# Classifying Symmetrical Differences and Temporal Change in Mammography Using Deep Neural Networks

arXiv: https://arxiv.org/abs/1703.07715 · HTML: https://mlsanity.com/paper/1703.07715/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2017.

## Built on by (most cited first, 5 of 5)

- [Attention-Map Augmentation for Hypercomplex Breast Cancer Classification](https://mlsanity.com/paper/2310.07633/) (2023)
- [RADIFUSION: A multi-radiomics deep learning based breast cancer risk prediction model using sequential mammographic images with image attention and bilateral asymmetry refinement](https://mlsanity.com/paper/2304.00257/) (2023)
- [Multi-task fusion for improving mammography screening data classification](https://mlsanity.com/paper/2112.01320/) (2021)
- [Unsupversied feature correlation model to predict breast abnormal variation maps in longitudinal mammograms](https://mlsanity.com/paper/2312.16772/) (2023)
- [MammoTracker: Mask-Guided Lesion Tracking in Temporal Mammograms](https://mlsanity.com/paper/2507.00328/) (2025)

## Abstract (arXiv)

We investigate the addition of symmetry and temporal context information to a deep Convolutional Neural Network (CNN) with the purpose of detecting malignant soft tissue lesions in mammography. We employ a simple linear mapping that takes the location of a mass candidate and maps it to either the contra-lateral or prior mammogram and Regions Of Interest (ROI) are extracted around each location. We subsequently explore two different architectures (1) a fusion model employing two datastreams were both ROIs are fed to the network during training and testing and (2) a stage-wise approach where a single ROI CNN is trained on the primary image and subsequently used as feature extractor for both primary and symmetrical or prior ROIs. A 'shallow' Gradient Boosted Tree (GBT) classifier is then trained on the concatenation of these features and used to classify the joint representation. Results shown a significant increase in performance using the first architecture and symmetry information, but only marginal gains in performance using temporal data and the other setting. We feel results are promising and can greatly be improved when more temporal data becomes available.