Background: The integration of artificial intelligence into medicine has led
to significant advances, particularly in diagnostics and treatment planning.
However, the reliability of AI models is highly dependent on the quality of the
training data, especially in medical imaging, where varying patient data and
evolving medical knowledge pose a challenge to the accuracy and
generalizability of given datasets. Results: The proposed approach focuses on
the integration and enhancement of clinical computed tomography (CT) image
series for better findability, accessibility, interoperability, and
reusability. Through an automated indexing process, CT image series are
semantically enhanced using the TotalSegmentator framework for segmentation and
resulting SNOMED CT annotations. The metadata is standardized with HL7 FHIR
resources to enable efficient data recognition and data exchange between
research projects. Conclusions: The study successfully integrates a robust
process within the UKSH MeDIC, leading to the semantic enrichment of over
230,000 CT image series and over 8 million SNOMED CT annotations. The
standardized representation using HL7 FHIR resources improves discoverability
and facilitates interoperability, providing a foundation for the FAIRness of
medical imaging data. However, developing automated annotation methods that can
keep pace with growing clinical datasets remains a challenge to ensure
continued progress in large-scale integration and indexing of medical imaging
for advanced healthcare AI applications.

该研究介绍了一种通过自动索引和语义增强来提高临床 CT 图像系列的可发现性、可访问性、可互操作性和可重用性的方法，使用 HL7 FHIR 资源对元数据进行标准化，以提供医学影像数据的易发现性并促进互操作性，为医疗人工智能应用的大规模集成和索引提供了基础。