Snake Algorithm Research Articles

Computerized segmentation and characterization of breast lesions in dynamic contrast-enhanced MR images using fuzzy c-means clustering and snake algorithm.

This paper presents a novel two-step approach that incorporates fuzzy c-means (FCMs) clustering and gradient vector flow (GVF) snake algorithm for lesions contour segmentation on breast magnetic resonance imaging (BMRI). Manual delineation of the lesions by expert MR radiologists was taken as a reference standard in evaluating the computerized segmentation approach. The proposed algorithm was also compared with the FCMs clustering based method. With a database of 60 mass-like lesions (22 benign and 38 malignant cases), the proposed method demonstrated sufficiently good segmentation performance. The morphological and texture features were extracted and used to classify the benign and malignant lesions based on the proposed computerized segmentation contour and radiologists' delineation, respectively. Features extracted by the computerized characterization method were employed to differentiate the lesions with an area under the receiver-operating characteristic curve (AUC) of 0.968, in comparison with an AUC of 0.914 based on the features extracted from radiologists' delineation. The proposed method in current study can assist radiologists to delineate and characterize BMRI lesion, such as quantifying morphological and texture features and improving the objectivity and efficiency of BMRI interpretation with a certain clinical value.

설진 유효 분석을 위한 혀의 기하정보 추출 방법

In Oriental medicine, the status of a tongue is the important indicator to diagnose the condition of internal organs in a body. A tongue diagnosis is not only convenient but also non-invasive, and therefore widely used in Oriental medicine. But tongue diagnosis has some problems that should be objective and standardized, it also exhaust the diagnosis tool that can help for oriental medicine doctor`s decision-making. In this paper, to solve the this problem we propose a method that calculates the tongue geometry information for effective tongue diagnosis analysis. Our method is to extract the tongue region for using improved snake algorithm, and calculates the geometry information by using convex hull and In-painting. In experiment, our method has stable performance as 7.2% by tooth plate and 8.5% by crack in region difference ratio.

Segmentation of cam-type femurs from CT scans

We introduce a new way to accurately segment cam-type pathological femurs from pelvic CT scans. The femur is a difficult target for segmentation due to its proximity to the acetabulum, irregular shape and the varying thickness of its hardened outer shell. In addition, the pathological femurs with femoral-acetabular impingements have a non-standard shape, which increases segmentation difficulty. We overcome these difficulties by (a) dividing the femur into two rounds of segmentation—one for the femur head and another for the body—(b) pre-processing the CT scan to reduce anatomical sources of error (c) two modes of segmentation—a rough estimation of a contour and another for fine contours. Segmentations of the CT volume are performed iteratively, on a slice-by-slice basis and contours are extracted using the morphological snake algorithm. Our methodology was designed to require little initialization from the user and to deftly handle the large variation in femur shapes, most notably from deformations attributed to cam femoral–acetabular impingements. Our efforts are to provide physicians with a new tool that creates patient-specific and high-quality 3D femur models while requiring much less time and effort. Femur models segmented with our method had an average volume overlap error of 2.71±0.44% and symmetric surface distance of 0.28±0.04 mm compared to ground truth models.

Texture Feature Analysis for Breast Ultrasound Image Enhancement

Texture analysis of breast ultrasound B-scans has been widely applied to the segmentation and classification of breast tumors. We present a parametric imaging method based on the texture features to preserve tumor edges and retain the texture information simultaneously. Four texture-feature parameters--homogeneity, contrast, energy and variance--were evaluated using the gray-level co-occurrence matrix. The local texture-feature parameter was assigned as the new pixel located at the center of the sliding window at each position. This process yielded the texture-feature parametric image as the map of texture-feature values. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were estimated to show the quality improvement of the images. The contours outlined from 11 experienced physicians and the gradient vector flow (GVF) snake algorithm segmentations were adopted to verify the edge enhancement of texture-feature parametric images. In addition, the Fisher's linear discriminant analysis (FLDA) and receiver-operating-characteristic (ROC) curve were used to test the performance of breast tumor classifications between texture-feature parametric images and B-scan images. The results show that the variance images have higher CNR and SNR estimates than those in the B-scan images. There was a high agreement between the physician's manual contours and the GVF snake automatic segmentations in the variance images, and the mean area overlap was over 93%. The area under the ROC curve from the B-scan images had 0.81 and 95% confidence interval of 0.72-0.88, and the texture-feature parametric images had 0.90 and 95% confidence interval of 0.84-0.96. These findings indicate that the texture-feature parametric imaging method can be not only useful for determining the location of the lesion boundary but also as a tool to improve the accuracy of breast tumor classifications.

A Fast Snake Algorithm for Tracking Multiple Objects

A Snake is an active contour for representing object contours. Traditional snake algorithms are often used to represent the contour of a single object. However, if there is more than one object in the image, the snake model must be adaptive to determine the corresponding contour of each object. Also, the previous initialized snake contours risk getting the wrong results when tracking multiple objects in successive frames due to the weak topology changes. To overcome this problem, in this paper, we present a new snake method for efficiently tracking contours of multiple objects. Our proposed algorithm can provide a straightforward approach for snake contour rapid splitting and connection, which usually cannot be gracefully handled by traditional snakes. Experimental results of various test sequence images with multiple objects have shown good performance, which proves that the proposed method is both effective and accurate.

Automated Karyotyping of Metaphase Cells with Touching Chromosomes

Since the birth of the automated karyotyping systems by the aid of computers, building a fully automated chromosome analysis system has been an ultimate goal. Along with many other challenges, automating chromosome classification and segmentation has been a major challenge especially due to overlapping and touching chromosomes. The earlier reported methods have limited success as they are sensitive to scale variations, computationally complex, use only color information in case of multispectral imaging and had challenges in segmentation. The proposed technique addresses the challenge of separating the touching chromosomes using initially the modified snake algorithm to disentangle the cluster of touching chromosomes from the metaphase image and then a greedy approach based on combinatorial computational geometry of the pixels on the boundary of the cluster is used to identify and resolve the set of touching chromosomes. Contribution and novelty of this work lies in the ability of the algorithm to successfully separate the clusters of any number of touching chromosomes. System performance was tested and analyzed using a variety of metaphase images exhibiting various levels of touching chromosomes giving an overall accuracy of 100 % for resolving the cluster with 2 touching chromosomes and 95 % for separating a cluster of 3, 4 touches. The overall time was 2.4 seconds.

Semi‐automatic delineation using weighted CT‐MRI registered images for radiotherapy of nasopharyngeal cancer

To develop a delineation tool that refines physician-drawn contours of the gross tumor volume (GTV) in nasopharynx cancer, using combined pixel value information from x-ray computed tomography (CT) and magnetic resonance imaging (MRI) during delineation. Operator-guided delineation assisted by a so-called "snake" algorithm was applied on weighted CT-MRI registered images. The physician delineates a rough tumor contour that is continuously adjusted by the snake algorithm using the underlying image characteristics. The algorithm was evaluated on five nasopharyngeal cancer patients. Different linear weightings CT and MRI were tested as input for the snake algorithm and compared according to contrast and tumor to noise ratio (TNR). The semi-automatic delineation was compared with manual contouring by seven experienced radiation oncologists. A good compromise for TNR and contrast was obtained by weighing CT twice as strong as MRI. The new algorithm did not notably reduce interobserver variability, it did however, reduce the average delineation time by 6 min per case. The authors developed a user-driven tool for delineation and correction based a snake algorithm and registered weighted CT image and MRI. The algorithm adds morphological information from CT during the delineation on MRI and accelerates the delineation task.

Computer-Assisted Diagnosis of Tuberculosis: A First Order Statistical Approach to Chest Radiograph

Textural properties of normal and tuberculosis posterior-anterior chest radiographs were looked into in this investigation. The proposed computerized scheme segmented the lung field of interest using a user-guided snake algorithm and extracted the corresponding pixel data. For both normal and tuberculosis radiographs, the grayscale intensity distribution within the region of interest was analyzed to study their respective characteristics, and fed to classifiers for automated classification. Statistically the tuberculosis infected radiographs manifested a higher variance, third moment, entropy and a lower mean value in their intensity distributions, compared to their normal peers. The greater disparities between a particular radiograph and the confidence interval determined by our normal groups on some of the features were observed to be related to the level of haziness at the upper lobe. Lastly, the C4.5 (a decision tree based classifier)-adaboost achieved an accuracy of 94.9% in normal-tuberculosis classification. An integrated index, called tuberculosis index (TI), is proposed based on texture features to discriminate normal and tuberculosis chest radiographs using just one index or number. We hope this TI can be used as an adjunct tool by the radiographers in their daily screening.

Automated volumetric assessment of the Achilles tendon (AVAT) using a 3D T2 weighted SPACE sequence at 3T in healthy and pathologic cases

Achilles tendinopathy has been reported to be frequently associated with increasing volume of the tendon. This work aims at reliable and accurate volumetric quantification of the Achilles tendon using a newly developed contour detection algorithm applied on high resolution MRI data sets recorded at 3T. A total of 26 healthy tendons and 4 degenerated tendons were examined for this study. Automated identification (AI) of tendon boundaries was performed in transverse slices with isotropic resolution (0.8mm) gained with a T2-weighted SPACE sequence at 3T. For AI a snake algorithm was applied and compared to manual tracing (MT). AI was feasible in all examined tendons without further correction. AI of both tendons was performed in each participant within 2 min (2 × 37 slices) compared to MT lasting 20 min. MT and AI showed excellent agreement and correlation (R(2) = 0.99, p<0.0001). AI provided a reduction of measurement error (0.4 cm(3) vs. 0.5 cm(3)) and coefficient of variation (1% vs. 2%). Compared to MT the AI allows assessment of tendon volumes in highly resolved MRI data in a more accurate and reliable time-saving way. Therefore automated volume detection is seen as a helpful clinical tool for evaluation of small volumetric changes of the Achilles tendon.

Detection and Linking Algorithm Based on Improved Snake Model for Pores with Weak Contour

For the pores edge detecting of the Activated Carbon Fibers (ACF) material images, traditional approaches are difficult to obtain the complete edge information. Snake algorithm is a reasonable approach for edge detection. An improved initial contour Snake model is proposed in this paper. A rectangle is first located to surround the edge to be detected instead of drawing a series of points as initial contour. Then, we map these points on the rectangle to the edge surrounded according to certain rule to constitute the initial contour. After the mapping strategy, Snake algorithm is used to iterate the initial contour. Experiments show that complete pores edge information are achieved. Based on the edge pixels, the area of each pores can be calculated easily.

Automatic recognition of five types of white blood cells in peripheral blood

This paper proposes image processing algorithms to recognize five types of white blood cells in peripheral blood automatically. First, a method based on Gram–Schmidt orthogonalization is proposed along with a snake algorithm to segment nucleus and cytoplasm of the cells. Then, a variety of features are extracted from the segmented regions. Next, most discriminative features are selected using a Sequential Forward Selection (SFS) algorithm and performances of two classifiers, Artificial Neural Network (ANN) and Support Vector Machine (SVM), are compared. The results demonstrate that the proposed methods are accurate and sufficiently fast to be used in hematological laboratories.

Automatic tongue image segmentation based on gradient vector flow and region merging

This paper presents a region merging-based automatic tongue segmentation method. First, gradient vector flow is modified as a scalar diffusion equation to diffuse the tongue image while preserving the edge structures of tongue body. Then the diffused tongue image is segmented into many small regions by using the watershed algorithm. Third, the maximal similarity-based region merging is used to extract the tongue body area under the control of tongue marker. Finally, the snake algorithm is used to refine the region merging result by setting the extracted tongue contour as the initial curve. The proposed method is qualitatively tested on 200 images by traditional Chinese medicine practitioners and quantitatively tested on 50 tongue images using the receiver operating characteristic analysis. Compared with the previous active contour model-based bi-elliptical deformable contour algorithm, the proposed method greatly enhances the segmentation performance, and it could reliably extract the tongue body from different types of tongue images.

An Efficient Automated Algorithm to Detect Ocular Surface Temperature on Sequence of Thermograms Using Snake and Target Tracing Function

Functional infrared (IR) imaging is widely adopted in medical field nowadays, with more emphasis on breast cancer and ocular abnormalities. In this article, an algorithm is presented to accurately locate the eye and cornea in ocular thermographic sequences, which were recorded utilizing functional infrared imaging. The localization is achieved by snake algorithm coupled with a newly proposed target tracing function. The target tracing function enables automated localization, allows the absence of any manual assistance before the algorithm runs. Genetic algorithm is used to perform the search for global minimum on the function to produce desired localization. On all the cases we have studied, in average the region encircled by the algorithm covers 92% of the true ocular region. As for the non-ocular region covered, it only accounts for less than 5% of the encircled region.

The effect of limited MR field of view in MR/PET attenuation correction

A critical question in the development of combined MR/PET scanners is whether MR can provide the tissue attenuation data required for PET reconstruction. Unfortunately, MR images are often unable to encompass the entire patient. The resulting truncation in the transverse plane leads to incomplete attenuation maps, causing artifacts in the reconstructed PET image. This article describes the experiments performed to quantify these artifacts. A method to compensate the missing data was evaluated to determine whether software correction is possible or whether additional transmission hardware has to be included in the scanner. Three studies were made. First, simulated PET data were used to quantify the bias due to an incomplete attenuation map. A set of spherical lesions was simulated in the lungs and mediastinum of a patient. The data were reconstructed with complete and partial attenuation maps and the uptake differences were evaluated. Second, clinical data from PET/CT oncology patients were used. To reproduce the expected conditions in an MR/PET scanner, only patients scanned with the arms resting along the body were considered. These scans were then used to create maps of the reconstruction bias due to field of view (FOV) limitations. Lastly, a PET reconstruction with incomplete attenuation data was evaluated as a means to obtain attenuation information beyond the MR FOV. The patient outline was automatically segmented with a three-dimensional snake algorithm and used to fill the truncated data in the attenuation map. Average bias up to 15% and local biases up to 50% were estimated when PET data were reconstructed with incomplete attenuation information. Completing the attenuation map with data extracted from a PET prereconstruction globally reduced these biases to below 10%. This correction proved to be tolerant to inaccuracies in positioning and attenuation values. However, local artifacts up to 20% could still be found near the edges of the MR FOV. MR FOV restrictions can indeed make the reconstructed PET data unacceptable for diagnostic purposes. Biases can be globally compensated by automatic preprocessing of the attenuation map. However, inaccuracies in the correction will result in small artifacts near the periphery of the image that could lead to false-positive findings.

Spatially adaptive active contours: a semi-automatic tumor segmentation framework

Tumor segmentation constitutes a crucial step in simulating cancer growth and response to therapy. Incorporation of imaging data individualizes the simulation and assists clinical correlation with the predicted outcome. We adapted snakes to improve tumor segmentation including difficult cases with inherently inhomogeneous structure and poorly defined margins. Snakes are flexible curves, based on the parameter-controlled deformation of an initial user-defined contour toward the boundary of the desired object, through the minimization of a suitable energy function. Although parameter-adjustment can yield fairly good results in homogeneous regions, traditional snakes often fail to provide an accurate segmentation result when both rigid and very elastic behavior is needed simultaneously to delineate the true outline of the tumor. We developed and tested a spatially adaptive active contour technique by introducing local snake bending, to improve traditional snakes performance for segmenting tumors. The key point of our method is the use of adaptable snake parameters, instead of constant ones, to adjust the bending of the curve according to the local edge characteristics. Our algorithm discriminates image regions according to underlying image features, such as gradient magnitude and corner strength. More specifically, it assigns each region a different "localized" set of parameters, one corresponding to a very flexible snake, and the other corresponding to a very rigid one, according to the local image characteristics. Qualitative results on more than 150 real MR images, as well as quantitative validation based on agreement with an expert clinician's annotations of the true tumor boundaries, demonstrate our approach is highly efficient compared to traditional active contours and region growing. Due to the use of adaptable parameters in the snake evolution process, our approach outperforms the other two methods, and consistently follows an expert's annotations. Statistical tests indicated significant difference between the results produced by our approach and two other algorithms traditional snakes and region growing, while multiple comparison showed that our method consistently outperformed those algorithms, with an average overlap of 89%, over the entire data set, while traditional snakes were at 82.5% and region growing at 59.2%. Furthermore, we performed several tests that demonstrate our method's stability to different initial contours, as well as, to lower resolution images. Our adaptive snake algorithm can spatially adapt to diverse image characteristics, producing outlines that mimic the true tumor boundaries. Results in MR datasets are very close to an expert clinician's intuition about the tumor boundaries.

Graphical processing unit–based machine vision system for simultaneous measurement of shrinkage and soil release in fabrics

We present a machine vision system for simultaneous and objective evaluation of two important functional attributes of a fabric, namely, soil release and shrinkage. Soil release corresponds to the efficacy of the fabric in releasing stains after laundering and shrinkage essentially quantifies the dimensional changes in the fabric postlaundering. Within the framework of the proposed machine vision scheme, the samples are prepared using a prescribed procedure and subsequently digitized using a commercially available off-the-shelf scanner. Shrinkage measurements in the lengthwise and widthwise directions are obtained by detecting and measuring the distance between two pairs of appropriately placed markers. In addition, these shrinkage markers help in producing estimates of the location of the center of the stain on the fabric image. Using this information, a customized adaptive statistical snake is initialized, which evolves based on region statistics to segment the stain. Once the stain is localized, appropriate measurements can be extracted from the stain and the background image that can help in objectively quantifying stain release. In addition, the statistical snakes algorithm has been parallelized on a graphical processing unit, which allows for rapid evolution of multiple snakes. This, in turn, translates to the fact that multiple stains can be detected and segmented in a computationally efficient fashion. Finally, the aforementioned scheme is validated on a sizeable set of fabric images and the promising nature of the results help in establishing the efficacy of the proposed approach.

Parametric active contour model by using the honey bee mating optimization

In this paper, the honey bee mating optimization (HBMO) algorithm is used to improve the detection of the concave region connected with the control points of active contour. In the traditional active contour model (ACM) method, the updating of control point is based on its local energy within a small searching window. As a result, it always results in the failure of precisely searching the boundary concavities. In order to vanquish these drawbacks, the HBMO-based snake algorithm is applied in this paper to search for the optimal position in a lager searching window around each control point. In this proposed algorithm, to each active contour there is a chromosome that includes several genes as well as the control points of active contour. These control points are moved iteratively by minimizing the total energy of the active contour. Experimental results reveal that the proposed HBMO-based snake algorithm can locate the object boundary of concavity more precisely without requiring large number of computational time.

Endocardial boundary extraction in left ventricular echocardiographic images using fast and adaptive B-spline snake algorithm

A fast and robust algorithm was developed for automatic segmentation of the left ventricular endocardial boundary in echocardiographic images. The method was applied to calculate left ventricular volume and ejection fraction estimation. A fast adaptive B-spline snake algorithm that resolves the computational concerns of conventional active contours and avoids computationally expensive optimizations was developed. A combination of external forces, adaptive node insertion, and multiresolution strategy was incorporated in the proposed algorithm. Boundary extraction with area and volume estimation in left ventricular echocardiographic images was implemented using the B-spline snake algorithm. The method was implemented in MATLAB and 50 medical images were used to evaluate the algorithm performance. Experimental validation was done using a database of echocardiographic images that had been manually evaluated by experts. Comparison of methods demonstrates significant improvement over conventional algorithms using the adaptive B-spline technique. Moreover, our method reached a reasonable agreement with the results obtained manually by experts. The accuracy of boundary detection was calculated with Dice's coefficient equation (91.13%), and the average computational time was 1.24 s in a PC implementation. In sum, the proposed method achieves satisfactory results with low computational complexity. This algorithm provides a robust and feasible technique for echocardiographic image segmentation. Suggestions for future improvements of the method are provided.

Topography mapping of whole body adipose tissue using A fully automated and standardized procedure

To obtain quantitative measures of human body fat compartments from whole body MR datasets for the risk estimation in subjects prone to metabolic diseases without the need of any user interaction or expert knowledge. Sets of axial T1-weighted spin-echo images of the whole body were acquired. The images were segmented using a modified fuzzy c-means algorithm. A separation of the body into anatomic regions along the body axis was performed to define regions with visceral adipose tissue present, and to standardize the results. In abdominal image slices, the adipose tissue compartments were divided into subcutaneous and visceral compartments using an extended snake algorithm. The slice-wise areas of different tissues were plotted along the slice position to obtain topographic fat tissue distributions. Results from automatic segmentation were compared with manual segmentation. Relatively low mean deviations were obtained for the class of total tissue (4.48%) and visceral adipose tissue (3.26%). The deviation of total adipose tissue was slightly higher (8.71%). The proposed algorithm enables the reliable and completely automatic creation of adipose tissue distribution profiles of the whole body from multislice MR datasets, reducing whole examination and analysis time to less than half an hour.

Using Active Contours for Semi-Automated Tracking of UV and EUV Solar Flare Ribbons

Solar-flare UV and EUV images show elongated bright “ribbons” that move over time. If these ribbons are assumed to locate the footpoints of magnetic-field lines reconnecting in the corona, then it is clear that studying their evolution can provide important insight into the reconnection process. An image-processing method based on active contours (commonly referred to as “snakes”) is proposed as a method for tracking UV and EUV flare ribbons and is tested on images from the Transition Region and Coronal Explorer (TRACE). This paper introduces the basic concepts of such an approach with a brief overview of the history and theory behind active contours. It then details the specifics of the snake algorithm developed for this work and shows the results of running the algorithm on test images. The results from the application of the developed algorithm are reported for six different TRACE flares (five in UV and one in EUV). The discussion of these results uses the output from an expert tracking the same ribbons by eye as a benchmark, and against these the snake algorithm is shown to compare favourably in certain conditions, but less so in others. The applicability of the automated snake algorithm to the general problem of ribbon tracking is discussed and suggestions for ways to improve the snake algorithm are proposed.