Association Rule Mining-Based Radiomics in Breast Cancer Diagnosis

Document Type : Original Paper


1 Pharmaceutical Research Center, Mashhad University of Medical Sciences, Mashhad, Iran

2 Department of Radiology and Biomedical Imaging, Yale School of Medicine, PO Box 208048, New Haven, CT, 06520-8048, USA.

3 Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran

4 Department of Radiation Physics, Division of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA


Introduction: Breast cancer is the most common cancer among women worldwide. Early detection of breast cancer reduces mortality and morbidity. Acquiring or identifying valuable information in the form of rules is the key to an accurate diagnosis and differentiation between benign and malignant breast cancers. Our goal is to find the hidden but beneficial knowledge in the form of rules from datasets. In this paper, we use association rule mining algorithms to obtain information in the form of data rules for differential diagnosis between benign and malignant breast masses based on radiomic features, extracted from mammography images.
Material and Methods: In this study, 703 patients with both benign and malignant tumors were selected from the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) database. The embedded method was employed to select the radiomic features of the image and uncover the hidden patterns of data through the Apriori algorithm.
Results: The association rules were generated from separated rules for benign and malignancy classes. The important features of the benign class include mass margins, horizontal long-run emphasis, 135drfraction, WavEnHLs3, vertical short-run emphasis, Teta1, 45dgr run-length with no uniformity, Teta2, and differential entropy2. However, the important features of the malignant class include assessment, correlation4, Teta1, WavEnLHs3, contrast5, vertical short-run emphasis, and differential entropy2.
Conclusion: It can be concluded that the proposed method has been successful in determining specific features for tumor prediction.


Main Subjects

  1. Rasti R, Teshnehlab M, Phung SL. Breast cancer diagnosis in DCI-MRI using mixture ensemble of convolutional neural networks. Pattern Recogn. 2017;72:38190.
  2. Devalapalli A, Thomas S, Mazurowski MA, Saha A, Grimm LJ. Performance of preoperative breast MRI based on breast cancer molecular subtype. Clin Imaging 2020;67:130–
  3. Lee MV, Konstantinoff K, Gegios A, Miles K, Appleton C, D Hui. Breast cancer malpractice litigation: A 10-year analysis and update in trends. Clin Imaging. 2020;60(1):26–
  4. Partovi S, Sin D, Lu Z, Sieck L, Marshall H, Pham R, et al. Fast MRI breast cancer screening – Ready for prime time. Clin Imaging 2020;60(2):160–
  5. Grubstein A, Rapson Y, Stemmer SM, Allweis T, Wolff-Bar M, Borshtein S, et al. Timing to imaging and surgery after neoadjuvant therapy for breast cancer. Clin Imaging 2021;71:24–
  6. Tsochatzidis L, Zagoris K, Arikidis N, Karahaliou A, Costaridou L, Pratikakis I. Computer-aided diagnosis of mammographic masses based on a supervised content-based image retrieval approach. Pattern Recogn. 2017;71:106–
  7. Jiao Z, Gao X, Wang Y, Li J: A parasitic metric learning net for breast mass classification based on mammography. Pattern Recogn. 2018;75:292–
  8. Elfarra BK, Abuhaiba IS. New feature extraction method for mammogram computer aided diagnosis. Int. J. Signal Processing, Image Processing and Pattern Recogn. 2013;6(1):13–
  9. Cao H, Bernard S, Sabourin R, Heutte L. Random forest dissimilarity based multi-view learning for Radiomics application. Pattern Recogn. 2019;88:185–
  10. Hajianfar G, shiri I, Maleki H, Haghparast A, Oveisi M. Advanced quantitative MRI radiomics features for recurrence prediction in glioblastoma multiform patients. Iran. J. Med. Phys. 2018, 15: 319.
  11. Abdollahi H, Shiri I, Mofid B, Razzaghdoust A, Sadipour A, Mahdavi S, et al. Prostate cancer radiomics: A study on IMRT response prediction based on MR image features and machine learning approaches. Iran. J. Med. Phys. 2018, 15: 337.
  12. Pesapane F, Rotili A, Agazzi GM, Botta F, Raimondi S, Penco S, et al. Recent Radiomics Advancements in Breast Cancer: Lessons and Pitfalls for the Next Future. Curr Oncol. 2021;28(4):2351-72.
  13. Bagherpour Z, Enferadi M, Reiazi M, Jajroudi M, Nafissi N, Mahdavi SR. Radiomics in IOERT of Unilateral Breast Cancer as a Biological Dosimetry. Iran. J. Med. Phys. 2022; 19(6).
  14. Oskouei RJ, Kor NM, Maleki SA. Data mining and medical world: breast cancers’ diagnosis, treatment, prognosis and challenges. Am. J. Cancer Res. 2017;7(3):610–
  15. Starikov A, Al'Aref SJ, Singh G, Min JK. Artificial intelligence in clinical imaging: An introduction. Clin Imaging. 2018;49:vii–
  16. Sogani J, Allen Jr B, Dreyer K, McGinty G. Artificial intelligence in radiology: the ecosystem essential to improving patient care. Clin Imaging. 2020;59(1):A3–
  17. Wang Q, Mao N, Liu M, Shi Y, Ma H, Dong J, et al. Radiomic analysis on magnetic resonance diffusion weighted image in distinguishing triple-negative breast cancer from other subtypes: a feasibility study. Clin Imaging. 2021;72:136–
  18. Jingle IB, Celin JJ: Enhanced algorithms for mining optimized positive and negative association rule from cancer dataset. ICTACT J. Soft. Comput. 2018;8(2):1583–
  19. Hu R. Medical data mining based on association rules. Comp. Inform. Sci. 2010;3(4):104–
  20. Ma W, Zhao Y, Ji Y, Guo X, Jian X, Liu P, et al. Breast cancer molecular subtype prediction by mammographic radiomics features. Acad. Radiol. 2019;26(2):196–
  21. Shah SZ, Amjad M. Using frequent itemset mining for breast cancer detection. Indian J. Sci. Technol. 2017; 10(9):1–
  22. Pala T, YÜCEDAĞ İ, Biberoğlu H. Association rule for classification of breast cancer patients. Sigma J. Eng. Nat. Sci. 2017;8(2):155–
  23. Karabatak M, Ince MC. An expert system for detection of breast cancer based on association rules and neural network. Exp. Syst. Appl. 2009;36(2):3465–
  24. The Cancer Imaging Archive (TCIA). 2021.
  25. Lee RS, Gimenez F, Hoogi A, Miyake KK, Gorovoy M, Rubin DL. A curated mammography data set for use in computer-aided detection and diagnosis research. Scientific data. 2017;4(1):1-9.
  26. Jantawan B, Tsai CF. A comparison of filter and wrapper approaches with data mining techniques for categorical variables selection. Int. J. Inno. Res. Comp. Comm. Engg. 2014;2(6):4501–
  27. Cunningham P, Delany SJ k-Nearest neighbour classifiers. Multiple Classifier Systems. 2007;34 (8):1–
  28. Nahar J, Tickle KS, Ali AS, Chen YP. Significant cancer prevention factor extraction: an association rule discovery approach. J. Med. Syst. 2011;35(3):353–
  29. Zhang C, Zhang S. Association rule mining: models and algorithms. Springer-Verlag; 2002.
  30. Ed-daoudy A, Maalmi K. Breast cancer classification with reduced feature set using association rules and support vector machine. Network Modeling Analysis in Health Informatics and Bioinformatics. 2020 Dec;9(1):34.
  31. Keyvanpour, MR,Barani Shirzad M, Mahdikhani L. WARM: a new breast masses classification method by weighting association rule mining. Signal, Image and Video Processing. 2022;16:481-8.
  32. Deshpande DS. A Novel Approach for Association Rule Mining using Pattern Generation. International Journal of Information Technology and Computer Science (IJITCS). 2014;6(11):59-65.
  33. Soulami KB, Kaabouch, N, Saidi MN. Breast cancer: Three‐class masses classification in mammograms using Apriori dynamic selection. Concurrency and Computation: Practice and Experience. 2022, 34(24):e7233