DICOM Structured Report Extraction via Intermediary OLAP Bridge
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
DICOM Structured Reports (DSRs) stored in Picture Archiving and Communications Systems (PACS) are not readily queryable using conventional data mining tools due to their proprietary and unstructured formats, making it difficult to extract and analyze medical data effectively.
Innovation Solution
The system and method for extracting values from DSRs involve generating criteria to locate specific nodes within the reports, processing these values, and applying rules to determine additional values, which are then stored and queried using OLAP tools to generate reports, enabling efficient data mining and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If DICOM Structured Reports are stored in proprietary PACS formats, then data storage is standardized for medical imaging, but data querying and analysis become difficult
Solution Approach 1:
The patent introduces an intermediary system that acts as a bridge between the proprietary PACS storage format and standard data querying tools. This intermediary extracts data from DSR objects stored in PACS, transforms it into a queryable format, and enables analysis without requiring changes to the original storage system. The intermediary layer resolves the contradiction by maintaining storage standardization while adding querying capability.
Solution Approach 2:
The system segments the data extraction and querying process into distinct components: (1) extraction of data from DSR objects in PACS, (2) transformation of extracted data into structured formats, and (3) enabling querying through OLAP tools. This segmentation allows each component to be optimized independently, maintaining storage integrity while improving data accessibility.
2Device complexity
If conventional data mining tools are used directly on DSRs, then tool simplicity is maintained, but data extraction efficiency deteriorates
Solution Approach 1:
The system performs preliminary data extraction and transformation before the actual data mining operation. By pre-processing DSR data into a queryable format and storing it in an accessible structure, the system enables conventional data mining tools to operate efficiently on already-prepared data, rather than requiring them to directly parse complex DSR formats.
3Reliability
If DSR data remains in unstructured proprietary format, then storage fidelity is preserved, but data analysis capability is reduced
Solution Approach 1:
The system creates copies of data from DSR objects and transforms these copies into queryable formats, while the original DSR data remains intact in PACS storage. This copying approach preserves storage fidelity of the original data while enabling analysis through transformed copies, eliminating the need to choose between fidelity and accessibility.
Data Source
AI summary
Described are techniques for extracting information from DICOM structured reports by applying criteria to the reports to locate values at particular nodes and extract the values into a data structure. One or more rules may be applied to determine additional values based on the extracted values. One or more of the extracted values or additional values may be queried, indexed, aggregated, and stored for searching, access, report generation, and so forth.