Artificial intelligence and convolution neural networks assessing mammographic images: a narrative literature review.

Journal: Journal of medical radiation sciences
Published Date: Mar 5, 2020

Abstract

Studies have shown that the use of artificial intelligence can reduce errors in medical image assessment. The diagnosis of breast cancer is an essential task; however, diagnosis can include 'detection' and 'interpretation' errors. Studies to reduce these errors have shown the feasibility of using convolution neural networks (CNNs). This narrative review presents recent studies in diagnosing mammographic malignancy investigating the accuracy and reliability of these CNNs. Databases including ScienceDirect, PubMed, MEDLINE, British Medical Journal and Medscape were searched using the terms 'convolutional neural network or artificial intelligence', 'breast neoplasms [MeSH] or breast cancer or breast carcinoma' and 'mammography [MeSH Terms]'. Articles collected were screened under the inclusion and exclusion criteria, accounting for the publication date and exclusive use of mammography images, and included only literature in English. After extracting data, results were compared and discussed. This review included 33 studies and identified four recurring categories of studies: the differentiation of benign and malignant masses, the localisation of masses, cancer-containing and cancer-free breast tissue differentiation and breast classification based on breast density. CNN's application in detecting malignancy in mammography appears promising but requires further standardised investigations before potentially becoming an integral part of the diagnostic routine in mammography.

Authors

  • Dennis Jay Wong
    Discipline of Medical Imaging Sciences, The University of Sydney, Lidcombe, New South Wales, Australia.
  • Ziba Gandomkar
    Image Optimisation and Perception, Discipline of Medical Imaging and Radiation Sciences, Faculty of Health Sciences, University of Sydney, Sydney, NSW, Australia. Electronic address: ziba.gandomkar@sydney.edu.au.
  • Wan-Jing Wu
    Discipline of Medical Imaging Sciences, The University of Sydney, Lidcombe, New South Wales, Australia.
  • Guijing Zhang
    Discipline of Medical Imaging Sciences, The University of Sydney, Lidcombe, New South Wales, Australia.
  • Wushuang Gao
    Discipline of Medical Imaging Sciences, The University of Sydney, Lidcombe, New South Wales, Australia.
  • Xiaoying He
    Department of Endocrinology, the First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China.
  • Yunuo Wang
    Discipline of Medical Imaging Sciences, The University of Sydney, Lidcombe, New South Wales, Australia.
  • Warren Reed
    Discipline of Medical Imaging Sciences, The University of Sydney, Lidcombe, New South Wales, Australia.

Keywords

External Resources

Popular Topics
Recent Journals