Density Based Breast Segmentation for Mammograms Using Graph Cut and Seed Based Region Growing Techniques

Objectives: Breast cancer is the most common cancer diagnosed in women, and microcalcification (MCC) clusters act as an early indicator. Thus, the detection of MCCs plays an important role in diagnosing breast cancer.Methods: This paper presents a methodology for mammogram preprocessing and MCC detection. The preprocessing method employs automatic artefact deletion and pectoral muscle removal based on region-growing segmentation and polynomial contour fitting. The MCC detection method uses a convolutional neural network for region-of-interest (ROI) classification, along with morphological operations and wavelet reconstruction to reduce false positives (FPs).Results: The methodology was evaluated using the mini-MIAS and UTP datasets in terms of segmentation accuracy in the preprocessing phase, as well as sensitivity and the mean FP rate per image in the MCC detection phase. With the mini-MIAS dataset, the proposed methods achieved accuracy scores of 99% for breast segmentation and 95% for pectoral segmentation, a sensitivity score of 82% for MCC detection, and an FP rate per image of 3.27. With the UTP dataset, the methods achieved accuracy scores of 97% for breast segmentation and 91% for pectoral segmentation, a sensitivity score of 78% for MCC detection, and an FP rate per image of 0.74.Conclusions: The proposed preprocessing method outperformed the state-of-the-art methods for breast segmentation and achieved relatively good results for pectoral muscle removal. Furthermore, the MCC detection module achieved the highest test accuracy in identifying potential ROIs with MCCs compared to other methods.

Download Full-text

COMPARISON OF ALGORITHMS FOR CONSTRUCTION DETECTION USING AIRBORNE LASER SCANNING AND NDSM CLASSIFICATION

Environment Technology Resources Proceedings of the International Scientific and Practical Conference ◽

10.17770/etr2019vol2.4032 ◽

2019 ◽

Vol 2 ◽

pp. 79

Author(s):

Sergejs Kodors

Keyword(s):

Laser Scanning ◽

Traditional Approach ◽

Region Growing ◽

Graph Cut ◽

Airborne Laser Scanning ◽

Surface Model ◽

Morphological Filter ◽

Height Difference ◽

Airborne Laser ◽

Cluster Methods

Traditional approach to classify the point cloud of airborne laser scanning is based on the processing of a normalized digital surface model (nDSM), when ground facilities are detected and classified. The main feature to detect a ground facility is height difference between adjacent points. The simplest method to extract a ground facility is region-growing algorithm, which applies threshold to identify the connection between two points. Region growing algorithm is working with the constant value of height difference. Therefore, it is not applicable due to diverse conditions of earth surface, when height difference must be defined for each region separately. As result, researchers propose hierarchical, statistical and cluster methods to solve this problem. The study goal is to compare four algorithms to generate nDSM: region growing, progressive morphological filter, adaptive TIN surfaces and graph-cut. The experiment is divided into two stages: 1) to calculate the number of detected and lost buildings in nDSM; 2) to measure the classification accuracy of extracted shapes. The experiment results have showed that progressive morphological filter and graph-cut provides the minimal loss of buildings (only 1%). The most effective algorithm for ground facility detection is the graph-cut (total accuracy 0.95, Cohen’s Kappa 0.89, F1 score 0.93).

Download Full-text