# Adaptation of a deep learning malignancy model from full-field digital mammography to digital breast tomosynthesis

arXiv: https://arxiv.org/abs/2001.08381 · HTML: https://mlsanity.com/paper/2001.08381/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2020.

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

- [Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentation](https://mlsanity.com/paper/2107.04914/) (2021)
- [CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis](https://mlsanity.com/paper/2407.17620/) (2024)
- [A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study](https://mlsanity.com/paper/2504.05636/) (2025)
- [An efficient deep neural network to find small objects in large 3D images](https://mlsanity.com/paper/2210.08645/) (2022)
- [From 2D to 3D Without Extra Baggage: Data-Efficient Cancer Detection in Digital Breast Tomosynthesis](https://mlsanity.com/paper/2511.10597/) (2025)

## Abstract (arXiv)

Mammography-based screening has helped reduce the breast cancer mortality rate, but has also been associated with potential harms due to low specificity, leading to unnecessary exams or procedures, and low sensitivity. Digital breast tomosynthesis (DBT) improves on conventional mammography by increasing both sensitivity and specificity and is becoming common in clinical settings. However, deep learning (DL) models have been developed mainly on conventional 2D full-field digital mammography (FFDM) or scanned film images. Due to a lack of large annotated DBT datasets, it is difficult to train a model on DBT from scratch. In this work, we present methods to generalize a model trained on FFDM images to DBT images. In particular, we use average histogram matching (HM) and DL fine-tuning methods to generalize a FFDM model to the 2D maximum intensity projection (MIP) of DBT images. In the proposed approach, the differences between the FFDM and DBT domains are reduced via HM and then the base model, which was trained on abundant FFDM images, is fine-tuned. When evaluating on image patches extracted around identified findings, we are able to achieve similar areas under the receiver operating characteristic curve (ROC AUC) of ~ 0.9 for FFDM and ~ 0.85 for MIP images, as compared to a ROC AUC of ~ 0.75 when tested directly on MIP images.