Abstract
Purpose
Mammography is an important imaging technique for the detection of early breast cancer. Doctors classify mammograms as Breast Imaging Reporting and Data Systems (BI-RADS). This study aims to provide an intelligent BI-RADS grading prediction method, which can help radiologists and clinicians to distinguish the most challenging 4A, 4B, and 4C cases in mammography.
Methods
Firstly, the breast region, the lesion region, and the corresponding region in the contralateral breast were extracted. Four categories of features were extracted from the original images and the images after the wavelet transform. Secondly, an optimized sequential forward floating selection (SFFS) was used for feature selection. Finally, a two-layer classifier integration was employed for fine grading prediction. 45 cases from the hospital and 500 cases from Digital Database for Screening Mammography (DDSM) database were used for evaluation.
Results
The classification performance of the support vector machine (SVM), Bayes, and random forest is very close on the 45 testing set, with the area under the receiver operating characteristic curve (AUC) of 0.978, 0.967, and 0.968. On the DDSM set, the AUC achieves 0.931, 0.938, and 0.874. Using the mean probability prediction, the AUC on the two datasets reaches 0.998 and 0.916. However, they are all significantly higher than the doctors’ diagnosis, with the AUC of 0.807 and 0.725.
Conclusions
A BI-RADS fine grading (2, 3, 4A, 4B, 4C, 5) prediction model was proposed. Through the evaluation from different datasets, the performance is proved higher than that of the doctors, which may provide great help for clinical BI-RADS classification diagnosis. Therefore, our method can produce more effective and reliable results.
Similar content being viewed by others
References
Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A (2018) Global cancer statistics 2018: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 68(6):394–424. https://doi.org/10.3322/caac.21492
Roberto A, Colombo C, Candiani G, Giordano L, Mantellini P, Paci E, Satolli R, Valenza M, Mosconi P (2017) Personalised informed choice on evidence and controversy on mammography screening: study protocol for a randomized controlled trial. BMC Cancer 17(1):429. https://doi.org/10.1186/s12885-017-3428-9
Navarro Vilar L, Alandete Germán SP, Medina García R, Blanc García E, Camarasa Lillo N, Vilar Samper J (2017) Mr imaging findings in molecular subtypes of breast cancer according to birads system. Breast J 23(4):421–428. https://doi.org/10.1111/tbj.12756
Lévy L, Suissa M, Bokobsa J, Tristant H, Chiche JF, Martin B, Teman G (2005) Présentation de la traduction française du bi-rads®(breast imaging reporting system and data system). Gynécologie Obstétrique & Fertilité 33(5):338–347. https://doi.org/10.1016/j.gyobfe.2005.04.006
Thawkar S (2021) A hybrid model using teaching-learning-based optimization and salp swarm algorithm for feature selection and classification in digital mammography. J Amb Intell Human Comput. https://doi.org/10.1007/s12652-020-02662-z
Mohanty F, Rup S, Dash B, Majhi B, Swamy MNS (2020) An improved scheme for digital mammogram classification using weighted chaotic salp swarm algorithm-based kernel extreme learning machine. Appl Soft Comput 91:106266. https://www.sciencedirect.com/science/article/pii/S1568494620302064
Kelder A, Lederman D, Zheng B, Zigel Y (2018) A new computer-aided detection approach based on analysis of local and global mammographic feature asymmetry. Med Phys 45(4):1459–1470. https://doi.org/10.1002/mp.12806
Li Y, Fan M, Cheng H, Zhang P, Zheng B, Li L (2018) Assessment of global and local region-based bilateral mammographic feature asymmetry to predict short-term breast cancer risk. Phys Med Biol 63(2):025004. https://doi.org/10.1088/1361-6560/aaa096
Tan M, Pu J, Zheng B (2014) Optimization of breast mass classification using sequential forward floating selection (sffs) and a support vector machine (svm) model. Int J Comput Assist Radiol Surg 9(6):1005–1020. https://doi.org/10.1007/s11548-014-0992-1
Milosevic M, Jankovic D, Peulic A (2015) Comparative analysis of breast cancer detection in mammograms and thermograms. Biomed Eng Biomedizinische Technik 60(1):49–56. https://doi.org/10.1515/bmt-2014-0047
Suresh A, Udendhran R, Balamurgan M (2020) Hybridized neural network and decision tree based classifier for prognostic decision making in breast cancers. Soft Comput 24(11):7947–7953. https://doi.org/10.1007/s00500-019-04066-4
Uzunhisarcikli E, Goreke V (2018) A novel classifier model for mass classification using bi-rads category in ultrasound images based on type-2 fuzzy inference system. Sādhanā 43(9):138. https://doi.org/10.1007/s12046-018-0915-x
Miranda GHB, Felipe JC (2015) Computer-aided diagnosis system based on fuzzy logic for breast cancer categorization. Comput Biol Med 64:334–346. https://www.sciencedirect.com/science/article
Domingues I, Abreu PH, Santos J (2018) Bi-rads classification of breast cancer: a new pre-processing pipeline for deep models training. In: 2018 25th IEEE international conference on image processing (ICIP), pp 1378–1382. https://ieeexplore.ieee.org/document/8451510
Chokri F, Hayet Farida M (2017) Mammographic mass classification according to bi-rads lexicon. IET Comput Vis 11(3):189–198. https://doi.org/10.1049/iet-cvi.2016.0244
Boumaraf S, Liu X, Ferkous C, Ma X (2020) A new computer-aided diagnosis system with modified genetic feature selection for bi-rads classification of breast masses in mammograms. BioMed Res Int 2020:7695207. https://doi.org/10.1155/2020/7695207
Wirth MA, Choi C, Jennings A (1999) A nonrigid-body approach to matching mammograms. In: 7th International conference on image processing and its applications, pp 484–488. https://schlr.cnki.net/Detail/doi/WWMERGECLAST/SPGI15070600006717
Zhang L, Fried DV, Fave XJ, Hunter LA, Yang J, Court LE (2015) ibex: An open infrastructure software platform to facilitate collaborative work in radiomics. Med Phys 42(3):1341–1353. https://doi.org/10.1118/1.4908210
Aerts HJWL, Velazquez ER, Leijenaar RTH, Parmar C, Grossmann P, Carvalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D, Hoebers F, Rietbergen MM, Leemans CR, Dekker A, Quackenbush J, Gillies RJ, Lambin P (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5(1):4006. https://doi.org/10.1038/ncomms5006
Song J, Liu Z, Zhong W, Huang Y, Ma Z, Dong D, Liang C, Tian J (2016) Non-small cell lung cancer: quantitative phenotypic analysis of ct images as a potential marker of prognosis. Sci Rep 6(1):38282. https://doi.org/10.1038/srep38282
Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3(6):610–621. https://doi.org/10.1109/tsmc.1973.4309314
Soh L, Tsatsoulis C (1999) Texture analysis of sar sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sens 37(2):780–795. https://doi.org/10.1109/36.752194
Clausi DA (2002) An analysis of co-occurrence texture statistics as a function of grey level quantization. Can J Remote Sens 28(1):45–62. https://doi.org/10.5589/m02-004
Thibault G (2009) Indices de forme et de texture: de la 2d vers la 3d: application au classement de noyaux de cellules. Thesis, http://www.theses.fr/2009AIX22014
Galloway MM (1975) Texture analysis using gray level run lengths. Comput Graphics Image Process 4(2):172–179. https://www.sciencedirect.com/science/article/pii/S0146664X75800086
Chu A, Sehgal CM, Greenleaf JF (1990) Use of gray value distribution of run lengths for texture analysis. Patt Recogn Lett 11(6):415–419. https://www.sciencedirect.com/science/article/pii/016786559090112F
Dasarathy BV, Holder EB (1991) Image characterizations based on joint gray level-run length distributions. Patt Recogn Lett 12(8):497–502. https://www.sciencedirect.com/science/article/pii/0167865591800142
Thibault G, Fertil B, Navarro L Claire, Pereira S, Cau P, Lévy N, Sequeira J, Mari JL (2009) Texture indexes and gray level size zone matrix. application to cell nuclei classification. In: 10th International conference on pattern recognition and information processing, PRIP 2009, pp 140–145. https://hal.archives-ouvertes.fr/hal-01499715
Jiang M, Han L, Sun H, Li J, Bao N, Li H, Zhou S, Yu T (2021) Cross-modality image feature fusion diagnosis in breast cancer. Phys Med Biol 66(10):105003. https://doi.org/10.1088/1361-6560/abf38b
Pashaei E, Ozen M, Aydin N (2016) Biomarker discovery based on bbha and adaboostm1 on microarray data for cancer classification. In: 2016 38th annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp 3080–3083. https://ieeexplore.ieee.org/document/7591380
Subash Chandra Bose S, Sivanandam N, Praveen Sundar PV (2020) Design of ensemble classifier using statistical gradient and dynamic weight logitboost for malicious tumor detection. J Amb Intell Human Comput. https://doi.org/10.1007/s12652-020-02295-2
Vani A, Saravanan V (2019) Tanimoto gaussian kernelized feature extraction based multinomial gentleboost machine learning for multi-spectral aerial image classification. Int J Innov Technol Explor Eng 8(10S):208–216. https://doi.org/10.35940/ijitee.j1036.08810s19
Wu S, Nagahashi H (2015) Analysis of generalization ability for different adaboost variants based on classification and regression trees. J Elect Comput Eng 2015:835357. https://doi.org/10.1155/2015/835357
Tan M, Pu J, Cheng S, Liu H, Zheng B (2015) Assessment of a four-view mammographic image feature based fusion model to predict near-term breast cancer risk. Ann Biomed Eng 43(10):2416–2428. https://doi.org/10.1007/s10439-015-1316-5
Acknowledgements
This work was supported by the Guizhou Province Science and Technology Project under Grant Qiankehezhicheng [2019] 2794, the Fundamental Research Funds for the Central Universities under Grant N2119003, 2017 young and middle-aged scientific and technological innovation talent support plan under Grant [RC170497], Guiyang Science and Technology Plan under Grant [2017] 30-34, National Natural Science Foundation of China (NSFC) under Grant 61701103, and Natural Science Foundation of Liaoning Province under Grant 2019-ZD-0005.
Funding
This work was supported by the Guizhou Province Science and Technology Project under Grant Qiankehezhicheng [2019] 2794, the Fundamental Research Funds for the Central Universities under Grant N2119003, 2017 young and middle-aged scientific and technological innovation talent support plan under Grant [RC170497], Guiyang Science and Technology Plan under Grant [2017] 30-34, National Natural Science Foundation of China (NSFC) under Grant 61701103, and Natural Science Foundation of Liaoning Province under Grant 2019-ZD-0005.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. All authors read and approved the final manuscript.
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lin, F., Sun, H., Han, L. et al. An effective fine grading method of BI-RADS classification in mammography. Int J CARS 17, 239–247 (2022). https://doi.org/10.1007/s11548-021-02541-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-021-02541-8