Healthc Inform Res.  2021 Jul;27(3):222-230. 10.4258/hir.2021.27.3.222.

Automatic Pectoral Muscle Removal and Microcalcification Localization in Digital Mammograms

Affiliations
  • 1Automatics Research Group, Faculty of Engineering, Universidad Tecnológica de Pereira (UTP), Risaralda, Colombia
  • 2Data Analysis and Computational Sociology Research Group, Faculty of Engineering, Universidad Tecnológica de Pereira (UTP), Risaralda, Colombia

Abstract


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.

Keyword

Machine Learning, Breast Neoplasms, Classification, Calcinosis, Diagnosis

Figure

  • Figure 1 Artefact removal steps. (A) Original image (I). (B) Binary image (B). (C) Binary frame (F). (D) After applying B ⊗ F and retaining the largest object (Bf). (E) After applying I ⊗ Bf. (F) Preprocessed image (J).

  • Figure 2 Steps 1 and 2 for pectoral muscle removal. (A) Artefact removal from the image (J). (B) Image flipping (JF). (C) Background estimation (BG); in this case, MPIV = 251. (D) After applying (JF − BG) to remove structures different from the pectoral muscle (P).

  • Figure 3 Steps 3 and 4 for pectoral muscle suppression. (A) Region-growing segmentation after perimeter fitting (Bp). (B) Pectoral muscle segmentation (BFp). (C) After applying JF ○ Bp, suppression of the pectoral muscle (Ip).

  • Figure 4 Third-order polynomial pectoral contour fitting.

  • Figure 5 Microcalcification enhancement. (A) Original ROI IROI. (B) After subtracting the background (IRBG). (C) After wavelet enhancement I′RBG. (D) After binarizing I′RBG.

  • Figure 6 Microcalcification detection result.


Reference

References

1. Kwan ML, Kushi LH, Weltzien E, Maring B, Kutner SE, Fulton RS, et al. Epidemiology of breast cancer subtypes in two prospective cohort studies of breast cancer survivors. Breast Cancer Res. 2009; 11(3):R31.
Article
2. Raba D, Oliver A, Marti J, Peracaula M, Espunya J. Breast segmentation with pectoral muscle suppression on digital mammograms. Marques JS, Perez de la Blanca N, Pina P, editors. Iberian conference on pattern recognition and image analysis. Springer Berlin, Heidelberg, Germany: Springer;2005. p. 471–8.
Article
3. Linguraru MG, Marias K, English R, Brady M. A biologically inspired algorithm for microcalcification cluster detection. Med Image Anal. 2006; 10(6):850–62.
Article
4. Elshinawy MY, Abdelmageed WW, Badawy AH, Chouikha MF. Pre-CAD system for normal mammogram detection using local binary pattern features. In : Proceedings of 2010 IEEE 23rd international Symposium on Computer-Based Medical Systems (CBMS); 2010 Oct 12–15; Bentley, Australia. p. 352–7.
Article
5. Karale VA, Ebenezer JP, Chakraborty J, Singh T, Sadhu A, Khandelwal N, et al. A screening CAD tool for the detection of microcalcification clusters in mammograms. J Digit Imaging. 2019; 32(5):728–45.
Article
6. Giger ML, Karssemeijer N, Schnabel JA. Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer. Annu Rev Biomed Eng. 2013; 15:327–57.
Article
7. Moghbel M, Ooi CY, Ismail N, Hau YW, Memari N. A review of breast boundary and pectoral muscle segmentation methods in computer-aided detection/diagnosis of breast mammography. Artif Intell Rev. 2020; 53(3):1873–918.
Article
8. Ancy CA, Nair LS. Tumour classification in graph-cut segmented mammograms using GLCM features-fed SVM. Bhateja V, Coello Coello C, Satapathy S, Pattnaik P, editors. Intelligent engineering informatics. Singapore: Springer;2018. p. 197–208.
Article
9. Rahimeto S, Debelee TG, Yohannes D, Schwenker F. Automatic pectoral muscle removal in mammograms. Evol Syst. 2019; 12:519–26.
Article
10. Karale VA, Singh T, Sadhu A, Khandelwal N, Mukhopadhyay S. Reduction of false positives in the screening CAD tool for microcalcification detection. Sadhana. 2020; 45:44.
Article
11. Chan HP, Sahiner B, Lam KL, Petrick N, Helvie MA, Goodsitt MM, et al. Computerized analysis of mammographic microcalcifications in morphological and texture feature spaces. Med Phys. 1998; 25(10):2007–19.
Article
12. Leichter I, Lederman R, Buchbinder S, Bamberger P, Novak B, Fields S. Optimizing parameters for computer-aided diagnosis of microcalcifications at mammography. Acad Radiol. 2000; 7(6):406–12.
Article
13. Tsujii O, Freedman MT, Mun SK. Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network. Pattern Recognit. 1999; 32(5):891–903.
Article
14. Betal D, Roberts N, Whitehouse GH. Segmentation and numerical analysis of microcalcifications on mammograms using mathematical morphology. Br J Radiol. 1997; 70(837):903–17.
Article
15. Paquerault S, Yarusso LM, Papaioannou J, Jiang Y, Nishikawa RM. Radial gradient-based segmentation of mammographic microcalcifications: observer evaluation and effect on CAD performance. Med Phys. 2004; 31(9):2648–57.
Article
16. Kim JK, Park HW. Statistical textural features for detection of microcalcifications in digitized mammograms. IEEE Trans Med Imaging. 1999; 18(3):231–8.
17. Soltanian-Zadeh H, Rafiee-Rad F. Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms. Pattern Recognit. 2004; 37(10):1973–86.
Article
18. Qayyum A, Basit A. Automatic breast segmentation and cancer detection via SVM in mammograms. In : Proceedings of 2016 International Conference on Emerging Technologies (ICET); 2016 Oct 18–19; Islamabad, Pakistan. p. 1–6.
Article
19. Slavkovic-Ilic M, Gavrovska A, Milivojevic M, Reljin I, Reljin B. Breast region segmentation and pectoral muscle removal in mammograms. Telfor J. 2016; 8(1):50–5.
Article
20. Yoon WB, Oh JE, Chae EY, Kim HH, Lee SY, Kim KG. Automatic detection of pectoral muscle region for computer-aided diagnosis using MIAS mammograms. Biomed Res Int. 2016; 2016:5967580.
Article
21. Camilus KS, Govindan VK, Sathidevi PS. Computer-aided identification of the pectoral muscle in digitized mammograms. J Digit Imaging. 2010; 23(5):562–80.
Article
22. Abdellatif H, Taha TE, Zahran OF, Al-Nauimy W, Abd El-Samie FE. K2. Automatic pectoral muscle boundary detection in mammograms using eigenvectors segmentation. In : Proceedings of 2012 29th National Radio Science Conference (NRSC);; 2012 Apr 10ă12; Cairo, Egypt. p. 633–40.
Article
23. Shinde V, Rao BT. Novel approach to segment the pectoral muscle in the mammograms. Mallick P, Balas V, Bhoi A, Zobaa A, editors. Cognitive informatics and soft computing. Singapore: Springer;2019. p. 227–37.
Article
24. El-Naqa I, Yang Y, Wernick MN, Galatsanos NP, Nishikawa RM. A support vector machine approach for detection of microcalcifications. IEEE Trans Med Imaging. 2002; 21(12):1552–63.
Article
25. Liu X, Mei M, Liu J, Hu W. Microcalcification detection in full-field digital mammograms with PFCM clustering and weighted SVM-based method. EURASIP J Adv Signal Process. 2015; 2015:73.
Article
26. Wang J, Nishikawa RM, Yang Y. Global detection approach for clustered microcalcifications in mammograms using a deep learning network. J Med Imaging (Bellingham). 2017; 4(2):024501.
Article
27. Wang J, Yang Y. A context-sensitive deep learning approach for microcalcification detection in mammograms. Pattern Recognit. 2018; 78:12–22.
Article
28. Alam N, Oliver A, Denton ER, Zwiggelaar R. Automatic segmentation of microcalcification clusters. Nixon M, Mahmoodi S, Zwiggelaar R, editors. Medical image understanding and analysis. Cham, Switzerland: Springer;2018. p. 251–61.
Article
29. McCann J, Stockton D, Godward S. Impact of false-positive mammography on subsequent screening attendance and risk of cancer. Breast Cancer Res. 2002; 4(5):R11.
Article
Full Text Links
  • HIR
Actions
Cited
CITED
export Copy
Close
Share
  • Twitter
  • Facebook
Similar articles
Copyright © 2024 by Korean Association of Medical Journal Editors. All rights reserved.     E-mail: koreamed@kamje.or.kr