Mota Ana M, Clarkson Matthew J, Almeida Pedro, Matela Nuno
Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal.
Department of Medical Physics and Biomedical Engineering and the Centre for Medical Image Computing, University College London, London WC1E 6BT, UK.
J Imaging. 2022 Aug 29;8(9):231. doi: 10.3390/jimaging8090231.
Microcalcification clusters (MCs) are among the most important biomarkers for breast cancer, especially in cases of nonpalpable lesions. The vast majority of deep learning studies on digital breast tomosynthesis (DBT) are focused on detecting and classifying lesions, especially soft-tissue lesions, in small regions of interest previously selected. Only about 25% of the studies are specific to MCs, and all of them are based on the classification of small preselected regions. Classifying the whole image according to the presence or absence of MCs is a difficult task due to the size of MCs and all the information present in an entire image. A completely automatic and direct classification, which receives the entire image, without prior identification of any regions, is crucial for the usefulness of these techniques in a real clinical and screening environment. The main purpose of this work is to implement and evaluate the performance of convolutional neural networks (CNNs) regarding an automatic classification of a complete DBT image for the presence or absence of MCs (without any prior identification of regions). In this work, four popular deep CNNs are trained and compared with a new architecture proposed by us. The main task of these trainings was the classification of DBT cases by absence or presence of MCs. A public database of realistic simulated data was used, and the whole DBT image was taken into account as input. DBT data were considered without and with preprocessing (to study the impact of noise reduction and contrast enhancement methods on the evaluation of MCs with CNNs). The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance. Very promising results were achieved with a maximum AUC of 94.19% for the GoogLeNet. The second-best AUC value was obtained with a new implemented network, CNN-a, with 91.17%. This CNN had the particularity of also being the fastest, thus becoming a very interesting model to be considered in other studies. With this work, encouraging outcomes were achieved in this regard, obtaining similar results to other studies for the detection of larger lesions such as masses. Moreover, given the difficulty of visualizing the MCs, which are often spread over several slices, this work may have an important impact on the clinical analysis of DBT images.
微钙化簇（MCs）是乳腺癌最重要的生物标志物之一，尤其是在不可触及病变的情况下。绝大多数关于数字乳腺断层合成（DBT）的深度学习研究都集中在检测和分类先前选定的小感兴趣区域内的病变，特别是软组织病变。只有约25%的研究专门针对MCs，而且所有这些研究都基于对预先选定的小区域进行分类。由于MCs的大小以及整个图像中存在的所有信息，根据MCs的有无对整个图像进行分类是一项艰巨的任务。一种完全自动且直接的分类方法，即接收整个图像而无需事先识别任何区域，对于这些技术在实际临床和筛查环境中的实用性至关重要。这项工作的主要目的是实现并评估卷积神经网络（CNN）在对完整DBT图像进行有无MCs的自动分类方面的性能（无需事先识别区域）。在这项工作中，训练了四种流行的深度CNN，并与我们提出的一种新架构进行比较。这些训练的主要任务是根据有无MCs对DBT病例进行分类。使用了一个真实模拟数据的公共数据库，并将整个DBT图像作为输入。考虑了有无预处理的DBT数据（以研究降噪和对比度增强方法对使用CNN评估MCs的影响）。使用受试者工作特征曲线下面积（AUC）来评估性能。取得了非常有前景的结果，GoogLeNet的最大AUC为94.19%。第二好的AUC值是由新实现的网络CNN-a获得的，为91.17%。这个CNN的特别之处还在于它也是最快的，因此成为其他研究中一个非常值得考虑的有趣模型。通过这项工作，在这方面取得了令人鼓舞的成果，在检测诸如肿块等较大病变方面获得了与其他研究相似的结果。此外，鉴于可视化MCs的难度，MCs通常分布在多个切片上，这项工作可能会对DBT图像的临床分析产生重要影响。
