Breast cancer diagnosis using self-organizing map for sonography

Chen, Dar Ren; Chang, Ruey-Feng; Huang, Yu-Len

doi:10.1016/s0301-5629(99)00156-8

Cited by 158 publications

(78 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultrasonography (US) has traditionally been used to differentiate cysts from solid masses and to direct biopsies. Research has been directed at differentiating malignant from benign breast lesions with US (11)(12)(13)(14)(15), including computer-aided diagnosis (CAD) studies of US (16)(17)(18)(19)(20)(21)(22) for the same task.…”

Section: Methodsmentioning

confidence: 99%

Computer-aided Classification of Breast Masses: Performance and Interobserver Variability of Expert Radiologists versus Residents

Singh¹,

Maxwell²,

Baker³

et al. 2011

Radiology

View full text Add to dashboard Cite

Purpose:To evaluate the interobserver variability in descriptions of breast masses by dedicated breast imagers and radiology residents and determine how any differences in lesion description affect the performance of a computer-aided diagnosis (CAD) computer classifi cation system. Materials and Methods:Institutional review board approval was obtained for this HIPAA-compliant study, and the requirement to obtain informed consent was waived. Images of 50 breast lesions were individually interpreted by seven dedicated breast imagers and 10 radiology residents, yielding 850 lesion interpretations. Lesions were described with use of 11 descriptors from the Breast Imaging Reporting and Data System, and interobserver variability was calculated with the Cohen k statistic. Those 11 features were selected, along with patient age, and merged together by a linear discriminant analysis (LDA) classifi cation model trained by using 1005 previously existing cases. Variability in the recommendations of the computer model for different observers was also calculated with the Cohen k statistic. Results:A signifi cant difference was observed for six lesion features, and radiology residents had greater interobserver variability in their selection of fi ve of the six features than did dedicated breast imagers. The LDA model accurately classifi ed lesions for both sets of observers (area under the receiver operating characteristic curve = 0.94 for residents and 0.96 for dedicated imagers). Sensitivity was maintained at 100% for residents and improved from 98% to 100% for dedicated breast imagers. For residents, the computer model could potentially improve the specifi city from 20% to 40% ( P , .01) and the k value from 0.09 to 0.53 ( P , .001). For dedicated breast imagers, the computer model could increase the specifi city from 34% to 43% ( P = .16) and the k value from 0.21 to 0.61 ( P , .001). Conclusion:Among fi ndings showing a signifi cant difference, there was greater interobserver variability in lesion descriptions among residents; however, an LDA model using data from either dedicated breast imagers or residents yielded a consistently high performance in the differentiation of benign from malignant breast lesions, demonstrating potential for improving specifi city and decreasing interobserver variability in biopsy recommendations.q RSNA, 2010 1

show abstract

Section: Methodsmentioning

confidence: 99%

Computer-aided Classification of Breast Masses: Performance and Interobserver Variability of Expert Radiologists versus Residents

Singh¹,

Maxwell²,

Baker³

et al. 2011

Radiology

View full text Add to dashboard Cite

show abstract

“…Different filters have been proposed including Gabor filters (Xie et al, 2005;Zhan and Shen, 2006), Gaussian derivatives (Chen et al, 1998) and wavelet transforms (Mojsilovic et al, 1998;Yoshida et al, 2003). The idea behind random fields is that the value at each pixel/voxel is chosen by two-dimensional (2-D)/ three dimensional (3-D) stochastic process.…”

Section: Texturementioning

confidence: 99%

“…Statistical approaches yield characterizations of textures as smooth, coarse, grainy, etc. Major statistical texture descriptors include co-occurrence matrix (Nicholas et al, 1986, Sahiner et al, 2004, Kuo et al, 2001, auto-correlation (Chen et al, 2000), edge frequency, run length, Law's texture energy, and fractal texture description. Several researchers have proposed to extract fractal texture features (Wu et al, 1992;Lee et al, 2003;Chen et al, 2005).…”

Section: Texturementioning

confidence: 99%

Automated Segmentation of Real-Time 3D Echocardiography Using an Incompressibility Constraint

Zhu¹,

Papademetris²,

Sinusas³

et al. 2012

Echocardiography - New Techniques

View full text Add to dashboard Cite

“…In addition, the National Cancer Institute of U.S. estimates that 16.4 percent of women born today and live with a breast cancer diagnosis [3]. For the diagnosis of the breast cancer cases as well as for the prognosis of the disease many methods have been discussed [4], [5], [6], [7], [8], [9], [10] and [11]. All machine leaning techniques to provide the same levels of exactness, without the negative sides of surgical biopsy.…”

Section: Introductionmentioning

confidence: 99%

Detect Breast Cancer using Fuzzy C means Techniques in Wisconsin Prognostic Breast Cancer (WPBC) Data Sets

Tintu¹,

Paulin²

2013

IJSEA

View full text Add to dashboard Cite

Abstract-Medical data mining is very much valuable to medical experts. The main task of data mining is diagnosing the patient's disease Classification. Breast cancer is a severe and life threatening disease very commonly found in woman. An unusual growth of cells in breast is the main source of breast cancer those cells can be of two types malignant (Cancerous) and benign (Non-Cancerous) these types must be diagnosed taking proper meditation and for proper treatment. Modern medical diagnosis scheme is totally based on data taken through clinical and/or other test; most of the decision related to classification of a disease is a very crucial and challenging job. In this research work, using intelligent techniques of data mining is Fuzzy C Means; we have focused on breast cancer diagnosis by fuzzy systems. Fuzzy rules are desirable because of their interpretability by human experts. It has been applied to classify data related to breast cancer from UCI repository site. Experimental works were done using MATLAB in order to reduce dimensionality of breast cancer data set a ranking based feature selection technique. Results on breast cancer diagnosis data set from UCI machine learning repository show that this approach would be capable of classifying cancer cases with high accuracy rate in addition to adequate interpretability of extracted rules.

show abstract

Breast cancer diagnosis using self-organizing map for sonography

Cited by 158 publications

References 25 publications

Computer-aided Classification of Breast Masses: Performance and Interobserver Variability of Expert Radiologists versus Residents

Computer-aided Classification of Breast Masses: Performance and Interobserver Variability of Expert Radiologists versus Residents

Automated Segmentation of Real-Time 3D Echocardiography Using an Incompressibility Constraint

Detect Breast Cancer using Fuzzy C means Techniques in Wisconsin Prognostic Breast Cancer (WPBC) Data Sets

Contact Info

Product

Resources

About