Approaches for automated detection and classification of masses in mammograms

Cheng, Heng-Da; Shi, Xiangjun; Min, Rui; Liang, Hu; Cai, Xiaopeng; Du, Hongyue

doi:10.1016/j.patcog.2005.07.006

Cited by 478 publications

(259 citation statements)

References 141 publications

Supporting

Mentioning

251

Contrasting

Unclassified

Order By: Relevance

“…Each of the proposed features needs some special kind of preprocessing steps. For instance, circularity, contrast, and average gray level measures need segmentation [9]. Zernike moments [3], [4], [14] need segmentation, co-scaling using NRL vector and translation.…”

Section: A Preprocessing and Segmentationmentioning

confidence: 99%

“…The proposed eleven features tabulated in Table I can cover all the BI-RADS categories. Circularity [9] and Zernike moments [3], [4], [14] are proper descriptors of mass shape. The NRL derivatives [5], [15] and SpI [16] are appropriate descriptors of mass margin.…”

Section: B Feature Extraction and Selectionmentioning

confidence: 99%

“…The NRL derivatives [5], [15] and SpI [16] are appropriate descriptors of mass margin. Moreover, contrast and average gray level [9] are suitable descriptors of mass density. Note that the order and iteration of utilized Zernike moments have been chosen so that they can represent a good descrimination between benign and malignant masses.…”

Section: B Feature Extraction and Selectionmentioning

confidence: 99%

“…Early detection of breast cancer increases the survival rate as well as the treatment options [2]. Mammography has been one of the most reliable methods for early detection and diagnosis of breast cancers [9]. Some of the important signs of breast cancer that radiologists look for are clusters of micro-calcifications, masses, and architectural distortions [2], [3].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Classification of Breast Masses based on Cognitive Resonance

Tahmasbi¹,

Saki²,

Amirkhani³

et al. 2012

IJCEE

View full text Add to dashboard Cite

Section: A Preprocessing and Segmentationmentioning

confidence: 99%

Section: B Feature Extraction and Selectionmentioning

confidence: 99%

Section: B Feature Extraction and Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Breast Masses based on Cognitive Resonance

Tahmasbi¹,

Saki²,

Amirkhani³

et al. 2012

IJCEE

View full text Add to dashboard Cite

“…Early detection is an effective way to control the disease [2]. Breast ultrasound (BUS) imaging has become one of the most prevalent and popular approaches for breast cancer diagnosis due to the fact that it is radiation-free, noninvasive, painless, cost-effective, and portable.…”

Section: Introductionmentioning

confidence: 99%

An Effective Approach of Lesion Segmentation Within the Breast Ultrasound Image Based on the Cellular Automata Principle

et al. 2012

View full text Add to dashboard Cite

In this paper, a novel lesion segmentation within breast ultrasound (BUS) image based on the cellular automata principle is proposed. Its energy transition function is formulated based on global image information difference and local image information difference using different energy transfer strategies. First, an energy decrease strategy is used for modeling the spatial relation information of pixels. For modeling global image information difference, a seed information comparison function is developed using an energy preserve strategy. Then, a texture information comparison function is proposed for considering local image difference in different regions, which is helpful for handling blurry boundaries. Moreover, two neighborhood systems (von Neumann and Moore neighborhood systems) are integrated as the evolution environment, and a similarity-based criterion is used for suppressing noise and reducing computation complexity. The proposed method was applied to 205 clinical BUS images for studying its characteristic and functionality, and several overlapping area error metrics and statistical evaluation methods are utilized for evaluating its performance. The experimental results demonstrate that the proposed method can handle BUS images with blurry boundaries and low contrast well and can segment breast lesions accurately and effectively.

show abstract

Breast cancer: A hybrid method for feature selection and classification in digital mammography

Thawkar

Katta

Parashar

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

In this article, a hybrid approach based on the Whale optimization algorithm (WOA) and the Dragonfly algorithm (DA) is proposed for breast cancer diagnosis. The hybrid WOADA method selects features based on the fitness value. These features are used to predict the breast masses as benign or malignant using artificial neural networks (ANN) and adaptive neuro‐fuzzy inference systems (ANFIS) as classifiers. The proposed solution is evaluated by using 651 mammograms. The results demonstrate that the WOADA technique outperforms the basic WOA and DA approaches. The accuracy of the suggested WOADA algorithm is 97.84%, with a Kappa value of 0.9477 and an AUC value of 0.972 ± 0.007 for the ANN classifier. Likewise, the ANFIS classifier achieved 98.00% accuracy with a Kappa value of 0.96 and an AUC value of 0.998 ± 0.001. In addition, the viability of the hybrid WOADA technique was evaluated on four benchmark datasets and then compared with four state‐of‐the‐art algorithms and published approaches.

show abstract

Approaches for automated detection and classification of masses in mammograms

Cited by 478 publications

References 141 publications

Classification of Breast Masses based on Cognitive Resonance

Classification of Breast Masses based on Cognitive Resonance

An Effective Approach of Lesion Segmentation Within the Breast Ultrasound Image Based on the Cellular Automata Principle

Breast cancer: A hybrid method for feature selection and classification in digital mammography

Contact Info

Product

Resources

About