Font Size: a A A

Registration Of SPECT Image And B-type Ultrasound Image Based On Artificial Bee Colony Algorithm

Posted on:2016-11-09Degree:MasterType:Thesis
Country:ChinaCandidate:L L GuoFull Text:PDF
GTID:2308330479978094Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
With the popularization of medical and the improvement of clinical diagnostic technology, the incidence of thyroid nodule gradually increased. Most thyroid nodules are benign, only a few for malignant tumor. Due to the different of the treatment and prognosis,identification of benign and malignant thyroid nodule is particularly important. B-type ultrasound can clearly show that subtle changes, discovery rate of thyroid nodules is high,accurate positioning, but not sure of benign and malignant thyroid nodules. SPECT imaging is functional imaging, can according to the distribution of radioactivity in the glands,providing of benign and malignant lesions and the function of the close relationship between the images, but to the positioning of the nodules are inaccurate. In order to solve this problem, proposed to thyroid SPECT image and B-type ultrasound image registration and fusion. This paper mainly studies the registration of the thyroid SPECT image and B-type ultrasound image, in preparation for fusion of the two kinds of pattern images.SPECT image doesn’t have a visible segmentation boundary, while B-type ultrasound image is characterized by speckle noise and low contrast. The two images have quite different pixels, which means the registration method based on gray level will result in great error. We use the KFCM method as the segmentation of SPECT image, the GCBAC and NSCT method is proposed as the segmentation of B-type ultrasound image. And then areas are filled as binary images to prepare for the thyroid image registration.The paper selects the mutual information as the similarity measure, and the greater of the mutual information, the higher of the registration accuracy. According to the criterion,the yield degree function of artificial colony algorithm is improved, and the improved artificial colony algorithm is applied to the registration of thyroid images. The experimental results show that the improved artificial colony algorithm is applied to the thyroid registration of SPECT image and B-type ultrasound image comes to good effect.
Keywords/Search Tags:thyroid tumor, SPECT image, B-type ultrasound image, GCBAC, NSCT, image registration, artificial colony algorithm
PDF Full Text Request
Related items