COIN: Contrastive Identifier Network for Breast Mass Diagnosis in Mammography

TL;DR

The paper introduces COIN, a deep learning framework that enhances breast mass diagnosis in mammography by using adversarial augmentation and contrastive learning to improve discriminativity despite data scarcity and entanglement.

Contribution

It presents a novel contrastive loss with a Signed graph and integrates adversarial augmentation to improve mammography diagnosis accuracy.

Findings

Achieves 93.4% accuracy in breast mass classification.

Attains 95.0% AUC score, outperforming state-of-the-art methods.

Effectively handles data scarcity and entanglement issues.

Abstract

Computer-aided breast cancer diagnosis in mammography is a challenging problem, stemming from mammographical data scarcity and data entanglement. In particular, data scarcity is attributed to the privacy and expensive annotation. And data entanglement is due to the high similarity between benign and malignant masses, of which manifolds reside in lower dimensional space with very small margin. To address these two challenges, we propose a deep learning framework, named Contrastive Identifier Network (\textsc{COIN}), which integrates adversarial augmentation and manifold-based contrastive learning. Firstly, we employ adversarial learning to create both on- and off-distribution mass contained ROIs. After that, we propose a novel contrastive loss with a built Signed graph. Finally, the neural network is optimized in a contrastive learning manner, with the purpose of improving the deep model's discriminativity on the extended dataset. In particular, by employing COIN, data samples from the same category are pulled close whereas those with different labels are pushed further in the deep latent space. Moreover, COIN outperforms the state-of-the-art related algorithms for solving breast cancer diagnosis problem by a considerable margin, achieving 93.4\% accuracy and 95.0\% AUC score. The code will release on ***.