AI-enabled DICOM data migration helps to streamline healthcare data

In the process of AI-enabled DICOM data migration, the steps of data extraction, normalisation and cleaning are essential to ensure that the new system is ready to operate with the best possible data quality. Software company Enlitic says that the journey begins with the extraction of data, where it is important to normalise DICOM files. Ideally, all PACS and VNAs should operate on the same regulated and approved DICOM formatting. However, due to the complexity of DICOM tags – some images can have more than 10,000 tags – errors can occur. Newer systems are more DICOM-compliant and less tolerant of non-compliant data, making normalisation a vital step, Enlitic points out.

To address these challenges, LAITEK performs a comprehensive check against the most common DICOM errors to correct and normalise the data before processing it further. This includes a seven-point data check that scans for inconsistencies between RIS and DICOM files. This process helps prevent data loss or incorrect categorisation during migration, especially when patient information has changed over time. In cases where studies cannot be reconciled, LAITEK places the files into an archive server (ATRIUM) for the client to review. This step ensures that all data is thoroughly examined before proceeding to the next stage.

The final stage before migration involves localising data, a necessity because old and new systems may handle data differently. LAITEK works with clients to understand how their new system operates. Real-world examples illustrate the benefits of AI in data migration. For instance, St Francis Hospital, Evanston, Illinois, had to adjust its patient IDs from a 12-digit alphanumeric format to the 16-digit numeric format used by Advocate. AI helped reconcile these differences.

Localisation also involves updating outdated terminology to maintain consistency between old and new studies. For instance, an order for a chest x-ray might have been coded as Chest PA Lat but is now coded as Chest 2 Views. By updating such terms, LAITEK ensures studies can be found by technicians using current terminology. AI automates manual tasks at scale with minimal human involvement, improves data quality by ensuring it is correct and consistently labelled and reduces costs by lowering the time required for migration and system configuration.

By eliminating inconsistencies and errors, tools like ENDEX enhance the overall quality and reliability of clinical data, says Enlitic. It facilitates seamless information exchange between different healthcare systems and institutions.

Read this report on page 20 of the May 2025 issue of RAD Magazine.