Anomaly classification in digital mammography based on multiple‐instance learning

Elmoufidi, Abdelali; Fahssi, Khalid El; Andaloussi, Said Jai; Sekkaki, Abderrahim; Quellec, Gwénolé; Lamard, Mathieu

doi:10.1049/iet-ipr.2017.0536

Cited by 41 publications

(20 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The usage of neural networks is an option that has been widely explored, but the results obtained from this author's work are lower than the one achieved by the proposed methodology. Elmoufidi et al (2017) proposed a feature vector which contains a combination of several families of texture and shape features. Five algorithms are implemented in their study: The first MIL solutions were mi-SVM and MI-SVM, which generalize the popular supervised SVM, diverse density, axis-parallel rectangles (APR), and MILBoost, which generalizes the popular ensemble classifiers in that context.…”

Section: Comparison With State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Classification of breast masses in mammograms using geometric and topological feature maps and shape distribution

et al. 2020

View full text Add to dashboard Cite

Purpose Breast cancer is the second most common cancer in the world, being more common among women and representing 24.2% of new cases each year. Mammography is currently the best technique for early detection of non-palpable breast lesions. Due to the need to create new more computationally efficient techniques, this paper presents a methodology for mass classification from mammographic images based on their geometric and topological features. Methods For each image, two spatial feature maps named distance map and surface map are computed. These features describe the mass geometry and topology, respectively. Also, shape descriptors based on distances histograms are used to characterize the shape of the masses. The purpose of this comparison is to discriminate its malignancy and benignity patterns. The high-boost filter is applied to enhance the masses, since the difference between them and the breast tissue or other components of them is very subtle. Mammograms digitized from the Digital Database for Screening Mammography (DDSM) were used for the testing of this methodology, corresponding to 794 ROIs that were separated into groups by density, according to BI-RADS classification. Results The best results for accuracy, sensitivity, and specificity were 93.70%, 96.29%, and 91.05%, respectively, for density 2 and 90.18%, 91.01%, and 89.94% for all images. Conclusion The results obtained demonstrate that the sets of features successfully discriminate mass standards, even with the exceptions and obstacles that characterize and classify the masses through their shape.

show abstract

Section: Comparison With State Of the Artmentioning

confidence: 99%

“…For the case of the 261 mammograms from the MIAS database, an Az value of 0.85 was obtained for the diagnosis of malignant tumors. Elmoufidi et al (2017) proposed to partition the mammogram into regions and from the detected ROIs. For each region, texture features and shape features were derived.…”

Section: Introductionmentioning

confidence: 99%

Classification of breast masses in mammograms using geometric and topological feature maps and shape distribution

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In [8], a new technique for partitioning the breast adaptively into regions was proposed, and multiple‐instance learning (MIL) algorithm was employed to recognise abnormal regions, achieving an accuracy of 94.6%. The MIL algorithm was also employed in the CAD system of [9] to classify ROIs extracted by the K ‐means algorithm as benign or malignant. A CAD system consisting of homomorphic filtering, local seed region growing, and spherical wavelet transform [10] was developed to detect and classify benign and malignant breast masses with a maximum accuracy of 96%.…”

Section: Introductionmentioning

confidence: 99%

Fully automated scheme for computer‐aided detection and breast cancer diagnosis using digitised mammograms

Eltrass

Salama

2020

IET Image Processing

View full text Add to dashboard Cite

“…In [13], ROI regions are located and extracted on the basis of the maximally inscribed circle and centroid methods. In addition, an algorithm automatically generates a class number that can partition mammogram into the best areas as ROI rigions can be found in [14]. Similarly, an algorithm that uses tetrolet filter to reduce the speckle noise and the active contour method based on statistical features to automatically segment breast lesions to obtain an ROI can be found in [15].…”

Section: Introductionmentioning

confidence: 99%

Fuzzy-rough assisted refinement of image processing procedure for mammographic risk assessment

Qi-lin

Shang

et al. 2020

Applied Soft Computing

View full text Add to dashboard Cite

The use of computer aided diagnosis (CAD) systems, which are computer based tools for the automatic analysis of medical images such as mammogram and prostate MRI, can assist in the early detection and diagnosis of developing cancer. In the process of CAD for mammogram, the task of image processing (IP) plays a fundamental role in providing promising diagnostic results, by exploiting high-quality features extracted from the mammographic images. Normally, an IP procedure for mammographic images involves three mechanisms: region of interest (ROI) extraction, image enhancement (IE) and feature extraction (FE). However, an improper utilisation of IE may lead to an inferior composition of the features due to unexpected enhancement of any irrelevant or useless information in ROI. In order to overcome this problem, a fuzzy-rough refined IP (FRIP) framework is presented in this paper to improve the quality of mammographic image features hierarchically. Following the proposed framework, the ROI of each mammographic image is segmented and enhanced locally in the area of the block which is of the highest value of fuzzy positive region (FPR). Here, FPR implies a positive dependency relationship between the block and the decision with regard to the given feature set. The higher a block's FPR value the more certain its underlying image category. To attain a high quality of the image enhancement procedure, the winner block will be further improved by a multi-round strategy to create a pool of IE results. As such, for a mammographic image,

show abstract

Anomaly classification in digital mammography based on multiple‐instance learning

Cited by 41 publications

References 69 publications

Classification of breast masses in mammograms using geometric and topological feature maps and shape distribution

Classification of breast masses in mammograms using geometric and topological feature maps and shape distribution

Fully automated scheme for computer‐aided detection and breast cancer diagnosis using digitised mammograms

Fuzzy-rough assisted refinement of image processing procedure for mammographic risk assessment

Contact Info

Product

Resources

About