# A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification

arXiv: https://arxiv.org/abs/1707.06978 · HTML: https://mlsanity.com/paper/1707.06978/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2017.

## Built on by (most cited first, 17 of 17)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network](https://mlsanity.com/paper/2303.15654/) (2023)
- [No More Sliding Window: Efficient 3D Medical Image Segmentation with Differentiable Top-k Patch Sampling](https://mlsanity.com/paper/2501.10814/) (2025)
- [Multi-task fusion for improving mammography screening data classification](https://mlsanity.com/paper/2112.01320/) (2021)
- [Medical Knowledge-Guided Deep Curriculum Learning for Elbow Fracture Diagnosis from X-Ray Images](https://mlsanity.com/paper/2110.10381/) (2021)
- [GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation](https://mlsanity.com/paper/2501.02598/) (2025)
- [CLOG-CD: Curriculum Learning based on Oscillating Granularity of Class Decomposed Medical Image Classification](https://mlsanity.com/paper/2505.01741/) (2025)
- [AI-based computer-aided diagnostic system of chest digital tomography synthesis: Demonstrating comparative advantage with X-ray-based AI systems](https://mlsanity.com/paper/2206.13504/) (2022)
- [Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills](https://mlsanity.com/paper/2303.15349/) (2023)
- [Putting the Segment Anything Model to the Test with 3D Knee MRI - A Comparison with State-of-the-Art Performance](https://mlsanity.com/paper/2504.13340/) (2025)
- [Independent evaluation of state-of-the-art deep networks for mammography](https://mlsanity.com/paper/2206.12407/) (2022)
- [Human not in the loop: objective sample difficulty measures for Curriculum Learning](https://mlsanity.com/paper/2302.01243/) (2023)
- [Using Weak Supervision and Data Augmentation in Question Answering](https://mlsanity.com/paper/2309.16175/) (2023)
- [Unsupversied feature correlation model to predict breast abnormal variation maps in longitudinal mammograms](https://mlsanity.com/paper/2312.16772/) (2023)
- [CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification](https://mlsanity.com/paper/2510.23442/) (2025)
- [Unsupervised Domain Adaptation for Calcification Classification in Mammography Across Multi-Site Datasets](https://mlsanity.com/paper/2607.06549/) (2026)
- [BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography](https://mlsanity.com/paper/2607.10188/) (2026)

## Abstract (arXiv)

Screening mammography is an important front-line tool for the early detection of breast cancer, and some 39 million exams are conducted each year in the United States alone. Here, we describe a multi-scale convolutional neural network (CNN) trained with a curriculum learning strategy that achieves high levels of accuracy in classifying mammograms. Specifically, we first train CNN-based patch classifiers on segmentation masks of lesions in mammograms, and then use the learned features to initialize a scanning-based model that renders a decision on the whole image, trained end-to-end on outcome data. We demonstrate that our approach effectively handles the "needle in a haystack" nature of full-image mammogram classification, achieving 0.92 AUROC on the DDSM dataset.