Medical Image Compression Based on Combining Region Growing and Wavelet Transform
Elnomery Allam Zanaty,
Sherif Mostafa Ibrahim
Issue:
Volume 7, Issue 3, September 2019
Pages:
57-65
Received:
20 August 2019
Accepted:
17 September 2019
Published:
27 September 2019
Abstract: Medical data grows very fast and hence medical institutions need to store high volume of data about their patients. Medical images are one of the most important data types about patients. As a result, hospitals have a high volume of images that require a huge storage space and transmission bandwidth to store these images. Most of the time transmission bandwidth is not sufficient to storing and transmit all the image data with the required efficiency. Image compression is the process of encoding information using fewer bits than an un-encoded representation using specific encoding schemes. Compression is useful because it helps to reduce the consumption of expensive resources, such as storage space or transmission bandwidth (computing). In this paper, a medical image compression technique based on combining region growing and wavelets algorithms was introduced. A region growing algorithm is used to simply partitioning the image into two parts foreground and background depending on the intensity values. Then, wavelets methods applied on foreground regions including important regions. These regions are compressed lossless to keep the appearance of the image as intact while making the simplifications and the other region is lossy compressed to reduce the file size, leading to that the overall compression ratio gets better and the reconstructed image seems like the original one. To prove the capability of the proposed algorithm, different four image structures from X-Ray, Computed tomography CT and Magnetic resonance imaging MRI types are tested.
Abstract: Medical data grows very fast and hence medical institutions need to store high volume of data about their patients. Medical images are one of the most important data types about patients. As a result, hospitals have a high volume of images that require a huge storage space and transmission bandwidth to store these images. Most of the time transmiss...
Show More
The Utility of Diffusion Weighted Imaging and Dynamic Contrast Enhanced MRI Techniques in Differentiation Between Benign and Malignant Uterine Masses
Al-Shimaa Magdy Ammar,
Mohammed Mahmoud Dawoud,
Mohamed Mohamed Hefeda,
Manal Ezzat Badawy,
Essmat Hamdy Abozaid
Issue:
Volume 7, Issue 3, September 2019
Pages:
66-80
Received:
12 July 2019
Accepted:
15 August 2019
Published:
30 September 2019
Abstract: The aim of the present study was to evaluate the role of diffusion weighted imaging (DWI) and dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) in the differentiation between benign and malignant endometrial, uterine and cervical masses. The study included 78 patients. All patients had uterine or cervical masses on ultrasound examination. All patients had conventional MRI, DWI, and DCE-MRI. The patients were classified into three groups: patients with endometrial masses, myometrial lesions and cervical masses. The mean ADC value of benign endometrial and myometrial lesions was higher significantly from malignant lesions (P value <0.001 and <0.001). The cut off value of ≤1.1×10-3mm2/sec as a predictor of malignant lesions yielded a sensitivity, specificity, PPV, NPV and accuracy of 89.65%, 91.54%, 88.67%, 92.41% and 95.21% respectively. The semi-quanitative parameters of DCE-MRI including the enhancement amplitude (EA), maximum slope (MS) and time of half rising (THR), all showed significant difference between the benign and malignant lesion in endometrial, myometrial and cervical lesions. In clinically and sonographically indeterminate endometrial, myometrial or cervical masses, DWI and DCE-MRI proved to be more accurate than conventional MRI in differentiation between benign and malignant masses, with the DWI and ADC value had more sensitivity and specificity especially in endometrial masses and should be included in the routine pelvic MRI. DCE-MRI should be reserved for still questionable cases after DWI and to study the vascularity of the lesions.
Abstract: The aim of the present study was to evaluate the role of diffusion weighted imaging (DWI) and dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) in the differentiation between benign and malignant endometrial, uterine and cervical masses. The study included 78 patients. All patients had uterine or cervical masses on ultrasound examinati...
Show More
