Detection of regions of interest's in mammograms by using local binary pattern, dynamic k-means algorithm and gray level co-occurrence matrix

Elmoufidi, Abdelali; Fahssi, Khalid El; Andaloussi, Said Jai; Madrane, Nabil; Sekkaki, Abderrahim

doi:10.1109/ngns.2014.6990239

Cited by 27 publications

(13 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Elmoufidi, A., et al [5] used the dynamic K-means clustering algorithm with local binary pattern for the detection of the ROI in mammograms. In this system the contrast enhancement step is necessary; therefore a two-dimensional median filtering was used for enhancement of the contrast in mammogram images.…”

Section: Literature Surveymentioning

confidence: 99%

“…: Hierarchical structure of the proposed CAD systemFig. (2):The elements that constitute a mammogram image[5] Therefore, a new simple method is proposed for removing the pectoral muscle region automatically. This method is summarized in the following steps: 1-Change image orientation: the orientation of all images is checked and changed (if necessary) to assure that the location of the pectoral muscle in the image at the upper left corner.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Computer-Aided Detection System for Breast Cancer Based on GMM and SVM

Arafa

El-Sokary

Asad

et al. 2019

Arab Journal of Nuclear Sciences and Applications

View full text Add to dashboard Cite

Region-of-interest (ROI) segmentation is an important critical step and challenging task in the evolution of computer-aided detection (CAD) system for breast cancer. The discovery of breast cancer in early stages can save many women lives.However, most of the early detection systems are costly in terms of complexity,price and processing time; that make it unsuited for developing countries.The digital mammography is proven to be one of the most important diagnostic techniques for breast cancer tumors. Therefore, this work proposes a CADsystem for breast cancer detectionfrom digital mammography based on GaussianMixture Model(GMM) followed bySupport Vector Machine (SVM).The best contribution of our proposed system is the usage of GMM for the first time in the literature for mammogram images segmentation into ROI areas.Besides, the discrimination betweenthe three classes of tissues as normal,benign ormalignant, isused without previous knowledge of mammogram images'type. Moreover, the proposed system is fully automated in all of its stages with reduced computation compared with recent used methods. Hence, it offers a suitable early detection system to our country regarding moneywise, timewise, and reduced complexity.A non-linear multi-class SVMis used for classifying the ROI into three classes: normal, benignor malignant tissue.The experiments show overall average classification accuracy of 90% for detecting normal, malignant or benignonrandomly chosen90 cases from the benchmark mini-MIAS dataset. On the other hand, the proposed method achieves 92.5% accuracy when classifying the benign from malignant cases. The confusion matrix was used to assess the proposed CAD system overall performance as it is considered to be a good evaluation metric method.

show abstract

Section: Literature Surveymentioning

confidence: 99%

mentioning

confidence: 99%

Computer-Aided Detection System for Breast Cancer Based on GMM and SVM

Arafa

El-Sokary

Asad

et al. 2019

Arab Journal of Nuclear Sciences and Applications

View full text Add to dashboard Cite

show abstract

“…For example, Adel et al [14] used a method to segment mammograms into three distinct regions are : pectoral muscle, fatty regions, and fibroglandular regions using Bayesian techniques with Markov random field. Elmoufidi et al [15][16] developed a method to Detect of ROIs in Mammograms using LBP algorithm, K-Means algorithm and GLCM algorithm. K. Hu et al [2] published an approach to detect of suspicious lesions in mammograms by adaptive thresholding based on multiresolution.…”

Section: Related Workmentioning

confidence: 99%

Automatic Diagnosing of Suspicious Lesions in Digital Mammograms

Elmoufidi¹,

Fahssi²,

Andaloussi³

et al. 2016

ijacsa

Self Cite

View full text Add to dashboard Cite

Abstract-Breast cancer is the most common cancer and the leading cause of morbidity and mortality among women's age between 50 and 74 years across the worldwide. In this paper we've proposed a method to detect the suspicious lesions in mammograms, extracting their features and classify them as Normal or Abnormal and Benign or Malignant for diagnosing of breast cancer. This method consists of two major parts: The first one is detection of regions of interest (ROIs). The second one is diagnosing of detected ROIs. This method was tested by Mini Mammography Image Analysis Society (Mini-MIAS) database. To check method's performance, we've used FROC (Free-Receiver Operating Characteristics) curve in the detection part and ROC (Receiver Operating Characteristics) curve in the diagnosis part. Obtained results show that the performance of detection part has sensitivity of 94.27% at 0.67 false positive per image. The performance of diagnosis part has 94.29% accuracy, with 94.11% sensitivity, 94.44% specificity in the classification as normal or abnormal mammogram, and has achieved 94.4% accuracy, with 96.15% sensitivity and 94.54% specificity in the classification as Benign or Malignant mammogram.

show abstract

“…Morphological operations [6] are used to remove the noisy data, enhance and contrast the input image. Morphological operators are those applied on the binary image, before convert the gray image into binary image.…”

Section: Preprocessingmentioning

confidence: 99%

Breast Cancer Detection using Local Binary Patterns

Naresh¹,

Kumari²

2015

IJCA

View full text Add to dashboard Cite

Breast cancer is a leading cause of cancer type for death among women in most of popular countries, breast cancer detection is important and challenging role in worldwide to save women's life. Due to inexperience to detect cancer, the doctors and radio logistic can miss the abnormality, which leads to death. Mammography is the most used method for breast cancer detection used by the radiologists. In this experiment, the MIAS (Mammogram Image Analysis Society) database is used and the MIAS database consists of normal and abnormal type of 322 mammograms. The pre-processing is most important step to capture quality mammogram image for next study and processing in mammogram analysis. Texture analysis plays important role to identify normal and abnormal types. Texture feature extraction can be done by local binary patterns (LBP) operator and by using LBP we can consider only sign parameters, it may loss the some texture information. The local binary pattern is a rotation invariant approach for the texture analysis. In this experiment famous completed LBP (CLBP) method used for extracting texture features. Completed LBP considering the sign, magnitude and centre gray level values. By using the joint or hybrid distributions combine CLBP_Sign, CLBP_Magnitude and CLBP_Center gray level values.LBP is one type of Completed LBP for texture analysis, advantage of CLBP is rotation invariant. Finally extracted texture features can be trained and classified by using the SVM classifier for identifying the normal and abnormal cancer type.

show abstract

Detection of regions of interest's in mammograms by using local binary pattern, dynamic k-means algorithm and gray level co-occurrence matrix

Cited by 27 publications

References 8 publications

Computer-Aided Detection System for Breast Cancer Based on GMM and SVM

Computer-Aided Detection System for Breast Cancer Based on GMM and SVM

Automatic Diagnosing of Suspicious Lesions in Digital Mammograms

Breast Cancer Detection using Local Binary Patterns

Contact Info

Product

Resources

About