A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910908846964736 |
|---|---|
| author | Park, Jungkyu Witowski, Jan Xu, Yanqi Trivedi, Hari Gichoya, Judy Brown-Mulry, Beatrice Westerhoff, Malte Moy, Linda Heacock, Laura Lewin, Alana Geras, Krzysztof J. |
| author_facet | Park, Jungkyu Witowski, Jan Xu, Yanqi Trivedi, Hari Gichoya, Judy Brown-Mulry, Beatrice Westerhoff, Malte Moy, Linda Heacock, Laura Lewin, Alana Geras, Krzysztof J. |
| contents | Although digital breast tomosynthesis (DBT) improves diagnostic performance over full-field digital mammography (FFDM), false-positive recalls remain a concern in breast cancer screening. We developed a multi-modal artificial intelligence system integrating FFDM, synthetic mammography, and DBT to provide breast-level predictions and bounding-box localizations of suspicious findings. Our AI system, trained on approximately 500,000 mammography exams, achieved 0.945 AUROC on an internal test set. It demonstrated capacity to reduce recalls by 31.7% and radiologist workload by 43.8% while maintaining 100% sensitivity, underscoring its potential to improve clinical workflows. External validation confirmed strong generalizability, reducing the gap to a perfect AUROC by 35.31%-69.14% relative to strong baselines. In prospective deployment across 18 sites, the system reduced recall rates for low-risk cases. An improved version, trained on over 750,000 exams with additional labels, further reduced the gap by 18.86%-56.62% across large external datasets. Overall, these results underscore the importance of utilizing all available imaging modalities, demonstrate the potential for clinical impact, and indicate feasibility of further reduction of the test error with increased training set when using large-capacity neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05636 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study Park, Jungkyu Witowski, Jan Xu, Yanqi Trivedi, Hari Gichoya, Judy Brown-Mulry, Beatrice Westerhoff, Malte Moy, Linda Heacock, Laura Lewin, Alana Geras, Krzysztof J. Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Although digital breast tomosynthesis (DBT) improves diagnostic performance over full-field digital mammography (FFDM), false-positive recalls remain a concern in breast cancer screening. We developed a multi-modal artificial intelligence system integrating FFDM, synthetic mammography, and DBT to provide breast-level predictions and bounding-box localizations of suspicious findings. Our AI system, trained on approximately 500,000 mammography exams, achieved 0.945 AUROC on an internal test set. It demonstrated capacity to reduce recalls by 31.7% and radiologist workload by 43.8% while maintaining 100% sensitivity, underscoring its potential to improve clinical workflows. External validation confirmed strong generalizability, reducing the gap to a perfect AUROC by 35.31%-69.14% relative to strong baselines. In prospective deployment across 18 sites, the system reduced recall rates for low-risk cases. An improved version, trained on over 750,000 exams with additional labels, further reduced the gap by 18.86%-56.62% across large external datasets. Overall, these results underscore the importance of utilizing all available imaging modalities, demonstrate the potential for clinical impact, and indicate feasibility of further reduction of the test error with increased training set when using large-capacity neural networks. |
| title | A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2504.05636 |