An automated segmentation technique for the processing of foot ultrasound images
02 Apr 2013-pp 380-383
TL;DR: This work aimed at developing a novel method for image processing in order to achieve automated segmentation of ultrasound images of the plantar soft tissue and took into account the difficulty of visualization of the tissues and bony structures in the foot.
Abstract: In spite of the advantages of ease of imaging and low acquisition cost, ultrasound images are noisier and have poorer image quality than other imaging modalities like CT or MRI and hence require an experienced clinician for interpretation. Processing by automated segmentation assists clinicians and improves the accuracy of assessment by minimizing its subjective nature. Various methods for the segmentation of ultrasound images exist, but there is not much literature on the processing of 2D ultrasound images of the foot. This work aimed at developing a novel method for image processing in order to achieve automated segmentation of ultrasound images of the plantar soft tissue. Preprocessing of the ultrasound images was performed using the anisotropic diffusion filter followed by contrast enhancement. The Chan-Vese active contour method was used for segmentation. Our method took into account the difficulty of visualization of the tissues and bony structures in the foot and used an additional curvature parameter for segmentation. Assessing the changes in the biomechanical properties of the plantar soft tissue can be a potential application of this method especially in case of the diabetic foot.
Citations
More filters
TL;DR: An automatic segmentation approach is proposed which for the first time extracts ultrasound data to estimate size across three sections of the PF (rearfoot, midfoot and forefoot) and is capable of accurately segmenting the PF region, differentiating it from surrounding tissues and estimating its thickness.
14 citations
01 Dec 2016
TL;DR: This method firstly deals with uneven illumination of ultrasound image, which makes the brightness of liver region in images to be consistent, and the Fuzzy C Mean (FCM) method using the priori shape information, which is called FCM_I, is proposed to segment the image.
Abstract: Ultrasonic examination is a routine inspection technology. It has several merits, such as no harm to human body, cheap and relative high precision inspection. So it is widely used in physical examination and various types of organ inspections. In order to increase the detection rate of liver disease in ultrasound images, a method extracting the liver region from ultrasound images is proposed in this paper. This method firstly deals with uneven illumination of ultrasound image, which makes the brightness of liver region in images to be consistent. Then, in order to better resist the noise, the Fuzzy C Mean (FCM) method using the priori shape information, which is called FCM_I, is proposed to segment the image. Finally, according to the distribution and shape of the liver, the largest foreground area in the image is obtained. The proposed method obtains good results in the abdominal ultrasound images obtained by the hospital.
2 citations
Additional excerpts
...[3] improved the quality of ultrasound images by using anisotropic diffusion filter....
[...]
TL;DR: The bone segmentation in ultrasound images is utilized in several applications of computer-aided surgery and is the challenging task in recent years in image processing.
Abstract: Segmentation of the bone surface in ultrasound images are utilized in several applications of computer-aided surgery. In image processing, the bone segmentation is the challenging task in recent da...
1 citations
09 Nov 2016
TL;DR: The proposed method firstly smoothes the images by using mean shift, which makes the brightness of the whole liver region to be consistent, and the Fuzzy C Mean (FCM) method is used for obtaining the main part of liver region and brightness compensation is applied around the main parts.
Abstract: Ultrasonic examination is widely used in physical examination and various types of organ inspections because of its merits, such as no harm to human body, cheap and relative high precision. In this paper, a method is proposed to extract liver region in ultrasound images for better liver disease detection. The proposed method firstly smoothes the images by using mean shift, which makes the brightness of the whole liver region to be consistent. Then, the Fuzzy C Mean (FCM) method is used for obtaining the main part of liver region and brightness compensation is applied around the main part. Finally, image segmentation is realized by FCM and the largest foreground area in the image is segmented as the result according to the distribution and shape of the liver. The proposed method has satisfactory results in the experiment of the abdominal ultrasound image segmentation.
1 citations
References
More filters
TL;DR: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced, chosen to vary spatially in such a way as to encourage intra Region smoothing rather than interregion smoothing.
Abstract: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced. The diffusion coefficient is chosen to vary spatially in such a way as to encourage intraregion smoothing rather than interregion smoothing. It is shown that the 'no new maxima should be generated at coarse scales' property of conventional scale space is preserved. As the region boundaries in the approach remain sharp, a high-quality edge detector which successfully exploits global information is obtained. Experimental results are shown on a number of images. Parallel hardware implementations are made feasible because the algorithm involves elementary, local operations replicated over the image. >
12,560 citations
"An automated segmentation technique..." refers background or methods in this paper
...The anisotropic diffusion filter [7], the image is convolved with a Gaussian kernel....
[...]
...Speckle was reduced by the anisotropic diffusion filter [7]....
[...]
TL;DR: A new model for active contours to detect objects in a given image, based on techniques of curve evolution, Mumford-Shah (1989) functional for segmentation and level sets is proposed, which can detect objects whose boundaries are not necessarily defined by the gradient.
Abstract: We propose a new model for active contours to detect objects in a given image, based on techniques of curve evolution, Mumford-Shah (1989) functional for segmentation and level sets. Our model can detect objects whose boundaries are not necessarily defined by the gradient. We minimize an energy which can be seen as a particular case of the minimal partition problem. In the level set formulation, the problem becomes a "mean-curvature flow"-like evolving the active contour, which will stop on the desired boundary. However, the stopping term does not depend on the gradient of the image, as in the classical active contour models, but is instead related to a particular segmentation of the image. We give a numerical algorithm using finite differences. Finally, we present various experimental results and in particular some examples for which the classical snakes methods based on the gradient are not applicable. Also, the initial curve can be anywhere in the image, and interior contours are automatically detected.
10,404 citations
"An automated segmentation technique..." refers methods in this paper
...The choice of the Chan-Vese active contour model is based on the fact that it is not edge dependent segmentation [8]....
[...]
...Segmentation Segmentation was based on the Chan-Vese active contour model [8]....
[...]
...The Heaviside function is regularized in the following manner in order to detect global minima rather than only local minima and also to detect interior boundaries [8]....
[...]
TL;DR: A fully automatic method for luminal contour segmentation in intracoronary ultrasound imaging is introduced, based on a contour with a priori properties that evolves according to the statistics of the ultrasound texture brightness, which is generally Rayleigh distributed.
Abstract: In this paper, a fully automatic method for luminal contour segmentation in intracoronary ultrasound imaging is introduced. Its principle is based on a contour with a priori properties that evolves according to the statistics of the ultrasound texture brightness, which is generally Rayleigh distributed. The main interest of the technique is its fully automatic character. This is insured by an initial contour that is not set by the user, like in classical snake-based algorithms, but estimated and, thus, adapted to each image. Its estimation combines two pieces of information extracted from the a posteriori probability function of the contour position: the function maximum location (or maximum a posteriori estimator) and the first zero-crossing of its derivative. Then, starting from the initial contour, a region of interest is automatically selected and the process iterated until the contour evolution can be ignored. In vivo coronary images from 15 patients, acquired with the 20-MHz central frequency Jomed Invision ultrasound scanner, were segmented with the developed method. Automatic contours were compared to those manually drawn by two physicians in terms of mean absolute difference. The results demonstrate that the error between automatic contours and the average of manual ones is of small amplitude, and only very slightly higher (0.099/spl plusmn/0.032 mm) than the interexpert error (0.097/spl plusmn/0.027 mm).
149 citations
01 Oct 2006
TL;DR: Experimental results show that the proposed method for biomedical ultrasound image segmentation based on watershed transformation can produce accurate contours in medical ultrasound images.
Abstract: This paper presents an efficient method for biomedical ultrasound image segmentation based on watershed transformation. It consists of four major stages. These stages are pre-processing, multiscale morphological gradient, watershed segmentation and finally region merging. The proposed scheme is tested using a set of medical ultrasound images. Experimental results show that our proposed method can produce accurate contours in medical ultrasound images.
11 citations
"An automated segmentation technique..." refers background in this paper
...Watershed segmentation [3] results in over segmentation if sufficient region merging is not performed....
[...]
TL;DR: An algorithm consisting of speckle reduction by median filtering, contrast enhancement using top- and bottom-hat morphological filters, and segmentation with a discrete dynamic contour (DDC) model was implemented for nondestructive measurements of soft tissue layer thickness, and modest variability provides confidence in the thickness measurements.
Abstract: An algorithm consisting of speckle reduction by median filtering, contrast enhancement using top- and bottom-hat morphological filters, and segmentation with a discrete dynamic contour (DDC) model was implemented for nondestructive measurements of soft tissue layer thickness. Algorithm performance was evaluated by segmenting simulated images of three-layer phantoms and high-frequency (40 MHz) ultrasound images of porcine aortic valve cusps in vitro. The simulations demonstrated the necessity of the median and morphological filtering steps and enabled testing of user-specified parameters of the morphological filters and DDC model. In the experiments, six cusps were imaged in coronary perfusion solution (CPS) then in distilled water to test the algorithm's sensitivity to changes in the dimensions of thin tissue layers. Significant increases in the thickness of the fibrosa, spongiosa, arid ventricularis layers, by 53.5% (p < 0.001), 88.5% (p < 0.001), and 35.1% (p = 0.033), respectively, were observed when the specimens were submerged in water. The intraobserver coefficient of variation of repeated thickness estimates ranged from 0.044 for the fibrosa in water to 0.164 for the spongiosa in CPS. Segmentation accuracy and variability depended on the thickness and contrast of the layers, but the modest variability provides confidence in the thickness measurements.
9 citations
"An automated segmentation technique..." refers background or methods in this paper
...This is followed by contrast enhancement using morphological transforms [6]....
[...]
...Discrete dynamic contour is similar to the active contour with respect to the movement of the initial contour ideally to the boundary of the structure [6]....
[...]