Wavelet transform (WT) is a commonly used method for noise suppression and feature extraction from biomedical images. The selection of WT system settings significantly affects the efficiency of denoising procedure. This comparative study analyzed the efficacy of the proposed WT system on real 292 ultrasound images from several areas of interest. The study investigates the performance of the system for different scaling functions of two basic wavelet bases, Daubechies and Symlets, and their efficiency on images artificially corrupted by three kinds of noise. To evaluate our extensive analysis, we used objective metrics, namely structural similarity index (SSIM), correlation coefficient, mean squared error (MSE), peak signal-to-noise ratio (PSNR) and universal image quality index (Q-index). Moreover, this study includes clinical insights on selected filtration outcomes provided by clinical experts. The results show that the efficiency of the filtration strongly depends on the specific wavelet system setting, type of ultrasound data, and the noise present. The findings presented may provide a useful guideline for researchers, software developers, and clinical professionals to obtain high quality images.
The paper deals with the segmentation of the retinal vascular system using hybrid methods as morphological operations for the purpose of highlighting the extraction of blood vessels and tortuosity. Up to now tortuosity has been evaluated through a visual comparison of the retinal images. The output is an extracted retinal binary image with a blood vessel map. For this reason, a model was suggested that can automatically indicate the tortuosity of the retinal blood vessels by setting a threshold of the blood vessel curvature. This paper used a dataset of images (2800 images) from a RetCam3 device. Before applying the image processing, 30 images were selected with pre-plus diseases diagnosed, and this was divided into two groups with low contrast and higher contrast images. Part of the work is to determine the level of the tortuosity symptom by setting a threshold. Comparing the results with this processing method is not possible because the reference methods of image processing are based on fundus camera scanning, which has twice the resolution. This camera is not used for premature babies, but for children about one year of age and older or adults. Thus, retinal data for 14-day-old to 1-year-old children are not available for the fundus camera. This is a pilot study for the segmentation and mapping of blood vessels from retinal images taken by RetCam3.
- MeSH
- cévní malformace diagnóza MeSH
- diagnostické zobrazování MeSH
- lidé MeSH
- nemoci nedonošenců diagnóza MeSH
- novorozenec MeSH
- retina patologie MeSH
- retinální cévy * patologie MeSH
- Check Tag
- lidé MeSH
- novorozenec MeSH
- Publikační typ
- práce podpořená grantem MeSH
