**6.3. Classification results**

As mentioned, the classification accuracies in different feature sets of **Table 1** are compared and with both SVM and ELM classifier and it was found out that the *f* 1 feature set with ELM classifier is the most effective feature set in terms of accuracy, sensitivity, specificity both two and three class study. For example, **Tables 2** and **3** demonstrate the results for both 2- and 3- class studies for the *f* 1 and *f* 3 feature sets respectively.

From **Tables 2** and **3**, it can be observed that *f* 1 feature set is more effective than *f* 3 feature set in terms of accuracy, sensitivity, specificity both two and three class study. In fact, *f* 1 feature set with ELM as classifier achieved the highest classification accuracy rate in terms of mean accuracy, sensitivity and specificity parameters after 10-fold CV as shown in **Table 4**.

The classification efficiency, training and testing the performances of SVM and ELM were compared independently. As shown in **Table 4**, it can be seen that the proposed methods are effective on the DDSM database and ELM is a highly-effective classification technique


**Table 1.** Utilized different types of feature sets.


for this task. It is also proved to be highly efficient as lesser computational time was required

**Table 5** shows the comparison between our proposed system and a number of state-of-the-art classification systems. For the DDSM database, our classification system obtained comparable performance in accuracy, sensitivity and specificity. The promising results might be owing to

the good segmentation algorithm as well as the effective feature extraction methods.

compared to SVM with same sets but of different training data sizes.

**Table 4.** Performance comparisons of SVM and ELM classifiers using different features.

**2 class 3 class**

**Table 3.** Classification performance of *f*

**Fold # Accuracy Sensitivity Specificity Accuracy Sensitivity Specificity** Fold 1 95.0417 95.3549 95.0417 91.6464 89.7668 92.3773 Fold 2 94.7807 95.9812 95.1983 91.1939 91.3679 91.1939 Fold 3 95.2505 95.0939 94.9895 91.2287 92.5513 91.6812 Fold 4 95.4592 97.1816 96.2421 92.1685 98.8512 99.0078 Fold 5 95.9290 96.2421 97.7035 98.6945 99.3212 98.8512 Fold 6 96.2421 94.5720 96.7640 98.1723 98.4334 98.0157 Fold 7 98.3298 98.0167 92.9018 98.2768 99.1645 92.0668 Fold 8 94.4676 94.1544 93.3194 93.3194 92.6931 91.2317 Fold 9 94.2588 94.1544 95.9290 91.1274 92.0668 91.3361 Fold 10 93.4238 91.6492 92.9018 94.1545 94.1545 92.2756 Ave 95.2192 96.7223 93.7161 91.5176 98.6789 92.4426

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

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

25

<sup>3</sup> feature set for the 2 and 3 class study.

2 class ELM Mean accuracy 96.973 95.709 95.219 93.742 92.228 94.665

3 class ELM Mean accuracy 92.415 92.318 91.517 79.547 78.092 85.788

**Measures** *f***<sup>1</sup>** *f***<sup>2</sup>** *f***<sup>3</sup>** *f***<sup>4</sup>** *f***<sup>5</sup>** *f***<sup>6</sup>**

SVM Mean accuracy 94.086 92.015 94.427 91.536 90.341 91.852

SVM Mean accuracy 90.125 89.654 89.884 76.004 74.011 83.256

Mean sensitivity 95.548 97.223 96.722 96.743 97.421 99.853 Mean specificity 94.123 94.196 93.716 90.741 87.035 89.478

Mean sensitivity 93.824 95.357 93.118 94.124 94.117 96.741 Mean specificity 91.216 92.628 90.240 88.687 84.896 86.224

Mean sensitivity 98.361 98.877 98.678 98.642 97.409 99.357 Mean specificity 93.479 91.691 92.442 83.016 83.528 93.152

Mean sensitivity 95.244 94.519 95.331 94.875 92.546 95.446 Mean specificity 89.886 87.359 90.214 79.954 80.820 89.744

**Table 2.** Classification performance of *f*<sup>1</sup> feature set for the 2 and 3 class study. A Decision Support System (DSS) for Breast Cancer Detection Based on Invariant Feature… http://dx.doi.org/10.5772/intechopen.81119 25


**Table 3.** Classification performance of *f* <sup>3</sup> feature set for the 2 and 3 class study.

**6.3. Classification results**

24 Medical Imaging and Image-Guided Interventions

3- class studies for the *f*

*f* **Feature set**

<sup>4</sup> NSCT

*f*

*f*

*f*

*f*

*f*

*f*

**Table 2.** Classification performance of *f*<sup>1</sup>

1 and *f* 3

From **Tables 2** and **3**, it can be observed that *f*

<sup>1</sup> Shape, Mass, GLCM, NSCT, eig(Hess)HOG

<sup>2</sup> Shape, Mass, GLCM, NSCT

<sup>5</sup> NSCT, eig(Hess)HOG

<sup>6</sup> eig(Hess)HOG

<sup>3</sup> Shape, Mass, GLCM, eig(Hess)HOG

**Table 1.** Utilized different types of feature sets.

As mentioned, the classification accuracies in different feature sets of **Table 1** are compared

classifier is the most effective feature set in terms of accuracy, sensitivity, specificity both two and three class study. For example, **Tables 2** and **3** demonstrate the results for both 2- and

1

set with ELM as classifier achieved the highest classification accuracy rate in terms of mean

The classification efficiency, training and testing the performances of SVM and ELM were compared independently. As shown in **Table 4**, it can be seen that the proposed methods are effective on the DDSM database and ELM is a highly-effective classification technique

feature sets respectively.

in terms of accuracy, sensitivity, specificity both two and three class study. In fact, *f*

accuracy, sensitivity and specificity parameters after 10-fold CV as shown in **Table 4**.

1

feature set is more effective than *f*

feature set with ELM

3

feature set

1 feature

and with both SVM and ELM classifier and it was found out that the *f*

**2 class 3 class**

**Fold # Accuracy Sensitivity Specificity Accuracy Sensitivity Specificity** Fold 1 98.0167 96.5553 95.0939 86.1817 92.8298 92.7950 Fold 2 97.7035 95.8768 94.0501 94.1176 92.5861 93.5955 Fold 3 96.7641 95.5637 94.3633 93.5607 92.7602 92.5513 Fold 4 97.7035 95.9290 94.1545 93.1778 97.7035 98.9039 Fold 5 96.9729 94.6159 94.2589 97.7035 98.4342 98.0689 Fold 6 97.4948 95.9812 94.4676 98.7474 98.5386 98.6952 Fold 7 96.9729 95.8768 94.7808 98.5908 98.2255 91.3271 Fold 8 97.3904 96.2422 95.0939 92.6854 94.3574 95.7158 Fold 9 97.4948 97.0856 94.6764 94.1484 92.4765 92.8945 Fold 10 97.3904 95.6681 93.9457 93.4169 93.9394 93.8349 Ave 96.9729 95.5480 94.1232 92.4155 98.3612 93.4796

feature set for the 2 and 3 class study.


**Table 4.** Performance comparisons of SVM and ELM classifiers using different features.

for this task. It is also proved to be highly efficient as lesser computational time was required compared to SVM with same sets but of different training data sizes.

**Table 5** shows the comparison between our proposed system and a number of state-of-the-art classification systems. For the DDSM database, our classification system obtained comparable performance in accuracy, sensitivity and specificity. The promising results might be owing to the good segmentation algorithm as well as the effective feature extraction methods.

#### **6.4. Retrieval results**

A precision–recall curve based on our similarity fusion approach of different feature sets (*f* 1 –*f* 6 ) is shown in **Figure 7**, which represents that *f* 1 feature set outperform the all other feature sets in terms of precision and recall. **Figure 8** shows that, when *f* 1 feature set are used, the cancer masses are the most discriminative among three types of masses.

**Figure 9** shows an example of a query image from benign category and retrieved images based

the query image and from the same direction (right). However, the views of top retrieved image are different where images 2, 3, 4 and 5 (left to right and top to bottom) are from MLO view while the others are from CC view. Another example of retrieval is demonstrated in

feature set. The system retrieved all the top eight images from the same category of

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

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

27

feature set on three different mass types of mass lesions.

1

feature set.

on the *f* 1

**Figure 8.** Performance evaluation of *f*

1

**Figure 9.** Retrieval example of one benign query of our proposed system using the *f*

The results verify that the characteristic of breast masses was better represented by the *f* 1 feature set, which was able to capture the difference between the gray level intensities of the breast densities. Concerning *f* 1 feature set, for a 4% of recall, a precision of 96% means that from 5880 mammogram images returned by the our proposed CBIR system, 5644 were relevant.


**Table 5.** Classification performance of different methods.

**Figure 7.** Performance evaluation of six feature sets on similar mass retrieval.

**Figure 9** shows an example of a query image from benign category and retrieved images based on the *f* 1 feature set. The system retrieved all the top eight images from the same category of the query image and from the same direction (right). However, the views of top retrieved image are different where images 2, 3, 4 and 5 (left to right and top to bottom) are from MLO view while the others are from CC view. Another example of retrieval is demonstrated in

**6.4. Retrieval results**

breast densities. Concerning *f*

is shown in **Figure 7**, which represents that *f*

26 Medical Imaging and Image-Guided Interventions

**Table 5.** Classification performance of different methods.

**Figure 7.** Performance evaluation of six feature sets on similar mass retrieval.

in terms of precision and recall. **Figure 8** shows that, when *f*

1

masses are the most discriminative among three types of masses.

A precision–recall curve based on our similarity fusion approach of different feature sets (*f*

1

The results verify that the characteristic of breast masses was better represented by the *f*

ture set, which was able to capture the difference between the gray level intensities of the

5880 mammogram images returned by the our proposed CBIR system, 5644 were relevant.

**Literature Database Classifier Accuracy (%) Sensitivity Specificity**

Wang et al. [16] DDSM SVM 92.74 — — Liu and Tang [17] DDSM SVM 93.00 92.00 92.00 Dong et al. [18] DDSM GA-SVM 93.24 94.78 91.76 Jen and Yu [19] DDSM ADC — 86.0 84.0 Wei et al. [30] DDSM ELM 95.73 — — Rouhi et al. [50] DDSM MLP 95.01 96.25 93.78 Jiao et al. [51] DDSM CNN 96.7 — — Proposed scheme DDSM ELM 96.973 95.548 94.123 1 –*f* 6 )

1 fea-

feature set outperform the all other feature sets

feature set are used, the cancer

1

feature set, for a 4% of recall, a precision of 96% means that from

**Figure 8.** Performance evaluation of *f* 1 feature set on three different mass types of mass lesions.

**Figure 9.** Retrieval example of one benign query of our proposed system using the *f* 1 feature set.

expert radiologist is still considered necessary for the overall visual assessment of the breast mass and the final diagnosis, based on the objective evaluation suggested by the system and

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

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

29

contextual information from the patient data.

Mahmudur Rahman\* and Nuh Alpaslan

\*Address all correspondence to: md.rahman@morgan.edu

Radiology and Surgery. 2013;**8**(4):561-574

Department of Computer Science, Morgan State University, Baltimore, MD, USA

[1] Na. American Cancer Society published second edition of global cancer atlas. Oncology

[2] Al Mousa DS et al. Mammographic density and cancer detection. Academic Radiology.

[3] Siegel RL, Miller KD, Jemal A. Cancer statistics, 2015. CA: A Cancer Journal for Clinicians.

[4] Moura DC, Guevara López MA. An evaluation of image descriptors combined with clinical data for breast cancer diagnosis. International Journal of Computer Assisted

[5] Jotwani A, Gralow J. Early detection of breast cancer. Molecular Diagnosis & Therapy.

[6] Demircioğlu Ö, Uluer M, Arıbal E. How many of the biopsy decisions taken at inexperienced breast radiology units were correct? The Journal of Breast Health. 2017;**13**(1):23-

[7] Ganesan K, Acharya UR, Chua CK, Min LC, Abraham KT, Ng K-H. Computer-aided breast cancer detection using mammograms: A review. IEEE Reviews in Biomedical

[8] Rangayyan RM, Ayres FJ, Leo Desautels JE. A review of computer-aided diagnosis of breast cancer: Toward the detection of subtle signs. Journal of the Franklin Institute.

[9] De Santo M, Molinara M, Tortorella F, Vento M. Automatic classification of clustered microcalcifications by a multiple expert system. Pattern Recognition. 2003;**36**:1467-1477

[10] Zhang Y, Tomuro N, Furst J, Raicu DS. Building an ensemble system for diagnosing masses in mammograms. International Journal of Computer Assisted Radiology and

**Author details**

**References**

Times. 2015;**37**:34

2014;**21**:1377-1385

2009;**13**(6):349-357

26. DOI: 10.5152/tjbh.2016.2962

Engineering. 2013;**6**:77-98

Surgery. 2011;**7**:323-329

2007;**344**:312-348

2015;**65**:5-29

**Figure 10.** Retrieval example of one cancer query of our proposed system using the *f* 1 feature set.

**Figure 10**, using an image of cancer category. All the retrieved images are from the same category of the query image and from the same direction (right); however from both MLO (images, 2, 4, 7) and CC views. This might occur due to the fact that the ROI selected from these MLO images contains a good portion of pectoral muscle that was confused with the white part of the breast density.

The proposed system was implemented using the MATLAB through its image processing toolbox. Feature extraction and image retrieval were performed on an Intel i7 2.9 GHz processor with 8 GB of RAM under Microsoft Windows operating system.
