Automatic Hepatic Tumor Segmentation Using Statistical Optimal Threshold

Park, Seungjin; Seo, Kyung-Sik; Park, Jong-An

doi:10.1007/11428831_116

Cited by 34 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two cases illustrated in Figs. 9,10,11,12,13,14,15,16 are evidence of the advantages associated with the application of rank filter, which ensures a continuity of the edges extracted from ultrasound images. Figure 17 An example of incorrect GB contour imaging due to the occurrence of a stone.…”

Section: Ideal Cases Of Gb Ultrasound Image Filtrationmentioning

confidence: 98%

Effective Filtration Techniques for Gallbladder Ultrasound Images with Variable Contrast

Bodzioch¹,

Ogiela

2008

J Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

This paper presents a new method of filtering gallbladder contours on static ultrasound images. A major stage in the analysis of ultrasound images is to segment and section off areas occupied by the said organ. In the majority of cases this procedure is a key phase in the process of diagnosing pathological changes in tested organs. Unfortunately ultrasound images present among the most troublesome methods of analysis owing to the echogenic inconsistency of structures under observation. This also applies to the analysis of gallbladder images, chiefly targeted at recognizing changes, which may reveal evidence of developing inflammatory or cancerous changes. This paper provides for an inventive algorithm for the extraction of gallbladder image contours. The algorithm is based on rank filtration, as well as on the analysis of histogram sections on tested organs. The proposed approach of gallbladder image segmentation allows to obtain the effective results of contour detection which exceed 70%. This method is based on two procedures, which independently determine the relevant contour points for both correctly contrasted and vague ultrasound images. The independent results obtained from both procedures when merged allowed for a final determination of a tested organ's actual shape. Defined in such way morphology makes possible to perform a further classification, which is intended to define certain morbid changes such as inflammation, and cancer. The presented approach based on dynamically adjusted contrast improvement, expand traditional methods of ultrasound images segmentation by additional parallel filtration procedures. As shown in the paper such algorithm is easy scalable and effective.

show abstract

Section: Ideal Cases Of Gb Ultrasound Image Filtrationmentioning

confidence: 98%

Effective Filtration Techniques for Gallbladder Ultrasound Images with Variable Contrast

Bodzioch¹,

Ogiela

2008

J Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

show abstract

“…These include thresholding and edge detection, 18 region-growing techniques 19 including the watershed method 20,21 and fuzzy c-mean clustering, 22 active contours or snakes, 23 and gradient vector flow ͑GVF͒ snakes. 24 Additionally, initial studies have been done on performing automatic segmentation on CT scans to determine liver tumor volume.…”

Section: ͒mentioning

confidence: 99%

Comparison of two‐dimensional and three‐dimensional iterative watershed segmentation methods in hepatic tumor volumetrics

et al. 2008

View full text Add to dashboard Cite

In this work the authors compare the accuracy of two-dimensional ͑2D͒ and three-dimensional ͑3D͒ implementations of a computer-aided image segmentation method to that of physician observers ͑using manual outlining͒ for volume measurements of liver tumors visualized with diagnostic contrast-enhanced and PET/CT-based non-contrast-enhanced ͑PET-CT͒ CT scans. The method assessed is a hybridization of the watershed method using observer-set markers with a gradient vector flow approach. This method is known as the iterative watershed segmentation ͑IWS͒ method. Initial assessments are performed using software phantoms that model a range of tumor shapes, noise levels, and noise qualities. IWS is then applied to CT image sets of patients with identified hepatic tumors and compared to the physicians' manual outlines on the same tumors. The repeatability of the physicians' measurements is also assessed. IWS utilizes multiple levels of segmentation performed with the use of "fuzzy regions" that could be considered part of a selected tumor. In phantom studies, the outermost volume outline for level 1 ͑called level 1_1 consisting of inner region plus fuzzy region͒ was generally the most accurate. For in vivo studies, the level 1_1 and the second outermost outline for level 2 ͑called level 2_2 consisting of inner region plus two fuzzy regions͒ typically had the smallest percent error values when compared to physician observer volume estimates. Our data indicate that allowing the operator to choose the "best result" level iteration outline from all generated outlines would likely give the more accurate volume for a given tumor rather than automatically choosing a particular level iteration outline. The preliminary in vivo results indicate that 2D-IWS is likely to be more accurate than 3D-IWS in relation to the observer volume estimates.

show abstract

“…In the conventional method [5], as the intensity of vessels is higher than those of health liver tissues and tumor tissues, intensity threshold method is used to remove vessels. We classify the CT volume into 3 classes by using Maximum likelihood method.…”

Section: Removement Of Vessels By Applying Maximum Likelihood Methodsmentioning

confidence: 99%

“…These methods can be classified as semi-automatic [2][3] and automatic [4] [5]. Smeets et al have proposed a semi-automatic level set method, which combines a spiral scanning technique with supervised fuzzy pixel classification [2].…”

Section: Introductionmentioning

confidence: 99%

“…Mala et al employed wavelet-based texture features in order to train a neural network for use in tumor detection [4]. In the method proposed by Park et al [5], the voxels representing the liver vessels are removed from liver images and a bimodal histogram is assumed for the intensity distribution of the liver and tumors. The optimal threshold to segment tumors is determined by a "mixture probability density" algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Liver tumor detection in CT images by adaptive contrast enhancement and the EM/MPM algorithm

Masuda

Tateyama

Xiong

et al. 2011

2011 18th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

Automatic Hepatic Tumor Segmentation Using Statistical Optimal Threshold

Cited by 34 publications

References 10 publications

Effective Filtration Techniques for Gallbladder Ultrasound Images with Variable Contrast

Effective Filtration Techniques for Gallbladder Ultrasound Images with Variable Contrast

Comparison of two‐dimensional and three‐dimensional iterative watershed segmentation methods in hepatic tumor volumetrics

Liver tumor detection in CT images by adaptive contrast enhancement and the EM/MPM algorithm

Contact Info

Product

Resources

About