**3. Breast mass detection**

obtained from comparison between the query and retrieved images. The system performance is compared with other state-of-the-art algorithms where experimental results indicate that

**Figure 1** shows the dataflow diagram of the proposed integrated decision support system based on image pre-processing, mass segmentation, feature extraction, classification, and

The rest of the paper is organized as follows. Section 2 describes the related works, specially talk about the CAD-based CBIR systems for mammographic mass retrieval. The mass detection based on marker-controlled watershed segmentation and feature extraction are described in Sections 3 and 4 respectively. Our classification and similarity matching methods are described in Section 5, while all discussions on the obtained experimental results are given in

There is a clear need to create effective tools and techniques to search, browse and retrieve images from large repositories to aid diagnoses and research due to the phenomenal growth in recent years in the volume of digital mammograms produced in hospitals and clinical centers. Due to the freely available access to datasets of digital mammograms, such as the Digital Database for Screening Mammography (DDSM), interest in developing CAD schemes for mammograms that use CBIR has been attracting continued research interest during the last several years [20–22]. Although mammography-based CAD is one of the mature and widely adopted fields, there have been only a limited number of studies devoted to CBIR-based CAD systems for the detection and retrieval of breast masses in mammograms. Alto et al. [21] proposed the use of the shape, gradient, and texture features for mammography image retrieval

the framework achieved a noticeable increase in recognition rates.

**Figure 1.** Dataflow diagram of the integrated decision support system (DSS).

14 Medical Imaging and Image-Guided Interventions

Section 6. The last section comprises of conclusions.

**2. Background review**

retrieval.

The most challenging aspect in developing any CAD based systems for mammograms is to segment the suspicious masses, which are often hidden in dense breast tissues. Since a cancerous region might typically represented by local-oriented patterns, accurately segmenting it is an important first step for the effective performances of the successive feature extraction, similarity matching and classification steps in developing a CAD system as shown in **Figure 1**. A large number of segmentation methods have been proposed in the literature for the detection of breast masses, such as adaptive region growth [32], multi-layer topographic region growth algorithm [33], active contour (snake) modeling [34], level set algorithm [35], dynamic programming [36] etc. However, due to the limitation of benchmark evaluation and testing datasets to compare the performances, it is difficult to find the most robust and effective method in this domain till now.

#### **3.1. Visual saliency based segmentation**

The breast anatomy has a complicated structure because of the presence of pectoral muscles and the different mass density. Although it is easy to analyze breast tissues without getting confused with pectoral muscles for a radiologist, it is always difficult to distinguish between pectoral muscles and mass for an automatic method in a CAD system. For that reason, pectoral muscles are removed usually before the segmentation, which has a huge limitation as it is done manually in most cases [8, 15, 19]. However, automatic segmentation of pectoral muscle is a troublesome process and also an additional workload in analysis of mammography images in cranio-caudal (CC) view, which are generally without pectoral muscles.

activation maps. The function D in Eq. (2) maps to the value at location (*k*, *l*) in activation map

A Decision Support System (DSS) for Breast Cancer Detection Based on Invariant Feature…

where *A*(*p*, *q*) represents a node in the activation map. In final stage, normalized activation maps are combined using the sum rule to obtain the saliency map. Once the saliency map

*A*(*p*, *q*) (3)

http://dx.doi.org/10.5772/intechopen.81119

17

(Eq. (5)). The value of the parameter σ in Eq. (1) is 0.06 times the image width [38].

=

**Figure 2.** Saliency map generated from enhanced image and suspicious regions obtained after thresholding.

A

*D*

In this study, for example a graph-based visual saliency (GBVS) method [37] is utilized for segmentation by applying thresholding on the saliency map, which does not require the removal of pectoral muscles to detect the breast masses. The reason for choosing GBVS is that it has the ability of generating an output showing concentrated saliency maps in the appropriate image regions where the value of an image pixel location corresponds to the saliency of that pixel with respect to the neighbors. The usefulness of saliency models in cases where some structures are implicit with respect to the image such as pectoral muscles in mammograms is demonstrated in [19]. It is also experimentally shown that the GBVS yields the best results for mass detection from screening mammograms [37].

The GBVS calculates the saliency of a region with respect to its local neighborhood using the directional contrast. In mammography images, it has been monitored that the contrast of mass containing regions is significantly different from the remaining breast tissue. As discussed earlier, the mass encircled by dense tissues is difficult to recognize, whereas, the directional contrast with respect to the local neighborhood helps in identifying such masses along with the masses present in fatty regions. The computation of saliency map consists of following stages: Firstly, to differentiate mass from the neighboring regions in contrast, feature maps are computed from contrast values along four different orientations of 2D Gabor filters (0°, 45°, 90°, and 135°). Then, activation maps are computed as the balanced distribution of a Markov chain which is obtained using the initial feature maps [20]. The balanced distribution denotes higher weights only for the edges present in salient regions. The Ergodic Markov chains are modeled on a fully connected directed graph obtained from feature maps. Weighted connections are used to create the graph. It is created by connecting nodes in a feature map. The directed edge node (*i*, *j*) to node (*k*, *l*) weight is assigned in the graph.

$$w((i,j),(k,l)) \triangleq D \cdot F(i-k, j-l)\_{\prime} \tag{1}$$

where *F*(*a*, *b*) = A exp(− *a* <sup>2</sup> + *b*<sup>2</sup> \_\_\_\_\_ <sup>2</sup> *<sup>σ</sup>*<sup>2</sup> )

$$\mathbf{D} \triangleq \left| \log \left( \frac{M(i, j)}{M(p, q)} \right) \right| \tag{2}$$

where *M*(*i*, *j*) denotes a node in the feature map and σ is set to 0.15 times the image width.

Due to the fact that activation maps lack the accumulation of weights, a normalization of activation map is performed to avoid uniform saliency maps. Activation maps are normalized using a similar approach as used in the previous step. Markov chains are computed from the activation maps. The function D in Eq. (2) maps to the value at location (*k*, *l*) in activation map (Eq. (5)). The value of the parameter σ in Eq. (1) is 0.06 times the image width [38].

confused with pectoral muscles for a radiologist, it is always difficult to distinguish between pectoral muscles and mass for an automatic method in a CAD system. For that reason, pectoral muscles are removed usually before the segmentation, which has a huge limitation as it is done manually in most cases [8, 15, 19]. However, automatic segmentation of pectoral muscle is a troublesome process and also an additional workload in analysis of mammography images in cranio-caudal (CC) view, which are generally without pectoral muscles.

In this study, for example a graph-based visual saliency (GBVS) method [37] is utilized for segmentation by applying thresholding on the saliency map, which does not require the removal of pectoral muscles to detect the breast masses. The reason for choosing GBVS is that it has the ability of generating an output showing concentrated saliency maps in the appropriate image regions where the value of an image pixel location corresponds to the saliency of that pixel with respect to the neighbors. The usefulness of saliency models in cases where some structures are implicit with respect to the image such as pectoral muscles in mammograms is demonstrated in [19]. It is also experimentally shown that the GBVS yields the best results for

The GBVS calculates the saliency of a region with respect to its local neighborhood using the directional contrast. In mammography images, it has been monitored that the contrast of mass containing regions is significantly different from the remaining breast tissue. As discussed earlier, the mass encircled by dense tissues is difficult to recognize, whereas, the directional contrast with respect to the local neighborhood helps in identifying such masses along with the masses present in fatty regions. The computation of saliency map consists of following stages: Firstly, to differentiate mass from the neighboring regions in contrast, feature maps are computed from contrast values along four different orientations of 2D Gabor filters (0°, 45°, 90°, and 135°). Then, activation maps are computed as the balanced distribution of a Markov chain which is obtained using the initial feature maps [20]. The balanced distribution denotes higher weights only for the edges present in salient regions. The Ergodic Markov chains are modeled on a fully connected directed graph obtained from feature maps. Weighted connections are used to create the graph. It is created by connecting nodes in a feature map. The directed edge node (*i*, *j*) to node (*k*, *l*) weight is assigned in the graph.

=


where *M*(*i*, *j*) denotes a node in the feature map and σ is set to 0.15 times the image width.

Due to the fact that activation maps lack the accumulation of weights, a normalization of activation map is performed to avoid uniform saliency maps. Activation maps are normalized using a similar approach as used in the previous step. Markov chains are computed from the

*M*(*i*, *j*) \_\_\_\_\_\_

=

A

<sup>A</sup> *<sup>D</sup>* <sup>⋅</sup> *<sup>F</sup>*(*<sup>i</sup>* <sup>−</sup> *<sup>k</sup>*, *<sup>j</sup>* <sup>−</sup> *<sup>l</sup>*), (1)

*<sup>M</sup>*(*p*, *<sup>q</sup>*))<sup>|</sup> (2)

mass detection from screening mammograms [37].

16 Medical Imaging and Image-Guided Interventions

*w*((*i*, *j*), (*k*, *l*))

*a* <sup>2</sup> + *b*<sup>2</sup> \_\_\_\_\_ <sup>2</sup> *<sup>σ</sup>*<sup>2</sup> )

D

where *F*(*a*, *b*)

=

A exp(−

$$D \stackrel{\mathbf{A}}{=} A(p, q) \tag{3}$$

where *A*(*p*, *q*) represents a node in the activation map. In final stage, normalized activation maps are combined using the sum rule to obtain the saliency map. Once the saliency map

**Figure 2.** Saliency map generated from enhanced image and suspicious regions obtained after thresholding.

is computed, a threshold is empirically selected to obtain the optimal size ROIs. **Figure 2** illustrates some examples of saliency maps generated from pre-processed images and ROI segmentation from the saliency maps.

the structure proposed in [21]. Additionally, the multi-scale and directional decomposition processes are free from each other. The number of decomposition directions is changeable

1 ⩽ j ⩽ J and J represents the number of decomposition scales. Different from the classical CT, all subbands of NSCT have the same resolution. That means, the NSCT coefficients of each subband are in one-to-one correspondence with the original surface in the spatial domain. For feature extraction, a combination of k mean, variance, energy, entropy, skewness, and kurtosis parameters from 4-level non-sampled contourlet transform is examined. An example of the NSCT for a mass is shown in **Figure 3**. The image is decomposed into four pyramidal

The HOG is computed for each key point from a block. The key point denotes the center of the central cell of the block. The adjacent area of each key point is partitioned into cells. Onedimensional histogram of gradient orientations is accumulated for each cell. The histogram of all the cells generates the feature of all key points [22, 46]. A simple 1-D [−1; 0; 1] mask is used

*j*

A Decision Support System (DSS) for Breast Cancer Detection Based on Invariant Feature…

parameter can be represented at scale *j*,

http://dx.doi.org/10.5772/intechopen.81119

19

where the *l*

*j*

and can be adjusted to any value of 2*<sup>l</sup>*

**4.2. Eig(Hess)-HOG features**

levels, resulting in one, two and eight sub-bands.

**Figure 3.** Non-sampled Contourlet transform of an ROI with four-level decomposition.
