Discipline of Medical Imaging Sciences, The University of Sydney, Lidcombe, New South Wales, Australia.
J Med Radiat Sci. 2020 Jun;67(2):134-142. doi: 10.1002/jmrs.385. Epub 2020 Mar 5.
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.
研究表明，人工智能的使用可以减少医学图像评估中的错误。乳腺癌的诊断是一项基本任务；然而，诊断可能包括“检测”和“解释”错误。为了减少这些错误，已经进行了使用卷积神经网络（CNN）的可行性研究。本叙述性综述介绍了最近在诊断乳腺恶性肿瘤方面的研究，调查了这些 CNN 的准确性和可靠性。使用术语“卷积神经网络或人工智能”、“乳腺肿瘤[MeSH]或乳腺癌或乳腺癌”和“乳腺摄影[MeSH 术语]”在 ScienceDirect、PubMed、MEDLINE、英国医学杂志和 Medscape 等数据库中进行了搜索。根据纳入和排除标准筛选收集的文章，考虑到出版日期和仅使用乳腺摄影图像的排他性，并仅包括英文文献。提取数据后，对结果进行了比较和讨论。本综述共纳入 33 项研究，确定了四个重复的研究类别：良性和恶性肿块的区分、肿块的定位、包含癌症和无癌症的乳腺组织区分以及基于乳腺密度的乳腺分类。CNN 在乳腺摄影中检测恶性肿瘤的应用似乎很有前景，但需要进一步的标准化研究，才能有可能成为乳腺摄影诊断常规的一个组成部分。
