Improvement of Sonographic Appearance Using HAT-TOP Methods (original) (raw)
Related papers
Enhancement of Ultrasound Images using Top-hat and Blind Deconvolution Algorithms
Enhancement of Ultrasound Images using Top-hat and Blind Deconvolution Algorithms, 2014
Ultrasound imaging is an incontestable vital tool for diagnosis, it provides in non-invasive manner the internal structure of the body to detect eventually diseases or abnormalities tissues. Unfortunately, the presence of speckle noise in these images affects edges and fine details which limit the contrast resolution and make diagnostic more difficult. The main objective of this paper was to study the enhancement of ultrasound image using filtering technique. The data analyzed by using MatLab program to enhance the contrast within the soft tissues, the gray levels in both enhanced and unenhanced images and noise variance. The main techniques of enhancement used in this study were Top-hat filtering and Deblurring Images Using the Blind Deconvolution Algorithm. In this paper, prominent constraints are firstly preservation of image's overall look; secondly preservation of the diagnostic content in the image and thirdly detection of small low contrast details in diagnostic content of the image.
Automatic image quality assessment and measurement of fetal head in two-dimensional ultrasound image
Journal of medical imaging (Bellingham, Wash.), 2017
Owing to the inconsistent image quality existing in routine obstetric ultrasound (US) scans that leads to a large intraobserver and interobserver variability, the aim of this study is to develop a quality-assured, fully automated US fetal head measurement system. A texton-based fetal head segmentation is used as a prerequisite step to obtain the head region. Textons are calculated using a filter bank designed specific for US fetal head structure. Both shape- and anatomic-based features calculated from the segmented head region are then fed into a random forest classifier to determine the quality of the image (e.g., whether the image is acquired from a correct imaging plane), from which fetal head measurements [biparietal diameter (BPD), occipital-frontal diameter (OFD), and head circumference (HC)] are derived. The experimental results show a good performance of our method for US quality assessment and fetal head measurements. The overall precision for automatic image quality assess...
Procedia Computer Science, 2019
In recent years, a considerable advancement can be seen in medical image examination. The proposed work implements a Hybrid-Scheme (HS) to determine the Fetal-Head-Circumference (FHC) section from the chosen Two-Dimensional Ultrasound Image (2DUI). Normally, the 2DUI analysis is widely implemented to supervise the development of the fetus. This study implements a combination of an image pre-processing plus post-processing practice to mine FHC from the 2DUI. This preprocessing implements the Jaya-Algorithm (JA) and Otsu's threshold and post-processing implements Chan-Vese (CV) and Level-Set (LS) segmentation. In this work, FHC extraction process is performed with and without pre-processing procedure. After extracting the head section from the chosen 2DUI, the supremacy of executed tool is next appraised by employing a qualified study between mined region and its associated ground-truth. Further, the Haar features are extracted and its values are later evaluated with the ground-truth picture. The results of experimental work substantiate that, the hybrid procedure is capable in examining the 2DUI and offers enhanced picture similarity measures (>88.5%) during the FHC examination.
A Conceptual Framework for Fetus Head Analysis Based on Ultrasound Images
Studies in Health Technology and Informatics
Ultrasound images are the most used imaging methodologies in obstetrics to monitor the growth of a fetus during the gestation period. In particular, the obstetrician uses fetus head images to monitor the growth state and identify essential features such as Gestational age (GA), estimated fetus weight (EFW), and brain anatomical structures. However, this work requires an expert obstetrician, and it is time-consuming and costly. Therefore, we proposed an automatic framework by adopting a hybrid approach that combines three components i) automatic segmentation to segment the region of interest (ROI) in the fetus head, ii) measurement extraction to measure the segmented ROI, and iii) anomaly and features detection to predict fetus GA, EFW, and abnormality status.
Implementation of image segmentation on foetus ultrasound imaging system
2012 IEEE Global High Tech Congress on Electronics, 2012
Obstetrics ultrasound scan has been a vital routine for a pregnant mother to get information on the foetus dating and growth. Foetus ultrasound image is normally not clear and contains unwanted noise. Furthermore, the displayed foetus scan on the monitor screen can be not in complete stationary because of the slight movement of the held ultrasound probe. Thus, a computerized method to do segmentation on the foetus image should be implemented. To obtain precise measurements, obstetrician needs to freeze the best possible scene throughout the scanning session. With the segmentation technique implemented, the point locations for measurement can be generated without the participation of the obstetrician. In this paper, the applied segmentation technique is variational level set algorithm. Based on the segmentation results, the level set contour evolved well on the ultrasound image although it is low in contrast and contains image noise.
IAEME PUBLICATION, 2020
Ultrasound images are used to provide information about fetal development in the womb. The image generated by the two-dimensional ultrasound has not been able to provide complete information. Therefore, in order to get the form of fetus on ultrasound image can be clearly identified with the necessary process of image analysis that can detect the boundaries of objects ROI, so that it can differentiate between one object with another object on the ultrasound image. In this paper, we explore a new local feature extraction technique pyramid histogram of oriented gradients (PHOG) to make simple, fast and high performance. PHOG can describe the local shape of the image and its relationship between the spaces. The using of PHOG algorithm to extract image features in image recognition and retrieval and other aspects have achieved good results.
Enrichment of Ultrasound Images using Contrast Enhancement Techniques
Ultrasound is one of the diagnostic equipments to diagnose human internal organs, tendons, to capture their size and structure. Ultrasound is usually used for pregnancy, as the images for others' internal organs that are not very clear. The main objective of this paper was to study the enhancement of ultrasound image using filtering technique. The data analyzed by using MatLab program to enhance the contrast within the soft tissues, the gray levels in both enhanced and unenhanced images and noise variance. The main techniques of enhancement used in this study were Top-hat filtering and Deblurring Images Using the Blind Deconvolution Algorithm. In this paper, prominent constraints are firstly preservation of image's overall look; secondly preservation of the diagnostic content in the image and thirdly detection of small low contrast details in diagnostic content of the image.
Ultrasound in Medicine & Biology, 1997
We have developed a tool to automatically detect inner and outer skull boundaries of a fetal head in ultrasound images. These boundaries are used to measure biparietal diameter (BPD) and head circumference (HC ) . The algorithm is based on active contour models and takes 32 s on a Sun SparcStation 20171. A high-performance desktop multimedia system called MediaStation 5000 (MSSOOO) is used as a model for onr future ultrasound subsystem. On the MSSOOO, the optimized implementation of this algorithm takes 24g ms. The difference (between the computer-measured values on MS50@0 and the gold standard) for BPD and HC was 1.43% (a = 1.00%) and 1.96% (a = l.%%), respectively. According to our data analysis, no significant differences exist in the BPD and HC measurements made on the MS5@00 and those measurements made on the Sun SparcStation 20171. Reduction in the overall execution time from 32 s to 248 ms will help making this algorithm a practical ultrasound tool for sonographers. 0 1997 World Federation for Ultrasound in Medicine and Biology.
Despeckling of Ultrasound Medical Images using DW and WP Transform Techniques
The existences of noise in the medical images impose misleading of diagnostic processes, because of the radiation problem while acquiring images. The medical images mostly affected by the speckle noise over other natural noises. There are number of noise removal techniques for speckle noise is proposed in both spatial and frequency domain. In this paper, we propose a frequency domain method using wavelet based noise removal technique to remove speckle noise that exists in the ultrasound images. Moreover, we have implemented two different methods in terms of decomposing the images. We used Discrete Wavelet Transform (DWT) and Wavelet Packet Transform (WPT) for decompose the images. For comparative analysis, the performance of these filtering techniques is quantitatively evaluated through Peak Signal to Noise Ratio (PSNR). Keyword-Speckle Noise, Ultrasound Image, Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT). I. INTRODUCTION In the medical imaging field, the noises occurring in the images are a crucial issue that leads to faulty decision during the patient diagnostics processes. There are variety of noise removal techniques also exists for mixed noises [1]. Noise removal techniques are constructed through spatial or frequency domain. Spatial filtering is nothing but the filtering operations that are performed directly on the intensity of the pixels [2]. It works by simply moving the kernel (i.e. filter mask) throughout the image from point to point. It mainly classified into smoothing, order-statistics and sharpening filtering. Ultrasound is one of the low cost medical imaging modality with simpler operations and so that used widely. High frequency sound waves are used to capture the inner organs [3]. The ultrasound image is produced by the reflection of the waves from the body structures. The amplitude of the signal and time taken for the wave to travel through the body are the two main factors to construct an ultrasound image. Moreover, ultrasound is a sound wave with frequencies higher than the upper audible limit of human hearing. The frequencies that operated in ultrasound devices are ranges from 20 kHz up to several gigahertz. Health care professionals uses ultrasound images to view the internal organs. During pregnancy, doctors are uses ultrasound to view the fetus, because it does not expose any radiation like other modalities. The noise occurrence in this modality is a big problem that occurs due to the value of the clear nature of the trend transferring [4]. These noises corrupt the images and often lead to incorrect diagnosis [5]. Medical imaging modalities are affected by different types of noises especially the ultrasound images are mainly affected by speckle noise. Speckle is a granular noise that exists inherently and it degrades the quality of the images such as synthetic aperture radar (SAR), medical ultrasound and optical coherence tomography images [6]. Reducing these speckle noise from a noisy image is the complicated step in medical image processing. Speckle noise degrades image quality with a backscattered wave appearance which originates from many sources like microscopic spreader reflections that pass through internal organs. It makes much difficulty for the observer to discriminate fine detail of the images while diagnostic processes. Thus, denoising or reducing these speckle noise from a noisy image has become the predominant step in medical field. Some spatial domain filtering techniques are existing for removing noises [7]. Ultimately, the speckle noise addresses the contrast related problems on images. So, there is great need to construct a denoising method to remove the speckle [8]. In this paper, we experimented the ultrasound images which are affected by speckle noise for denoising. A wavelet based image filtering technique is applied to ultrasound images which effectively remove the noises. In addition, the performance of aforementioned filters is compared (in terms of PSNR) and discussed in the following sections. This paper is further organized as follows: Section 2 contains the brief introduction about the Discrete Wavelet Transform (DWT) and Wavelet Packet Transform (WPT), our proposed method is explained in section 3, the results and discussion included in section 4 and we conclude our paper in section 5.
Detection of abnormalities in Fetus using Medical Image Processing
IRJET, 2022
Fetal MRI volumetry is a valuable method yet it is restricted by a reliance upon movement free sweeps, monotonous manual division, and spatial error because of thick slice checks. A picture handling pipeline that locations these impediments was created and tested. The chief successions gained in fetal MRI clinical practice are different symmetrical single-shot quick twist reverberation checks. Cutting edge picture handling methods were utilized for between cut movement adjustment also, super-goal recreation of high-goal volumetric pictures from these outputs. The recreated volume pictures were processed with force non-consistency amendment furthermore, the fetal mind removed by utilizing directed robotized segmentation. Reconstruction, division and volumetry of the fetal cerebrums for a partner of 25 clinically procured fetal MRI filters was finished. Execution measurements for volume reproduction, division and not entirely set in stone by contrasting with manual drawings in five arbitrarily picked cases. At long last, examination of the fetal mind and parenchymal volumes was performed in view of the gestational age of the babies. The picture handling pipeline created in this study empowers volume delivering and precise fetal cerebrum volumetry by tending to the impediments of current volumetry methods, which remember reliance for movement free filters, manual division, and erroneous thick-cut insertion.