management of breast cancer. After the introduction of radical mastectomy as a standard treatment technique, there has been a continuing shift toward decreasing the amount of tissue removed during surgery, especially for the treatment of small cancers. Breast conservative treatment has been increasingly used because it has demonstrated survival rates similar to those of the more radical treatments. These treatments also have the added advantage of resulting in a more-natural appearing breast after cosmetic surgery. In fact, the current standard treatment for T1N0M0 tumors is lumpectomy followed by radiation therapy.nnOver the past decade, a number of new, minimally invasive image-guided techniques have been developed that allow the insertion of needle-shaped devices into the tumor to completely and percutaneously destroy, or ablate, the cells using cold or heat. These techniques have demonstrated their efficacy and are being routinely used in the treatment of diverse tumors, especially in liver, kidney, lung, or bone.nnAblative techniques allow parenchyma-sparing treatment of tumors. In addition, in patients who are not candidates for surgery, percutaneous ablation allows local treatment with lower morbidity and mortality. Therefore, this approach could increase the number of patients who are candidates for treatment. Ablative techniques may be considered alone or in conjunction with resection. Radiofrequency (RF) ablation is the most widely used of these techniques.

Segmentation and Skeletonization of 3D Contrast Enhanced Ultrasound Images for the Characterization of Single Thyroid Nodule

The thyroid nodules are common findings in clinical practice. Recent studies demonstrated that thyroid nodules can be found in about 66% of the adult population. Nevertheless, only 5–7% of the thyroid nodules is malignant. In the presence of a suspicious nodule, thyroidectomy is performed. As a consequence, the patient will lack the thyroid hormones, which will be integrated by using drugs.

Automated Ocular Localization in Thermographic Sequences of Contact Lens Wearer

Nowadays, infrared (IR) imaging is widely used in the detection of breast cancer, eye abnormalities, impotency, and blood flow in the muscles. An algorithm to correctly localize the eye and cornea in IR thermogram of contact lenser using gradient vector flow (GVF) snake coupled with target tracking function was used in a sequence of thermogram images. The target tracking function helps to locate the eye automatically and increases the accuracy of detection. Genetic algorithm helps to identify the local minima in the target function. In this work, we have used 46 ocular thermographic sequence of normal contact lens wearer (aged from 16 to 20 years) and the proposed method is able to automatically identify correctly the eye and cornea with an accuracy of 92%.