Abstract
Accurate and automatic analysis of breast MRI plays an important role in early diagnosis and successful treatment planning for breast cancer. Due to the heterogeneity nature, accurate diagnosis of tumors remains a challenging task. In this paper, we propose to identify breast tumor in MRI by Cosine Margin Sigmoid Loss (CMSL) with deep learning (DL) and localize possible cancer lesion by COrrelation Attention Map (COAM) based on the learned features. The CMSL embeds tumor features onto a hypersphere and imposes a decision margin through cosine constraints. In this way, the DL model could learn more separable inter-class features and more compact intra-class features in the angular space. Furthermore, we utilize the correlations among feature vectors to generate attention maps that could accurately localize cancer candidates with only image-level label. We build the largest breast cancer dataset involving 10,290 DCE-MRI scan volumes for developing and evaluating the proposed methods. The model driven by CMSL achieved classification accuracy of 0.855 and AUC of 0.902 on the testing set, with sensitivity and specificity of 0.857 and 0.852, respectively, outperforming other competitive methods overall. In addition, the proposed COAM accomplished more accurate localization of the cancer center compared with other state-of-the-art weakly supervised localization method.
Abstract (translated)
乳腺MRI的准确、自动分析对乳腺癌的早期诊断和成功的治疗规划具有重要意义。由于肿瘤的异质性，精确诊断仍然是一项具有挑战性的任务。本文提出了利用余弦边缘-乙状结肠丢失（CMSL）和深度学习（DL）来鉴别MRI中的乳腺肿瘤，并根据所学特征，利用相关注意图（COAM）来定位可能的肿瘤病变。CMSL将肿瘤特征嵌入到超球体中，并通过余弦约束施加决策边界。这样，DL模型可以在角空间中学习到更多的可分离类间特征和更紧凑的类内特征。此外，我们利用特征向量之间的相关性来生成注意力地图，该地图可以精确地定位仅带有图像级标签的癌症候选对象。我们建立了最大的乳腺癌数据集，涉及10290个DCE-MRI扫描量，用于开发和评估所提出的方法。CMSL驱动的模型在测试集上实现了0.855和0.902的分类精度，灵敏度和特异性分别为0.857和0.852，总体上优于其他竞争方法。此外，与其他最先进的弱监督定位方法相比，本文提出的COAM实现了更精确的癌症中心定位。
URL
https://arxiv.org/abs/1906.02999
