A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study

• URL: http://arxiv.org/abs/2504.05636v2
• Date: Fri, 11 Apr 2025 15:53:20 GMT
• Title: A Multi-Modal AI System for Screening Mammography: Integrating 2D and 3D Imaging to Improve Breast Cancer Detection in a Prospective Clinical Study
• Authors: Jungkyu Park, Jan Witowski, Yanqi Xu, Hari Trivedi, Judy Gichoya, Beatrice Brown-Mulry, Malte Westerhoff, Linda Moy, Laura Heacock, Alana Lewin, Krzysztof J. Geras,
• Abstract summary: False-positive recalls remain a concern in breast cancer screening.<n>We developed a multi-modal artificial intelligence system integrating full-field digital mammography and synthetic mammography.<n>Our AI system, trained on approximately 500,000 exams, achieved 0.945 AUROC on an internal test set.
• Score: 2.9992821862882546
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• A Clinician-Friendly Platform for Ophthalmic Image Analysis Without Technical Barriers [51.45596445363302]
  GlobeReady is a clinician-friendly AI platform that enables ocular disease diagnosis without retraining/fine-tuning or technical expertise. It achieves high accuracy across imaging modalities: 93.9-98.5% for an 11-category fundus photo dataset and 87.2-92.7% for a 15-category OCT dataset. It addresses domain shifts across centers and populations, reaching an average accuracy of 88.9% across five centers in China, 86.3% in Vietnam, and 90.2% in the UK.
  arXiv  Detail & Related papers  (2025-04-22T14:17:22Z)
• Multi-modal AI for comprehensive breast cancer prognostication [18.691704371847855]
  We developed a novel artificial intelligence (AI)-based approach that integrates digital pathology with clinical data.<n>The test was developed and evaluated using data from a total of 8,161 female breast cancer patients across 15 cohorts.<n>Our results suggest that our AI test improves upon the accuracy of existing prognostic tests, while being applicable to a wider range of patients.
  arXiv  Detail & Related papers  (2024-10-28T17:54:29Z)
• Enhancing Clinically Significant Prostate Cancer Prediction in T2-weighted Images through Transfer Learning from Breast Cancer [71.91773485443125]
  Transfer learning is a technique that leverages acquired features from a domain with richer data to enhance the performance of a domain with limited data. In this paper, we investigate the improvement of clinically significant prostate cancer prediction in T2-weighted images through transfer learning from breast cancer.
  arXiv  Detail & Related papers  (2024-05-13T15:57:27Z)
• COVID-Net USPro: An Open-Source Explainable Few-Shot Deep Prototypical Network to Monitor and Detect COVID-19 Infection from Point-of-Care Ultrasound Images [66.63200823918429]
  COVID-Net USPro monitors and detects COVID-19 positive cases with high precision and recall from minimal ultrasound images. The network achieves 99.65% overall accuracy, 99.7% recall and 99.67% precision for COVID-19 positive cases when trained with only 5 shots.
  arXiv  Detail & Related papers  (2023-01-04T16:05:51Z)
• High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detection [48.88813637974911]
  Computer-aided detection systems based on deep learning have shown good performance in breast cancer detection. High-density breasts show poorer detection performance since dense tissues can mask or even simulate masses. This study aims to improve the mass detection performance in high-density breasts using synthetic high-density full-field digital mammograms.
  arXiv  Detail & Related papers  (2022-09-20T15:57:12Z)
• A deep learning algorithm for reducing false positives in screening mammography [1.914044679141325]
  This work demonstrates an AI algorithm that reduces false positives by identifying mammograms not suspicious for breast cancer. We trained the algorithm to determine the absence of cancer using 123,248 2D digital mammograms (6,161 cancers) and performed a retrospective study on 14,831 screening exams (1,026 cancers) from 15 US and 3 UK sites.
  arXiv  Detail & Related papers  (2022-04-13T23:37:40Z)
• EMT-NET: Efficient multitask network for computer-aided diagnosis of breast cancer [58.720142291102135]
  We propose an efficient and light-weighted learning architecture to classify and segment breast tumors simultaneously. We incorporate a segmentation task into a tumor classification network, which makes the backbone network learn representations focused on tumor regions. The accuracy, sensitivity, and specificity of tumor classification is 88.6%, 94.1%, and 85.3%, respectively.
  arXiv  Detail & Related papers  (2022-01-13T05:24:40Z)
• Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence [79.038671794961]
  We launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution. Our study is based on 9,573 chest computed tomography scans (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK.
  arXiv  Detail & Related papers  (2021-11-18T00:43:41Z)
• COVID-Net US: A Tailored, Highly Efficient, Self-Attention Deep Convolutional Neural Network Design for Detection of COVID-19 Patient Cases from Point-of-care Ultrasound Imaging [101.27276001592101]
  We introduce COVID-Net US, a highly efficient, self-attention deep convolutional neural network design tailored for COVID-19 screening from lung POCUS images. Experimental results show that the proposed COVID-Net US can achieve an AUC of over 0.98 while achieving 353X lower architectural complexity, 62X lower computational complexity, and 14.3X faster inference times on a Raspberry Pi. To advocate affordable healthcare and artificial intelligence for resource-constrained environments, we have made COVID-Net US open source and publicly available as part of the COVID-Net open source initiative.
  arXiv  Detail & Related papers  (2021-08-05T16:47:33Z)
• Automatic Breast Lesion Detection in Ultrafast DCE-MRI Using Deep Learning [0.0]
  We propose a deep learning-based computer-aided detection (CADe) method to detect breast lesions in ultrafast DCE-MRI sequences. This method uses both the three-dimensional spatial information and temporal information obtained from the early-phase of the dynamic acquisition.
  arXiv  Detail & Related papers  (2021-02-07T22:03:39Z)
• Detection of masses and architectural distortions in digital breast tomosynthesis: a publicly available dataset of 5,060 patients and a deep learning model [4.3359550072619255]
  We have curated and made publicly available a large-scale dataset of digital breast tomosynthesis images. It contains 22,032 reconstructed volumes belonging to 5,610 studies from 5,060 patients. We developed a single-phase deep learning detection model and tested it using our dataset to serve as a baseline for future research.
  arXiv  Detail & Related papers  (2020-11-13T18:33:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.