Enterprise imaging company DataFirst has released Silverback HarmoniX, a platform designed to automatically classify, curate, and normalize imaging data to improve hanging protocol performance and enterprise interoperability.
The company is highlighting the platform at the Society for Imaging Informatics in Medicine (SIIM) annual meeting.
Silverback HarmoniX combines protocol-driven clinical logic with computer vision technology to identify anatomy, imaging sequences, study types, and clinical context directly from imaging data, rather than relying solely on text-based DICOM metadata, according to the company. The approach aims to address inconsistent series descriptions and naming conventions that vary across vendors and facilities, which can cause hanging protocols to fail and require radiologists to manually organize studies, DataFirst said.
The platform is part of the firm's Silverback Workflow Engine offerings for enterprise imaging workflow orchestration, DICOM routing, and data migration.
Check out AuntMinnie’s full coverage of SIIM 2026 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.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)
