# M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector

arXiv: https://arxiv.org/abs/2308.06420 · HTML: https://mlsanity.com/paper/2308.06420/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 11 Aug 2023.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization](https://mlsanity.com/paper/2002.07613/) (2020)
- [OPTIMAM Mammography Image Database: a large scale resource of mammography images and clinical data](https://mlsanity.com/paper/2004.04742/) (2020)
- [Multi-view analysis of unregistered medical images using cross-view transformers](https://mlsanity.com/paper/2103.11390/) (2021)
- [Robust breast cancer detection in mammography and digital breast tomosynthesis using annotation-efficient deep learning approach](https://mlsanity.com/paper/1912.11027/) (2019)
- [Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection](https://mlsanity.com/paper/2105.10160/) (2021)
- [Cross-view Relation Networks for Mammogram Mass Detection](https://mlsanity.com/paper/1907.00528/) (2019)
- [Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection](https://mlsanity.com/paper/2209.05809/) (2022)
- [A Two-Stage Multiple Instance Learning Framework for the Detection of Breast Cancer in Mammograms](https://mlsanity.com/paper/2004.11726/) (2020)
- [A deep learning algorithm for reducing false positives in screening mammography](https://mlsanity.com/paper/2204.06671/) (2022)
- [Deep is a Luxury We Don't Have](https://mlsanity.com/paper/2208.06066/) (2022)

## Built on by (most cited first, 2 of 2)

- [Random Token Fusion for Multi-View Medical Diagnosis](https://mlsanity.com/paper/2410.15847/) (2024)
- [From 2D to 3D Without Extra Baggage: Data-Efficient Cancer Detection in Digital Breast Tomosynthesis](https://mlsanity.com/paper/2511.10597/) (2025)

## Abstract (arXiv)

Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike natural images, a malignant mammogram typically contains only one malignant finding; (2) mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment; (3) most mammograms are negative and do not contain any findings. In this work, we tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; (3) incorporating multi-instance learning (MIL) to train with unannotated images and perform breast-level classification. The resulting model, M&M, is a Multi-view and Multi-instance learning system that can both localize malignant findings and provide breast-level predictions. We validate M&M's detection and classification performance using five mammography datasets. In addition, we demonstrate the effectiveness of each proposed component through comprehensive ablation studies.