Hypo and hyperthyroid disorder detection from thermal images using Bayesian Classifier

摘要

Nowadays thyroid gland disorder is very common disease. More than one third of all women may be found to have at least one thyroid nodule disorder during their lifetime. Thyroid detection test is usually done by invasive and non-invasive methods. Invasive methods like Thyroid Function Tests(TFTs), biopsy are traumatic methods and non-invasive methods like ultrasound and x-rays should not be used many time. TFT is a collective term for blood tests used to check the function of the thyroid. This is invasive method to detect thyroid gland disease. TFTs may be requested if a patient is thought to suffer from hyperthyroidism or hypothyroidism. This paper gives the state of the art of image processing techniques to detect the thyroid gland disease non- traumatically using Thermograph. Thermographs are the images taken by Thermal Imaging. Thermal Imaging is a technology that creates and analyses image by detecting the heat radiating from an object. We have proposed a system to detect the thyroid gland disease using thermograph. A hyperactive thyroid gland is a center of increased blood flow and chemical activity, so it is a center of heat production that can be detected by thermal sensing. Temperature can be sensed using thermal camera FLIRE30 with thermal sensitivity of 0.1°C with temperature range -20°C to +120°C. The images of the patients neck is captured by using thermal camera FLIR-E30. These images are filtered by using median filter, and enhanced by histogram equalization. The segmentation of the images is done done using Otsus Thresholding technique to extract the thyroid region from the image. Features are then extracted and thyroid images are classified in hypo and hyperthyroid using Bayesian Classifier.