The European Institute for Biomedical Imaging Research (EIBIR) has begun curating a large-scale dataset of breast images to facilitate AI development and testing.
Funded with nearly €3.7 million from the EU, the project called BreastSCan will draw data from 19 scientific partners in nine member states. The project launched on 1 September and will start with a specific focus on gathering data from over 7,500 proven breast cancer cases and include mammograms, ultrasound, and MRI scans, according to EIBIR.
EIBIR highlighted five objectives of BreastSCan, noting that the scheme both aligns with the European Health Data Space and will directly contribute to the Cancer Image Europe platform, an initiative under the broader European Cancer Imaging Initiative.
The goals include establishing a pan-European platform specifically for advanced AI-based breast cancer screening; training and validating AI tools for various clinical applications, including image preprocessing and quality assessment, breast cancer risk stratification, lesion detection and characterization, and breast density classification; and AI literacy.
"BreastSCan will pave the way for AI to be seamlessly integrated into breast cancer screening, supporting healthcare professionals and ultimately improving outcomes for patients," the institute said.
Read more about BreastSCan here.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=100&q=70&w=100)
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
