GE HealthCare has launched its deep learning (DL)-enabled CleaRecon DL to improve the quality of conebeam CT (CBCT) images.
The system is designed to remove streak artifacts caused by pulsating blood flow in the arteries and changes in contrast distribution during CBCT image acquisitions in the liver, prostate, brain, and endovascular aortic repair procedures.
Images compare CBCT liver images with and without the CleaRecon DL system.GE HealthCare
CleaRecon DL recently received 510(k) clearance from the U.S. Food and Drug Administration (FDA) and CE marking. It will be available for use on the Allia platform, the company added.
CleaRecon DL uses deep learning algorithms that are designed to provide clearer and more accurate imaging. GE HealthCare said that during clinical validation testing, a recent survey noted that in 98% of cases, CBCT images reconstructed with CleaRecon DL are clearer than conventional CBCT images.
CleaRecon DL is available in the U.S. and the European Union. It will be showcased on the Allia platform at the Global Embolization Symposium & Technologies (GEST) 2025 annual meeting from May 15 to 18 in New York.
![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)
