Breast mass segmentation on digital mammograms by a combined deterministic annealing method

Cao, Aize; Song, Qing; Yang, Xulei; Liu, S.

doi:10.1109/isbi.2004.1398785

Cited by 10 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to K -means and FCM, which are sensitive to data initialization and converge to local optimal solutions, deterministic annealing (DA) clustering [ 14 ] is a global minimisation algorithm by incorporating randomness into the energy function to be minimized, such that it is independent of the choice of the initial data configuration and has the ability to avoid poor local optima. The DA approach has also been used for mass segmentation in [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

A Spatial Shape Constrained Clustering Method for Mammographic Mass Segmentation

Lou

Yang

Cao

2015

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

A novel clustering method is proposed for mammographic mass segmentation on extracted regions of interest (ROIs) by using deterministic annealing incorporating circular shape function (DACF). The objective function reported in this study uses both intensity and spatial shape information, and the dominant dissimilarity measure is controlled by two weighting parameters. As a result, pixels having similar intensity information but located in different regions can be differentiated. Experimental results shows that, by using DACF, the mass segmentation results in digitized mammograms are improved with optimal mass boundaries, less number of noisy patches, and computational efficiency. An average probability of segmentation error of 7.18% for well-defined masses (or 8.06% for ill-defined masses) was obtained by using DACF on MiniMIAS database, with 5.86% (or 5.55%) and 6.14% (or 5.27%) improvements as compared to the standard DA and fuzzy c-means methods.

show abstract

Section: Introductionmentioning

confidence: 99%

A Spatial Shape Constrained Clustering Method for Mammographic Mass Segmentation

Lou

Yang

Cao

2015

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…She proposed a region merging algorithm on the basis of the intensity distribution of regions and the characteristic of triangle shape, and the region merging algorithm is used to identify the pectoral muscle. Cao, A.Z [4] developed a breast mass segmentation scheme, which is based on the concept of deterministic annealing and incorporated with a gain adaptive contrast enhancement (GACE) preprocessing technique. The probability distribution of gray levels within the region of interest after GACE filter is estimated and a series of image partitions obtained according to the intensity proximity.…”

Section: Introductionmentioning

confidence: 99%

A Segmentation Method for Mammogram X-ray Image Based on Image Enhancement with Wavelet Fusion

Zhang

Gou²

2015

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

A segmentation method based on image enhancement method with wavelet fusion was proposed to segment X-ray mammogram images with low pixel and unclarity. Firstly, a breast X-ray image was pretreated by histogram equalization and median filtering. Then a wavelet fusion algorithm with the rule of taking large low frequency energy and high-frequency variance was applied to the pretreated image, subsequently producing an enhanced image. Secondly, an improved live-wire interactive segmentation algorithm with qualification to make the shortest path search was used to divide suspicious masses on the enhanced image. Related experiments were carried out on typical data-sources that came from the Mammographic Image Analysis Society mini-database and clinical mammography images, and the results indicated that the algorithm have good effect on image enhancement and segmentation.

show abstract

“…It is reported by Beijing Research Institute of Cancer Prevention and Treatment that breast cancer is the most harm among cancers for women with Beijing household register. It is reported that early diagnosis and treatment can increase the chances of survival for the patients of breast cancer [1][2] . Mammography is a strong indicator for breast cancer detection [3][4] .…”

Section: Introductionmentioning

confidence: 99%

Perceptual mass segmentation using eye-tracking and seed-growing

Liu

et al. 2012

SPIE Proceedings

View full text Add to dashboard Cite

In the paper, we propose a novel scheme for breast mass segmentation in mammography, which is based on visual perception and consists of two steps. Firstly, radiologists' eye-gazing data is recorded by the eye-tracker during reading and then clustered with a density-based spatial clustering of applications with noise (DBSCAN) algorithm to achieve seeds locating radiologists' regions of interest (ROIs). The seeds-based region growing (SBRG) algorithm is applied to buckle ROIs containing suspicious lesions. Secondly, in order to achieve fine lesion contour as final result, the ROIs are segmented with a multi-scale mass segmentation approach using active contour models. The result of applying the proposed method to the mammograms from both DDSM and Zhejiang Cancer Hospital shows that the achieved average of overlap rate is 0.5915 and the achieved average of misclassification rate is 0.6342. The innovative point of the proposed approach is to introduce visual perception into breast mass segmentation, which makes the result of mass segmentation meet radiologists' subjective demand.

show abstract

Breast mass segmentation on digital mammograms by a combined deterministic annealing method

Cited by 10 publications

References 6 publications

A Spatial Shape Constrained Clustering Method for Mammographic Mass Segmentation

A Spatial Shape Constrained Clustering Method for Mammographic Mass Segmentation

A Segmentation Method for Mammogram X-ray Image Based on Image Enhancement with Wavelet Fusion

Perceptual mass segmentation using eye-tracking and seed-growing

Contact Info

Product

Resources

About