AstraZeneca has partnered with deep-learning algorithm developer Qure.ai to integrate artificial intelligence (AI) solutions for the early detection of lung cancer.
The partnership is part of AstraZeneca's Emerging Markets Health Innovation Hubs program. AstraZeneca will employ Qure.ai's solutions in the company's Emerging Markets region that spans Latin America, Asia, the Middle East, and Africa.
The collaboration will scale the use of Qure.ai's qXR tool, which automatically detects and localizes anomalies on chest radiographs, including those that could indicate lung cancer. The qXR tool has received the CE Mark and can detect lung cancer nodules from chest radiographs, according to the firm.
AstraZeneca's Emerging Markets Health Innovation Hubs will also work with Qure.ai to explore additional applications that leverage AI to identify and refer patients with radiographic lung abnormalities to specialists. Ultimately, the partnership aims to improve referral and diagnostic pathways for patients with possible lung cancers and to increase lung cancer detection at an earlier stage.
![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.auntminnie.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)
