access icon free Novel breast cancer classification framework based on deep learning

© The Institution of Engineering and Technology
Received 25/01/2020, Accepted 30/06/2020, Revised 10/05/2020, Published 24/08/2020

AbstractBreast cancer is a major cause of transience amongst women. In this paper, two novel techniques, ResNet50 and VGG-16, are utilised and re-trained to recognise two classes rather than 1000 classes with high accuracy and low computational requirements. In addition, transfer learning and data augmentation are performed to solve the problem of lack of tagged data. To get a better accuracy, the support vector machine (SVM) classifier is utilised instead of the last fully connected layer. Our models performance are verified utilising k-fold cross-validation. Our proposed techniques are trained and evaluated on three mammographic datasets: mammographic image analysis society, digital database for screening mammography (DDSM) and the curated breast imaging subset of DDSM. This paper explains end-to-end fully convolutional neural networks without any prepossessing or post-processing. The proposed technique of employing ResNet50 hybridised with SVM achieves the best performance, specifically with the DDSM dataset, producing 97.98% accuracy, 98.46% area under the curve, 97.63% sensitivity, 96.51% precision, 95.97% F1 score and computational time 1.8934 s.

Inspec keywords: cancer; learning (artificial intelligence); convolutional neural nets; image classification; support vector machines; mammography; pattern classification; feature extraction; medical image processing

Other keywords: SVM; DDSM dataset; screening mammography; end-to-end fully convolutional neural networks; digital database; mammographic image analysis society; deep learning; tagged data; low computational requirements; ResNet50; models performance; computational time; breast cancer classification framework; support vector machine classifier; transfer learning; curated breast imaging subset; mammographic datasets; data augmentation; cross-validation; fully connected layer

Subjects: Neural computing techniques; Biology and medical computing; Data handling techniques; X-rays and particle beams (medical uses); Patient diagnostic methods and instrumentation; Knowledge engineering techniques; Optical, image and video signal processing; X-ray techniques: radiography and computed tomography (biomedical imaging/measurement); Computer vision and image processing techniques

References

    1. 1)
      • 12. Rampun, A., Scotney, B.W., Morrow, P.J., et al: ‘Breast mass classification in mammograms using ensemble convolutional neural networks’. 2018 IEEE 20th Int. Conf. on e-Health Networking, Applications and Services (Healthcom), Ostrava, Czach Republic, 2018, pp. 1–6.
    2. 2)
      • 10. Jiao, Z., Gao, X., Wang, Y., et al: ‘A deep feature based framework for breast masses classification’, Neurocomputing, 2016, 197, pp. 221–231.
    3. 3)
      • 20. Sun, C., Shrivastava, A., Singh, S., et al: ‘Revisiting unreasonable effectiveness of data in deep learning era’. Proc. of the IEEE Int. Conf. on Computer Vision, Venice, Italy, 2017, pp. 843–852.
    4. 4)
      • 3. Maniecka-Bryła, I., Bryła, M., Bryła, P., et al: ‘The burden of premature mortality in Poland analysed with the use of standard expected years of life lost’, BMC Public Health, 2015, 15, (1), p. 101.
    5. 5)
      • 25. Available at: https://www.repository.cam.ac.uk/handle/1810/250394, Accessed 7 June 2019.
    6. 6)
      • 4. Hubbard, R.A., Kerlikowske, K., Flowers, C.I., et al: ‘Cumulative probability of false-positive recall or biopsy recommendation after 10 years of screening mammography: a cohort study’, Ann. Intern. Med., 2011, 155, (8), pp. 481–492.
    7. 7)
      • 15. Shin, H.C., Roth, H.R., Gao, M., et al: ‘Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning’, IEEE Trans. Med. Imaging, 2016, 35, (5), pp. 1285–1298.
    8. 8)
      • 11. Ting, F.F., Tan, Y.J., Sim, K.S.: ‘Convolutional neural network improvement for breast cancer classification’, Expert Syst. Appl., 2019, 120, pp. 103–115.
    9. 9)
      • 6. Arevalo, J., González, F.A., Ramos-Pollán, R., et al: ‘Representation learning for mammography mass lesion classification with convolutional neural networks’, Comput. Methods Programs Biomed., 2016, 127, pp. 248–257.
    10. 10)
      • 2. Saslow, D., Boetes, C., Burke, W., et al: ‘American cancer society guidelines for breast screening with MRI as an adjunct to mammography’, CA-Cancer J. Clin., 2007, 57, (2), pp. 75–89.
    11. 11)
      • 14. Ragab, D.A., Sharkas, M., Marshall, S., et al: ‘Breast cancer detection using deep convolutional neural networks and support vector machines’, PeerJ, 2019, 7, p. p. e6201.
    12. 12)
      • 19. Lee, R.S., Gimenez, F., Hoogi, A., et al: ‘A curated mammography data set for use in computer-aided detection and diagnosis research’, Sci. Data, 2017, 4, p. 170177.
    13. 13)
      • 5. Tsochatzidis, L., Costaridou, L., Pratikakis, I.: ‘Deep learning for breast cancer diagnosis from mammograms – A comparative study’, J. Imaging, 2019, 5, (3), p. 37.
    14. 14)
      • 30. Yu, S., Liu, L.L., Wang, Z.Y., et al: ‘Transferring deep neural networks for the differentiation of mammographic breast lesions’, Science China Technological Sciences, 2019, 62, (3), pp. 441–447.
    15. 15)
      • 23. Long, M., Cao, Y., Cao, Z., et al: ‘Transferable representation learning with deep adaptation networks’, IEEE Trans. Pattern Anal. Mach. Intell., 2018, 41, (12), pp. 3071–3085.
    16. 16)
      • 22. Flusser, J., Suk, T.: ‘Pattern recognition by affine moment invariants’, Pattern Recognit., 1993, 26, (1), pp. 167–174.
    17. 17)
      • 16. Ballester, P., Araujo, R.M.: ‘On the performance of GoogLeNet and AlexNet applied to sketches’. 13th AAAI Conf. on Artificial Intelligence, Phoenix, AZ, USA, 2016.
    18. 18)
      • 26. Available at: https://wiki.cancerimagingarchive.net/display/Public/CBIS-DDSM, Accessed 1 June 2019.
    19. 19)
      • 24. Available at: http://marathon.csee.usf.edu/Mammography/Database.html, Accessed 5 June 2019.
    20. 20)
      • 21. Wong, S.C., Gatt, A., Stamatescu, V., et al: ‘Understanding data augmentation for classification: when to warp?’. 2016 Int. Conf. on Digital Image Computing: IEEE Techniques and Applications (DICTA), Gold Coast, Queensland, Australia, 2016, pp. 1–6.
    21. 21)
      • 28. Lévy, D., Jain, A.: ‘Breast mass classification from mammograms using deep convolutional neural networks’, arXiv preprint arXiv:1612.00542, 2016.
    22. 22)
      • 1. Siegel, R.L., Miller, K.D., Jemal, A.: ‘Cancer statistics, 2015’, CA-Cancer J. Clin., 2015, 65, (1), pp. 5–29.
    23. 23)
      • 17. Dai, J., Li, Y., He, K., et al: ‘R-fcn: object detection via region-based fully convolutional networks’, Adv. Neural. Inf. Process. Syst. (NIPS 2016), Barcelona, Spain, 2016, pp. 379–387.
    24. 24)
      • 8. Huynh, B.Q., Li, H., Giger, M.L.: ‘Digital mammographic tumor classification using transfer learning from deep convolutional neural networks’, J. Med. Imaging, 2016, 3, (3), p. 034501.
    25. 25)
      • 13. Vijayarajan, R., Muttan, S.: ‘Discrete wavelet transform based principal component averaging fusion for medical images’, AEU-Int. J. Electron. Commun., 2015, 69, (6), pp. 896–902.
    26. 26)
      • 27. Stone, M.: ‘Cross-validatory choice and assessment of statistical predictions’, J. R. Stat. Soc.: Series B (Methodol.), 1974, 36, pp. 111–147.
    27. 27)
      • 9. Available at: http://www.eurekaselect.com/node/171972/article/breast-infrared-thermography-segmentation-based-on-adaptive-tuning-of-a-fully convolutional-network (Accessed July 2019).
    28. 28)
      • 18. Russakovsky, O., Deng, J., Su, H., et al: ‘Imagenet large scale visual recognition challenge’, Int. J. Comput. Vision, 2015, 115, (3), pp. 211–252.
    29. 29)
      • 7. Moura, D.C., López, M.A.G., Cunha, P., et al: ‘Benchmarking datasets for breast cancer computer-aided diagnosis (CADx)’. Iberoamerican Congress on Pattern Recognition, Springer, Berlin, Heidelberg, 2013, pp. 326–333.
    30. 30)
      • 29. Jiang, F., Liu, H., Yu, S., et al: ‘Breast mass lesion classification in mammograms by transfer learning’. Proc. of the 5th Int. Conf. on Bioinformatics and Computational Biology, ACM, Hong Kong, People's Republic of China, 2017, pp. 59–62.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2020.0122
Loading

Related content

content/journals/10.1049/iet-ipr.2020.0122
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading