The ESR and Cancer Image Europe (EUCAIM) have issued a document called "Advancing Precision Medicine for Europe's Cancer Patients with AI-powered Imaging." Prof. Regina Beets-Tan, Prof. Luis Martí-Bonmatí, and others have welcomed the publication.
The document is the result of an ESR-led Thematic Network on the EU Health Policy Platform (EUHPP) and was presented at the EUHPP annual meeting last November. It covers aspects such as literature review and validation, in-vivo clinical trials and screening, interdisciplinary collaboration, research strategy development, data quality and accessibility, regulatory compliance, and trust-building and safety related to AI.
Endorsers of the document include European medical/scientific societies, cancer centers and universities, patient organizations, national radiology societies, industry associations, and AI companies, according to the ESR.
“It is heartening to see that not only numerous ESR national and subspecialties & allied sciences member societies, the ESR Patient Advisory Group, and the ESR’s European Imaging Biomarkers Alliance (EIBALL) endorsed the joint statement, but also a diverse range of other actors involved in cancer care,” noted Prof. Regina Beets-Tan, Director of Imaging Innovation Research at Netherlands Cancer Institute and former ESR President, on behalf of the Thematic Network’s core team.
“By endorsing the joint statement, you have expressed your commitment to contribute to the full implementation of Europe’s Beating Cancer Plan – in particular its flagship project EUCAIM, the EU Cancer Mission, and the EU’s digital health policies”, Prof. Luis Martí-Bonmatí, EUCAIM Scientific Coordinator, added.
To read the document, go to https://health.ec.europa.eu/document/download/6e4f5ecb-ea9c-445a-a661-7147809aa255_en?filename=policy_20241126_js02_en.pdf.
For details on the EUHPP annual meeting, go to https://health.ec.europa.eu/events/eu-health-policy-platform-annual-meeting-2024-11-26_en.
![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)
