Open AccessJournal Article
Pre-processing Algorithms on Digital Mammograms
TL;DR: One low-pass mask for detecting breast contour and a new method for the identification of the pectoral muscle in most medio-lateral oblique mammograms based on Non-Linear Diffusion algorithm which is an edge preserving smoother are proposed.
read more
Abstract: Mammography is the best method for early mass detection. In order to limit the search for abnormalities by Computer Aided Diagnosis systems to the region of the breast without undue influence from the background of the mammogram, extraction of the breast contour and pectoral muscle is necessary. Breast contour helps to find the position of the nipple, which its position is important for mass detection in the next stages and presence of pectoral muscle in the mammogram could bias the detection procedures. So during analysis, the pectoral muscle should preferably be excluded from processing. In this paper we propose one low-pass mask for detecting breast contour and a new method for the identification of the pectoral muscle in most medio-lateral oblique mammograms based on Non-Linear Diffusion algorithm which is an edge preserving smoother. Evaluation of the breast contour and pectoral muscle detected in the mammograms were performed by the Hausdorff Distance Measure (HDM) and also the Mean of Absolute Error Distance Measure (MAEDM) based on a distance transform and image algebra between the edges identified by radiologists and by the proposed methods. Then we compare our results by other segmentation methods. Our proposed algorithms show superior results in comparison.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Review of recent advances in segmentation of the breast boundary and the pectoral muscle in mammograms
TL;DR: The most often used methods for segmentation such as thresholding, morphology, region growing, active contours, and wavelet filtering are addressed and are the ones most used in the last decade by the majority of work published in this image processing domain.
A review of breast boundary and pectoral muscle segmentation methods in computer-aided detection/diagnosis of breast mammography
TL;DR: The most effective pre-processing, image enhancement and segmentation concepts proposed for breast boundary and pectoral muscle segmentation are identified and discussed in hopes of aiding the readers with identifying the best possible solutions for these segmentation problems.
58
Breast segmentation using k-means algorithm with a mixture of gamma distributions
Abdu Gumaei,Ali El-Zaart,Muhamad Hussien,M.A. Berbar +3 more
- 28 May 2012
TL;DR: Exploiting Gamma distribution for modeling the k-mean method, an efficient technique for the segmentation of mammograms showed improvement in the accuracy of breast segmentation for breast cancer detection.
21
An algorithm for pre-processing and segmentation of mammogram images
Naglaa S. Ali Ibrahim,Naglaa F. Soliman,Mahmoud Abd-Allah,Fathi E. Abd El-Samie +3 more
- 01 Dec 2016
TL;DR: An algorithm is presented, which assists the radiologists identifying breast tumors at their early stages using morphological operations, and then it enhances contrast of mammogram images using the Band Limited Histogram Equalization (BLHE) method for easier detection of lesions or tumors.
20
The Effect of Mammogram Preprocessing on Microcalcification Detection with Convolutional Neural Networks
Agnese Marchesi,Alessandro Bria,Claudio Marrocco,Mario Molinara,Jan-Jurre Mordang,Francesco Tortorella,Nico Karssemeijer +6 more
- 01 Jun 2017
TL;DR: This work investigates the influence of preprocessing of digital mammograms on the microcalcification detection performance of two CNNs inspired by the popular AlexNet and VGGnet and finds that the square-root transform was superior to those obtained with the log transform.
17
References
•Book
Multiple view geometry in computer vision
Richard Hartley,Andrew Zisserman +1 more
- 01 Jan 2000
TL;DR: In this article, the authors provide comprehensive background material and explain how to apply the methods and implement the algorithms directly in a unified framework, including geometric principles and how to represent objects algebraically so they can be computed and applied.
20.1K
Scale-space and edge detection using anisotropic diffusion
Pietro Perona,Jitendra Malik +1 more
TL;DR: A new definition of scale-space is suggested, and a class of algorithms used to realize a diffusion process is introduced, chosen to vary spatially in such a way as to encourage intra Region smoothing rather than interregion smoothing.
A non-local algorithm for image denoising
Antoni Buades,Bartomeu Coll,Jean-Michel Morel +2 more
- 20 Jun 2005
TL;DR: A new measure, the method noise, is proposed, to evaluate and compare the performance of digital image denoising methods, and a new algorithm, the nonlocal means (NL-means), based on a nonlocal averaging of all pixels in the image is proposed.
Comparing images using the Hausdorff distance
TL;DR: Efficient algorithms for computing the Hausdorff distance between all possible relative positions of a binary image and a model are presented and it is shown that the method extends naturally to the problem of comparing a portion of a model against an image.
4.7K
The curvelet transform for image denoising
TL;DR: In this paper, the authors describe approximate digital implementations of two new mathematical transforms, namely, the ridgelet transform and the curvelet transform, which offer exact reconstruction, stability against perturbations, ease of implementation, and low computational complexity.