Artificial intelligence and convolution neural networks assessing mammographic images: a narrative literature review. Issue 2 (5th March 2020)

• Record Type: Journal Article
• Authors: Wong, Dennis Jay; Gandomkar, Ziba; Wu, Wan‐Jing; Zhang, Guijing; Gao, Wushuang; He, Xiaoying; Wang, Yunuo; Reed, Warren
• Is Part Of: Journal of medical radiation sciences. Volume 67:Issue 2(2020:Jun.)
• Page Start: 134
• Page End: 142
• Publication Date: 2020-03-05
• Subjects: Artificial intelligence -- breast cancer -- breast density -- convolutional neural network -- mammography; Radiology, Medical -- Periodicals; Radiology, Medical -- Australia -- Periodicals; Radiology, Medical -- New Zealand -- Periodicals; Radiotherapy -- Periodicals; Diagnostic imaging -- Periodicals; 616
• DOI: 10.1002/jmrs.385
• Languages: English
• ISSNs: 2051-3895

Abstract

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. Abstract : This article explores the current research and developments in using convolutional neural networks for mammography diagnosis. Current developments are focused on four distinct categories; however, limitations of this artificial intelligence withhold it from clinical implementation.