# Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification

arXiv: https://arxiv.org/abs/2009.14406 · HTML: https://mlsanity.com/paper/2009.14406/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [DisAsymNet: Disentanglement of Asymmetrical Abnormality on Bilateral Mammograms using Self-adversarial Learning](https://mlsanity.com/paper/2307.02935/) (2023)
- [Clinical Inspired MRI Lesion Segmentation](https://mlsanity.com/paper/2502.16032/) (2025)
- [Semi- and Weakly-Supervised Learning for Mammogram Mass Segmentation with Limited Annotations](https://mlsanity.com/paper/2403.09315/) (2024)
- [MAMBO-NET: Multi-Causal Aware Modeling Backdoor-Intervention Optimization for Medical Image Segmentation Network](https://mlsanity.com/paper/2505.21874/) (2025)
- [TACE: Tumor-Aware Counterfactual Explanations](https://mlsanity.com/paper/2409.13045/) (2024)
- [Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis](https://mlsanity.com/paper/2605.26483/) (2026)

## Abstract (arXiv)

Mammogram benign or malignant classification with only image-level labels is challenging due to the absence of lesion annotations. Motivated by the symmetric prior that the lesions on one side of breasts rarely appear in the corresponding areas on the other side, given a diseased image, we can explore a counterfactual problem that how would the features have behaved if there were no lesions in the image, so as to identify the lesion areas. We derive a new theoretical result for counterfactual generation based on the symmetric prior. By building a causal model that entails such a prior for bilateral images, we obtain two optimization goals for counterfactual generation, which can be accomplished via our newly proposed counterfactual generative network. Our proposed model is mainly composed of Generator Adversarial Network and a prediction feedback mechanism, they are optimized jointly and prompt each other. Specifically, the former can further improve the classification performance by generating counterfactual features to calculate lesion areas. On the other hand, the latter helps counterfactual generation by the supervision of classification loss. The utility of our method and the effectiveness of each module in our model can be verified by state-of-the-art performance on INBreast and an in-house dataset and ablation studies.