As sensitive healthcare data get distributed throughout and beyond the enterprise, unauthorized access, eavesdropping, masquerading, intrusion, and data integrity become more of a concern.Although ongoing research has sought to solve these security
As sensitive healthcare data get distributed throughout and beyond the enterprise, unauthorized access, eavesdropping, masquerading, intrusion, and data integrity become more of a concern.
Although ongoing research has sought to solve these security issues, these efforts so far have been in isolation, according to Vijay Kallepalli, a computer scientist at the University of Manitoba in Canada.
"To our knowledge, there is no evidence of work that studies the overall security components required for sharing radiology data and how these can be used together without degrading performance, scalability, and fault tolerance," Kallepalli said.
Some security architectures have been designed for hospitals, but these are restricted to sharing data within a single enterprise. Although existing technology to interconnect hospitals permits data sharing, some healthcare institutions are reluctant to share medical data because of the lack of proper security infrastructure.
To meet the need for broader and more comprehensive security measures, researchers at Manitoba configured a scalable, fault-tolerant, and well-performing security infrastructure for sharing DICOM images for distributed environments beyond the single enterprise. Hospitals can use it as a blueprint for sharing radiology data.
The model provides fine-grained access control, policy management, demographics filtering, log maintenance, and auditing constrained to the Canadian-Manitoban Personal Health Information Act (PHIA) of 1999, according to Kallepalli. PHIA is similar to the Health Insurance Portability and Accountability Act (HIPAA) in the U.S.
In the Manitoba prototype, an authentication engine performs user validation, an authorization engine provides access control, a log maintenance engine maintains log data, and a filtering engine replaces the demographics embedded in DICOM images with dummy values.
The model uses SSL (secure sockets layer, a protocol designed to provide secure communications on the Internet) for communication between client and security nodes to protect data from eavesdropping and to ensure data integrity.
"Our work is specific to radiology data, where the DICOM standard is used for communication," Kallepalli said.
DICOM Work Group-14 provides mechanisms for applications to perform integrity checks, secure authentication, and secure transmission of data. But the group defers access control, log maintenance, and auditing for future consideration.
Study: AI Bolsters Sensitivity for Pneumothorax on CXR and Significantly Reduces Reporting Time
October 30th 2024For clinically actionable pneumothorax, an artificial intelligence algorithm demonstrated a 93 percent AUC and a 96 percent specificity rate in a study involving chest X-rays from over 27,000 adults.
AI Segmentation, Intraprostatic Tumor Volume and Metastases: What a New mpMRI Study Reveals
October 29th 2024For patients who received radiotherapy for localized prostate cancer, total intraprostatic tumor volume derived from AI segmentation had a 10 percent higher AUC for predicting seven-year metastases in comparison to a risk model from the National Comprehensive Cancer Network (NCCN).