Deep Angular Embedding and Feature Correlation Attention for Breast MRI Cancer Analysis

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.

[1]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[3]  Guang-Zhong Yang,et al.  Small Lesion Classification in Dynamic Contrast Enhancement MRI for Breast Cancer Early Detection , 2018, MICCAI.

[4]  Qi Song,et al.  Integrate Domain Knowledge in Training CNN for Ultrasonography Breast Cancer Diagnosis , 2018, MICCAI.

[5]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Guy Amit,et al.  Hybrid Mass Detection in Breast MRI Combining Unsupervised Saliency Analysis and Deep Learning , 2017, MICCAI.

[7]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[8]  Jiajun Wu,et al.  Deep multiple instance learning for image classification and auto-annotation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Leon A. Gatys,et al.  Texture Synthesis Using Convolutional Neural Networks , 2015, NIPS.

[11]  Guy Amit,et al.  Classification of breast MRI lesions using small-size training sets: comparison of deep learning approaches , 2017, Medical Imaging.

[12]  Maximilian Reiser,et al.  Prospective multicenter cohort study to refine management recommendations for women at elevated familial risk of breast cancer: the EVA trial. , 2010, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[13]  Gustavo Carneiro,et al.  Training Medical Image Analysis Systems like Radiologists , 2018, MICCAI.

[14]  A. Jemal,et al.  Breast cancer statistics, 2017, racial disparity in mortality by state , 2017, CA: a cancer journal for clinicians.

[15]  Xing Ji,et al.  CosFace: Large Margin Cosine Loss for Deep Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Jun Fu,et al.  Dual Attention Network for Scene Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Wentao Zhu,et al.  Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification , 2016 .

[18]  Xiaohui Xie,et al.  Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification , 2016, bioRxiv.