scholarly journals Automatic Pectoral Muscles Detection and Removal in Mammogram Images

2021 ◽  
pp. 676-688
Author(s):  
Sarah Siham Fadhil ◽  
Faten Abed Ali Dawood
Keyword(s):  
Pectoral Muscle ◽  
Accurate Diagnosis ◽  
Second Step ◽  
Median Filtering ◽  
Computer Aided Detection ◽  
Local Thresholding ◽  
Otsu Method ◽  
Region Extraction ◽  
Pectoral Muscle Detection ◽  
Mammogram Images

The main aim of the Computer-Aided Detection/Diagnosis system is to assist the radiologists in examining the digital mammograms. Digital mammogram is the most popular screening technique for early detection of breast cancer. One of the problems in breast mammogram analysis is the presence of pectoral muscles region with high intensity in the upper right or left side of most Media-Lateral Oblique views of mammogram images. Therefore, it is important to remove this pectoral muscle from the image for accurate diagnosis results. The proposed method consists of three main steps. In the first step, noise is reduced using Median filtering. In the second step, artifacts removal and breast region extraction are performed using Otsu method. Finally, the pectoral muscle is extracted and removed using the proposed Split Orientation Local Thresholding (SOLTH) algorithm. For this study, a total of 110 mammogram images from the Mini-Mias database (MIAS) were used to evaluate the proposed method’s performance. The experimental results of automatic pectoral muscle detection and removal were observed by radiologist and showed 90.9% accuracy of acceptable results.

REGION-BASED CONTRAST ENHANCEMENT OF DIGITAL MAMMOGRAMS USING AN IMPROVED WATERSHED SEGMENTATION

2013 ◽  
Vol 13 (01) ◽  
pp. 1350007 ◽  
Author(s):  
ABUBACKER KAJA MOHIDEEN ◽  
KUTTIANNAN THANGAVEL
Keyword(s):  
Contrast Enhancement ◽  
Absolute Error ◽  
Pectoral Muscle ◽  
Histogram Equalization ◽  
Classification Performance ◽  
Performance Measure ◽  
Watershed Segmentation ◽  
Muscle Region ◽  
Edge Based ◽  
Mammogram Images

A simple edge-based preprocessing scheme is proposed in this paper for contrast enhancement of digital mammogram images while preserving the edges more accurately. This proposed method has three steps: (i) initially the breast region is segmented from the mammogram images by removing the film artifacts, (ii) the pectoral muscle region is identified and excluded from the breast region using a novel adaptive thresholding method, and (iii) an Improved Watershed Segmentation (IWS) is applied to segment the breast profile, and each region is enhanced with simple histogram equalization. The segmentation is performed in order to achieve adaptive contrast enhancement. The performance of this proposed pectoral removal method is analyzed with two measures: Hausdorff Distance (HD) and Mean of Absolute Error Distance (MAED), and the proposed contrast enhancement approach is been analyzed with the five diverse parameters along with the classification accuracy. The experiments and results show the potential performance of our proposed algorithm over the existing approaches with optimum results on all the performance measure and the classification performance is been evaluated with a hybrid neural network, our proposed method proves the better performance with the achievement of 92% accuracy.

scholarly journals Improved Threshold Based and Trainable Fully Automated Segmentation for Breast Cancer Boundary and Pectoral Muscle in Mammogram Images

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 203097-203116
Author(s):  
Dilovan Asaad Zebari ◽  
Diyar Qader Zeebaree ◽  
Adnan Mohsin Abdulazeez ◽  
Habibollah Haron ◽  
Haza Nuzly Abdull Hamed
Keyword(s):  
Breast Cancer ◽  
Pectoral Muscle ◽  
Automated Segmentation ◽  
Mammogram Images

Removal of Pectoral Muscle Region in Digital Mammograms using Binary Thresholding

2012 ◽  
Vol 2 (3) ◽  
pp. 21-29 ◽  
Author(s):  
A. Kaja Mohideen ◽  
K. Thangavel
Keyword(s):  
Binary Operation ◽  
Distance Measure ◽  
Absolute Error ◽  
Pectoral Muscle ◽  
Density Region ◽  
Muscle Region ◽  
Pectoral Region ◽  
The Mean ◽  
Error Distance ◽  
Mammogram Images

The pectoral muscle represents a predominant density region in Medio-Lateral Oblique (MLO) views of mammograms, which appears at approximately the same density as the dense tissues of interest in the image and can affect the results of image analysis methods. Therefore, segmentation of pectoral muscle is important in order to limit the search for the breast abnormalities only to the breast region. In this paper, a simple and effective approach is proposed to exclude the pectoral muscle based on binary operation. The performance is analyzed by the Hausdorff Distance Measure (HDM) and also the Mean of Absolute Error Distance Measure (MAEDM) based on differences between the results received from the radiologists and by the proposed method. The digital mammogram images are taken from MIAS dataset which contains 322 images in total, out of which the proposed algorithm able to detect and remove the pectoral region from 291 images successfully.

Thresholding Techniques for Dental Radiographic Images

2019 ◽  
pp. 40-61
Author(s):  
Arockia Sukanya ◽  
Kamalanand Krishnamurthy
Keyword(s):  
Early Detection ◽  
Imaging Techniques ◽  
Accurate Diagnosis ◽  
Diagnostic Process ◽  
Radiographic Images ◽  
Fundamental Step ◽  
Local Thresholding ◽  
Otsu’S Method ◽  
Global Thresholding ◽  
Natural Way

Imaging techniques play a major role in improving the early detection and diagnostic process that helps dentists to make accurate diagnosis. One of the most useful medical images used by dentists is radiographic image, which is used for the treatment of various dental disorders. Segmentation is a fundamental step as it involves separation of an image into regions corresponding to the objects. A simple and natural way to segment such regions is through thresholding. In this chapter, various thresholding techniques such as Otsu's method for global thresholding and Niblack's, Bersen's, and Sauvola's techniques for local thresholding are extensively explained with the help of dental radiographic images.

scholarly journals Deep Learning Based Pectoral Muscle Segmentation on MIAS Mammograms

2020 ◽  
Author(s):  
Young Jae Kim ◽  
Eun Young Yoo ◽  
Kwang Gi Kim
Keyword(s):  
Breast Cancer ◽  
Image Processing ◽  
Deep Learning ◽  
Cross Validation ◽  
Pectoral Muscle ◽  
Training Data ◽  
Dice Similarity Coefficient ◽  
Detection Accuracy ◽  
Pectoral Muscle Detection ◽  
Fold Cross Validation

Abstract Background: The purpose of this study was to propose a deep learning-based method for automated detection of the pectoral muscle, in order to reduce misdetection in a computer-aided diagnosis (CAD) system for diagnosing breast cancer in mammography. This study also aimed to assess the performance of the deep learning method for pectoral muscle detection by comparing it to an image processing-based method using the random sample consensus (RANSAC) algorithm. Methods: Using the 322 images in the Mammographic Image Analysis Society (MIAS) database, the pectoral muscle detection model was trained with the U-Net architecture. Of the total data, 80% was allocated as training data and 20% was allocated as test data, and the performance of the deep learning model was tested by 5-fold cross validation. Results: The image processing-based method for pectoral muscle detection using RANSAC showed 92% detection accuracy. Using the 5-fold cross validation, the deep learning-based method showed a mean sensitivity of 95.55%, mean specificity of 99.88%, mean accuracy of 99.67%, and mean Dice similarity coefficient (DSC) of 95.88%. Conclusions: The proposed deep learning-based method of pectoral muscle detection performed better than an existing image processing-based method. In the future, by collecting data from various medical institutions and devices to further train the model and improve its reliability, we expect that this model could greatly reduce misdetection rates by CAD systems for breast cancer diagnosis.

A Survey on Machine Learning Algorithms for the Diagnosis of Breast Masses with Mammograms

2020 ◽  
Vol 16 (6) ◽  
pp. 639-652
Author(s):  
Vaira Suganthi Gnanasekaran ◽  
Sutha Joypaul ◽  
Parvathy Meenakshi Sundaram
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Low Cost ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Computer Aided Detection ◽  
Breast Masses ◽  
Cad System ◽  
The Past ◽  
Mammogram Images

Breast cancer is leading cancer among women for the past 60 years. There are no effective mechanisms for completely preventing breast cancer. Rather it can be detected at its earlier stages so that unnecessary biopsy can be reduced. Although there are several imaging modalities available for capturing the abnormalities in breasts, mammography is the most commonly used technique, because of its low cost. Computer-Aided Detection (CAD) system plays a key role in analyzing the mammogram images to diagnose the abnormalities. CAD assists the radiologists for diagnosis. This paper intends to provide an outline of the state-of-the-art machine learning algorithms used in the detection of breast cancer developed in recent years. We begin the review with a concise introduction about the fundamental concepts related to mammograms and CAD systems. We then focus on the techniques used in the diagnosis of breast cancer with mammograms.

Sign in / Sign up

Export Citation Format

Share Document