Automatic generation of Regions Of Interest for Radionuclide Renograms
نویسنده
چکیده
Automatic generation of kidney regions of interest for radionuclide renograms is possible by defining a reference image and reference regions, using a non-linear image registration algorithm to map a totalised image from a patient to the reference image and using the mapping produced to map the predefined reference regions back onto the patient image. The accuracy of the automatically derived regions is evaluated by comparison with regions drawn independently by experienced operators. The median success factors, a measure of the overlap between automatic and manual regions, over 49 kidneys was 0.95 and the average linear displacement between the boundaries of the automatic and manual regions was 0.43 in units of pixel dimensions.
منابع مشابه
CONTINUING EDUCATION Computer Processing Methods for Nuclear Medicine Images
Objective: This review is a discussion of computer processing methods for modern nuclear medicine images. Methods: Basic image processing and quantification techniques are described, and their application to specific nuclear medicine studies is presented. Generation and use of regions of interest, time-activity curves, tomographic reconstruction and oblique reformatting are all addressed, as we...
متن کاملSalient regions detection in satellite images using the combination of MSER local features detector and saliency models
Nowadays, due to quality development of satellite images, automatic target detection on these images has been attracted many researchers' attention. Remote-sensing images follow various geospatial targets; these targets are generally man-made and have a distinctive structure from their surrounding areas. Different methods have been developed for automatic target detection. In most of these met...
متن کاملPrognostic value of radioisotope renograms in kidney transplantation.
function of kidney transplants in man and experi mental animals (1—8).This study is a valuable aid for diagnosing the rejection reaction, especially if serial renograms are made (3,4,6,8). Nevertheless, little emphasis has been given to evaluating the prognostic significance of serial renograms in the rejection reaction. This report presents an evaluation of the prognos tic application of ser...
متن کاملAutomating Medical Diagnosis in Renal Scintigrams Using Rbf Networks
In thi paper we present a novel method for automatic detection of the Renals ROI, automat c detection of the dynamic Renograms excluding the pelv area, and the pathological Renograms are detected using RBF neural networks. The proposed diagnost c system was evaluated using 485 scin graphic files. The experimen al results g ve classification error less than 4.2%, with 96.9% sensitivity and 95.5%...
متن کاملImprovement of generative adversarial networks for automatic text-to-image generation
This research is related to the use of deep learning tools and image processing technology in the automatic generation of images from text. Previous researches have used one sentence to produce images. In this research, a memory-based hierarchical model is presented that uses three different descriptions that are presented in the form of sentences to produce and improve the image. The proposed ...
متن کامل