Reading:
new journal format Essay
Share: Twitter, Facebook, Pinterest
Free Essay
Nov 26th, 2019

new journal format Essay

LIVER SEGMENTATION ON CT S.SUBHA (Ph.D) SOUTH TRAVANCORE HINDU COLLEGE ABSTRACT Organ segmentation from medical images is still an open problem and liver segmentation is a much more challenging task among other organ segmentations. Computer Aided Diagnosis of liver tumors from abdominal Computer Tomography (CT) images requires segmentation of tumor. Automatic segmentation of tumor from CT images is a challenging task due in part to the variation of size, shape, and position of the tumor and on the other part to the presenc e of other objects with the same intensity in the CT images.

Therefore, it is necessary to segment the liver first so that tumor can then be segmented accurately. This paper presents a new method for automatic segmentation of liver and tumor from CT images . The pro -posed segmentation evaluated on real -world clinical data from patients is based on a hybrid method integrating cuckoo optimization and fuzzy c -means algorithm with random walker’s algorithm.

Don't use plagiarized sources. Get Your Custom Essay on
new journal format Essay
Just from $13/Page
Order Essay

The accuracy of the proposed method was validated using a clinical liver dataset containing one of the highest numbers of tumors utilized for liver tumor segmentation. Keywords: Liver segmentation, cuckoo optimization, Random walker, Fuzzy C mean 1. INTRODUCTION The liver is an organ onl y found in vertebrates which detoxifies various metabolities, synthesizes proteins and produce biochemical necessary for digestion. In humans , it is located in the right upper quadrant of the abdomen , below the diaphragm . Its other roles in metabolism include the regulation of glycogen storage, decomposition of red blood cells and production of cells and the production of hormones. The liver is an accessory digestive gland that produces bile , an alkaline compound which helps the breakdown of fat . Bile aids in digestion via the emulsification of lipids . The gallbladder , a small pouch that sits just under the liver, stores bile produced by the liver which is afterwards moved to the small intestine to complete digestion . The liver’shighly specialized tissue consisti ng hepatocytes regulates a wide variety of high -volume biochemical reactions, including the synthesis and breakdown of small and complex molecules, many of which are necessary for normal vital functions. Estimates regarding the organ’s total number of functions vary, but textbooks generally cite it being around 500 .The structure the liver is a reddish – brown we dge shaped organ with four lobes of unequal size and shape. A human liver normally weighs approximately 1.5 kg and has a width of about 15 cm (6 in). It is both the heaviest internal organ and thelargest gland in the human body. Located in the right upper quadrant of the abdominal cavity , it rests just below the diaphragm , to the right of the stomach and overlies the gallbladder . The liver is connected to two large blood vessels : the hepatic artery and the portal vein and common hepatic duct. The hepatic artery carries oxygen -rich blood from the aorta via the celiac plexus, whereas the portal vein carries blood rich in digested nutrients from the entire gastrointestinal tract and also from the spleen and pancreas . These blood vessels subdivide into small capillaries known as liver sinusoids , which then lead to lobules . Lobules are the functional units of the liver. Each lobule is made up of millions of hepatic cells (hepatocytes), which are the basic metabolic cells. The lobules are held together by a fine, dense, irregular, fibroelastic connective tissue layer which extends from the fibrous capsule covering the entire liver known as Glisson’s capsule . This extends into the structu re of the liver, by accompanying the blood vessels (veins and arteries), ducts, and nerves at the hepatic hilum. The whole surface of the liver except for the bare area , is covered in a serous coat derived from the peritoneum, and this firmly adheres to the inner Glisson’s capsule. Automated liver segmentation is a challenging task in the field of medical image processing. Usually performed on contrast -enhanced CT images, it provides physicians with 3D models and precise regions of interest for the evaluation of numerous clinical par ameters relevant in virtual surgery planning , radio -therap y planning and image -guided surgery . 2. RELATED WORK Computerized Liver Volumetry on MRI by Using 3D Geodesic Active Contour Segmentation Hieu Trung Huynh, Ibrahim Karademir et al. Medical and surgical advances have brought about a global success of liver transplantation with increasing survival rates after transplantation over the past decades. One of the important assessments contributing to the success of a transplantation procedu re is the estimation of total and segmental liver volumes. This is a major factor in predicting the safe outcome for both donor and recipient. Hence, an accurate estimation of liver volumes is crucial for planning. Although the manual tracing method can gi ve accurate results, it is subjective, tedious, and time consuming. In addition, relatively large intraobserver and interobserver variations still occur with the manual method. To address this issue, automated liver segmentation is being developed with ima ge analysis techniques and has become an important research topic liver transplantation. Liver segmentation in MRI: A fully automatic method based on stochastic partitions F. Lіpez -Mira , V. Naranjoa, J. Angulo et al. Fully automatic liver segmentation in medical images is currently an unsolved proble m. An accurate liver segmen tation has a direct application in the planning, monitoring, and treatment of different types of pathologies such ascirrhosis or hepatocellular carcin oma diseases. In these cases, hepatic tissue anom alies are treated using qualita tive comparison, which is related to physician experience; however, quantitative measures are not widely used. Liver segmentation is the first step to calculate objectiveme asure ments and liver/lesion ratios for decisions regarding treatment and planning for the patient. The segmentation of internal organs is also essential for image -guided surgery and virtual reality scen arios for medical training . Automatic Volumetric Live r Segmentation Using Texture Based Region Growing, O. Gambino, S. Vitabile, G. Lo Re, G. La Tona1 et al. In the context of medical imaging, the problem of tissue segmentation is to delimit the image areas representing different anatomies. It is an essentia l step for automatic analysis of medical images because it increases the radiologists’ productivity and permits a more accurate diagnosis and quantitative analysis. In this paper an automatic texture based volumetric region growing method for liver segment ation is proposed. 3D seeded region growing is based on texture features with the automatic selection of the seed voxel inside the liver organ and the automatic threshold value computation for the region growing stop condition. Co – occurrence 3D texture fea tures are extracted from CT abdominal volumes and the seeded region growing algorithm is based on statistics in the features space. Each CT volume is composed by 230 slices, having 512 x 512 pixels as spatial resolution, and 12 -bit gray level resolution. In this initial feasible study, 5 healthy volunteer acquisitions has been used. Tests have been performed on both basal phase and arterial phase images. Segmentation result shows the effectiveness of the proposed method: liver organ is correctly recognized and segmented, leaving out liver vessels form the segmented area and overcoming the organ -splitting problem. The goodness of the proposed method has been confirmed by manual liver segmentation results, having analogous and superimposable behavior. A 3 -D Liver Segmentation Method with Parallel Computing for Selective Internal Radiation Therapy, Mohammed Goryawala, Magno R. Guillen, Mercedes Cabrerizo, et al. This study describes a new 3-D liver segmentation method in support of the selective internal radi ation treatment as a treatment for liver tumors. This 3 – Dsegmentation is based on coupling a modified k-means segmentation method with a special localized contouring algorithm. In the segmentation process, five separate regions are identified on the computerized tomography image frames. The merit of the proposed method lays in its potential to provide fast and accurate liver segmentation and 3 -D rendering as well as in delineating tumor region(s), all with minimal user interaction. Leveraging of multicore platforms is shown to speed up the processing of medical images considerably, making this method more su itable in clinical settings. Experiments were performed to assess the effect of parallelization using up to 442 slices. Empirical results, using a single workstation, show a reduction in processing time from 4.5 h to almost 1 h for a 78% gain. Most importa nt is the accuracy achieved in estimating the volumes of the liver and tumor region(s), yielding an average error of less than 2% in volume estimation over volumes generated on the basisof the current manually guided segmentation processes. Results were assessed using the analysis of variance statistical analysis. Fully Automatic Segmentations of Liver and Hepatic Tumors From 3 -D Computed Tomography AbdominalImages: Comparative Evaluation of Two Automatic Methods, Sergio Casciaro, Roberto Franchini, Laure nt Massoptier, Ernesto Casciaro, An adaptive initialization method was developed to produce fully automatic processing frameworks based on graph -cut and gradient flow active contour algorithms. This method was applied to abdominal Computed Tomography (CT) images for segmentation of liver tissue and hepatic tumors. Twenty -five anonymized datasets were randomly collected from several radiology centres without specific request on acquisition parameter settings nor patient clinical situation as inclusion criter ia. Resulting automatic segmentations of liver tissue and tumors were compared to their reference standard delineations manually performed by a specialist. Segmentation accuracy has been assessed through the following evaluation framework: dice similarity coefficient (DSC), false negative ratio (FNR), false positive ratio (FPR) and processing time. Regarding liver surfaces, graph -cuts achieved a DSC of 95.49% , while active contours reached a DSC of 96.17%. The analyzed datasets presented 52 tumors: graph -cut algorithm detected 48 tumors with a DSC of 88.65%, while active contour algorithm detected only 44 tumors with a DSC of 87.10%. In addition, in terms of time performances, less time was requested for graph -cut algorithm with respect to active contour on e. The implemented initialization method allows fully automatic segmentation leading to superior overall performances of graph -cut algorithm in terms of accuracy and processing time. The initialization method here presented resulted suitable and reliable f or two different segmentation techniques and could be further extended. 3D Liver Segmentation from CT Images Using a Level Set Method Based on a Shape and Intensity Distribution Prior, Nuseiba M. Altarawneh, Suhuai Luo, Brian Regan, Guijin Tang et al. LIVERS constitute one of t he most prominent organs in our bodies. It performs key fun ctions including cleaning blood from impurities, producing bil e and proteins, treating sugar, decomposition of medications, and storing valuable nutrients suc h as iron, minerals an d vitamins. As a result of high functionality, the liver is prone to many notorious diseases such as hepatitis C, cirrhosis, and cancer. With the very rapid advancement in computer sc ience and its associated technology, computer -aided surgical planning systems (CAD) continue to play an important rol e in diagnosis and treatment of the aforementioned liver disea ses. These promising approaches can map out the structures of various liver vessels, afford accurate 3D visualizations, and prov ide surgical insights of simulations with cutting. All these applications have the potential to lead to shorter planning times. One of the most daunting tasks in the context of computer tomography (CT) images is to carry out an auto matic and accurate segme ntation of a liver from its surrounding or gans. Establishing an effective methodology for liver segmen tation from CT images proves to be a challenging mission. This is mainly due to the profoundly similar intensity values between liver and its adjacent org ans. Other contributing factors inc lude artifacts of pulsation and motion and partial volume effects . The substantial variations in shape and volume of liver amo ng people even add more hurdles toward accurate segmentation of t he liver. It follows that live r segmentation from medical i mages still pose an interesting theme of research. Liversegmentation from medical images poses more challenges than analogous segm entations of other organs. This contribution introduces a liver segmentation method from a serie s of computer tomography images. Overall , we present a novel method for segmenting liver by coupling dens ity matching with shape priors. Density matching signifies a tracking method which operates v ia maximizing the Bhattacharyya similarity measure between the photometric distribution from an est imated image region and a model photometric distribution. Density mat ching controls the direction of the evolution process and slows down the evolving contou r in regions with weak edge s. T he shape prior improves the robustness of density matching and discourages the evolving contour from exceeding liver’ s boundaries at regions wit h weak boundaries. The model is implemented using a modified distance regularized level set (DRLS) model. The ex perimental results show that the method achieves a satisfactory result. By comparing with the original DRLS model, it is evident that the proposed model herein is more effective in addressing the over segmentation problem. Final ly, we gauge our performance of our model against matrices comprisin g of accuracy, sensitivity, and specificity. 3. METHODS CUCKOO OPTIMIZATION Inspire d by reproduction strategies of cuckoo birds, cuckoo search optimization was proposed Cuckoo lays egg on other bird’s nest, based on this observation the following rules we re proposed : 1) Choosing a random nes t, each bird lays one egg representing a set of so – lutions for the optimized problem. 2) With a fixed number of nests, there is a probability that the host might dis -cover and discard the egg. 3) The nests containing the best solu – tions (egg) will be car ried to the next iteration (new generation). FUZZY C MEAN The Fuzzy C -Means (FCM) clustering algorithm wa s first introduced by Dunn and later was extended by Bezdek . The algorithm is an iterative clustering method that produces an optimal c partition by mini mizing the weighted within group sum of squared erro r objective function JF CM where X = {x 1, x 2, · · · , x n} Rp is the data set in the p -dimensional vector space, n is the number of data items, c is th e number of clusters with 2 ‰¤ c < n, u ik is the degree of membership of x k in the i th cluster, q is a weighting exponent on each fuzzy membership, vi is the prototype of the centre of cluster i, d 2 (xk, v i) is a distance . Huang measure betw een object xk and cluster centre v i . RANDOM WALKER ALGORITHM Graph -Cut (GC) based segmentation is an alternative to boundary based seg menta tion meth ods, being a semi – automatic seg mentation the user is required to provide the seeds representing the background and the object to be segmented,GC represents the image pixels as nodes on a graph with weighted edges representing the adjacency between the pixels. By finding the minimum cost function between all possible cuts of the graph, the GC segments the image into background and the object . 4. CONCLUSION It is concluded that the detection of tumor in the liver was performed very accurately because of using the three methods such as Fuzzy C mean, Cuckoo optimization and the random walker algorithm. These techniques provide the accurate detection of the boundary for the segmented image and identify whether the input i mage is the normal i mage or tumor detected image. 5. REFERENCES 1. Tang, J. Chen et al. , Cross – sectio nal and longitudinal evaluation of liver volume and total liver fat bur den in adults with non – alcoholic steatohepatitis, Abdominal Imaging , vol. 40, no. 1, pp. 26 “37, 2015. 2. O. Gambino, S. Vitabile et al. , Automati c Volumetric Liver Segmentation Using Texture Based Region Growing, in IEEE ICIS . Krakow, Poland: IEEE, Feb. 2010, pp. 146 “152. 3. M. Goryawala, M. R. Guillen et al. , A 3 -D liver segmentation method with parallel computing for selective internal radi ation therapy. IEEE Trans. Inf Technol Biomed , vol. 16, no. 1, pp. 62 “9, Jan. 2012. 4. S. Casciaro, R. Franchini et al. , Fully Automatic Segmentations of Liver and Hepatic Tumors From 3 – D Computed Tomography Abdominal Images: Comparative Evaluation of Two Automatic Methods, IEEE Sensors Journal , vol. 12, no. 3, pp. 464 “473, Mar. 2012. 5. G. Chartrand, A. Tang et al. , Li ve minimal path for interactive segmentation of medical images, in Proc. of SPIE , vol. 9413, 2015, pp. 94 133U “94 133U “7.

Recommended stories