Automated segmentation using PCA and area estimation of thyroid gland using ultrasound images

Thyroid is a hormone secreting gland which influences all metabolic activities in our body. The production of hormone is regulated by the feedback loop between the hypothalamus, pituitary -gland and thyroid gland. The most common thyroid problems involve over production of thyroid hormones is said to be hyperthyroidism. Insufficient hormone production leads to hypothyroidism. Thyroid gland area varies with age, sex and production of hormone inbalance. This gland area can be estimated with an accuracy and gives effective result in diagnosis. The CAD system employs automatic segmentation of thyroid gland based on principle component analysis and morphological processess. The area of the thyroid gland is measured by using matlab. The segmentation process will be applied for the input image for the detection of gland region. The ROI based clustering is used here for effective segmentation to diagnose the tumour part. The morphological process will be used to avoid distortion from background and smoothing the region. This proposed method will reduce the errors caused due to manual analysis, time consuming, inaccurate and also eliminate the need of intensive trained person´s in order to avoid diagnostic errors.