Browsing by Author "Kumari, RS"

Now showing 1 - 2 of 2
  • Item
    A Genetic Algorithm Optimized Artificial Neural Network for the Segmentation of MR Images in Frontotemporal Dementia
    (SWARM, EVOLUTIONARY, AND MEMETIC COMPUTING, PT II (SEMCCO 2013), 2013) Kumari, RS; Varghese, T; Kesavadas, C; Singh, NA; Mathuranath, PS
    Frontotemporal Dementia (FTD) is an early onset dementia with atrophy in frontal and temporal regions. The differential diagnosis of FTD remains challenging because of the overlapping behavioral symptoms in patients, which have considerable overlap with Alzheimer's disease (AD). Neuroimaging analysis especially Magnetic Resonance Image Imaging (MRI) has opened up a new window to identify, and track disease process and progression. In this paper, we introduce a genetic algorithm (GA) tuned Artificial Neural Network (ANN) to measure the structural changes over a period of 1year. GA is a heuristic optimization method based on the Darwin's principle of natural evolution. The longitudinal atrophy patterns obtained from the proposed approach could serve as a predictor of impending behavioral changes in FTD subjects. The performance of our computerized scheme is evaluated and compared with the ground truth information. Using the proposed approach, we have achieved an average classification accuracy of 95.5 %, 96.5% and 98% for GM, WM and CSF respectively.
  • Item
    Longitudinal Evaluation of Structural Changes in Frontotemporal Dementia Using Artificial Neural Networks
    (PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON FRONTIERS OF INTELLIGENT COMPUTING: THEORY AND APPLICATIONS (FICTA) 2013, 2014) Kumari, RS; Varghese, T; Kesavadas, C; Singh, NA; Mathuranath, PS
    Automatic Segmentation of Magnetic Resonance (MR) Images plays an important role in medical image processing. Segmentation is the process of extracting the brain tissue components such as grey matter (GM), white matter (WM) and cerebrospinal fluids (CSF). The volumetric analysis of the segmented tissues helps in determining the amount of GM loss in specific disease pathology. Among the various segmentation techniques, fuzzy c means (FCM) is the most widely used one. The performance of traditional FCM is considerably reduces in noisy MR images. However, in the clinical analysis accurate segmentation of MR image is very important and crucial for the early diagnosis and prognosis. This paper put forward an Artificial Neural Network based segmentation to map the longitudinal structural changes overtime in Frontotemporal dementia (FTD) subjects that could be a better cue to impending behavioural changes. Our proposed approach has achieved an average classification accuracy of 96.7%, 96.4% and 97.96% for GM, WM and CSF respectively