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

TL;DR

This paper introduces a deep learning approach for breast MRI analysis that combines angular feature embedding with correlation-based attention to improve tumor classification and localization accuracy.

Contribution

It proposes a novel Cosine Margin Sigmoid Loss for better feature separation and a correlation attention map for accurate lesion localization using only image-level labels.

Findings

Achieved 85.5% classification accuracy and 0.902 AUC on breast MRI data.

Outperformed existing methods in tumor localization accuracy.

Utilized the largest breast cancer MRI dataset with over 10,000 scans.

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.