Canadian Association of Radiologists White Paper on De-Identification of Medical Imaging: Part 1, General Principles.

The application of big data, radiomics, machine learning, and artificial intelligence (AI) algorithms in radiology requires access to large data sets containing personal health information. Because machine learning projects often require collaboration between different sites or data transfer to a third party, precautions are required to safeguard patient privacy. Safety measures are required to prevent inadvertent access to and transfer of identifiable information. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI Ethical and Legal standing committee with the mandate to guide the medical imaging community in terms of best practices in data management, access to health care data, de-identification, and accountability practices. Part 1 of this article will inform CAR members on principles of de-identification, pseudonymization, encryption, direct and indirect identifiers, k-anonymization, risks of reidentification, implementations, data set release models, and validation of AI algorithms, with a view to developing appropriate standards to safeguard patient information effectively.

Canadian Association of Radiologists White Paper on De-identification of Medical Imaging: Part 2, Practical Considerations.

The application of big data, radiomics, machine learning, and artificial intelligence (AI) algorithms in radiology requires access to large data sets containing personal health information. Because machine learning projects often require collaboration between different sites or data transfer to a third party, precautions are required to safeguard patient privacy. Safety measures are required to prevent inadvertent access to and transfer of identifiable information. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI Ethical and Legal standing committee with the mandate to guide the medical imaging community in terms of best practices in data management, access to health care data, de-identification, and accountability practices. Part 2 of this article will inform CAR members on the practical aspects of medical imaging de-identification, strengths and limitations of de-identification approaches, list of de-identification software and tools available, and perspectives on future directions.

Identifying Institutional Diagnostic Reference Levels for CT with Radiation Dose Index Monitoring Software.

PURPOSE: To retrospectively evaluate radiation optimization efforts over 4 years for three computed tomography (CT) protocols and to determine institutional (local) diagnostic reference levels for prospective tracking by using automated radiation dose index monitoring software. MATERIALS AND METHODS: Approval for this retrospective observational study was obtained from the hospital research ethics board, and the need to obtain informed consent was waived. The study followed a 48-month radiation dose optimization effort in a large academic inner-city trauma and quaternary referral center. Exposure according to equipment, protocol, and year (2010-2013) for adult patients was determined for routine unenhanced head CT examinations, CT pulmonary angiography examinations, and CT examinations for renal colic. Mean exposure (as volume CT dose index [CTDIvol] and dose-length product [DLP]) was averaged to establish local diagnostic reference levels. Means and 75th percentiles for 2013 were compared with findings from surveys in Canada and diagnostic reference levels for similar protocol types internationally. Student t tests were performed to assess significance between annual means, and χ(2) tests were performed for changes in categoric variables. RESULTS: There were 36 996 examinations in 25 234 patients. There was an average exposure reduction of 22% for CTDIvol and 13% for DLP from 2010 to 2013. In 2013, mean CTDIvol for routine head examinations was 50.8 mGy ± 3.7 (standard deviation), 11.8 mGy ± 5.6 for CT pulmonary angiography examinations, and 10.2 mGy ± 4.2 for renal colic CT examinations, while mean DLP was 805.7 mGy · cm ± 124.3, 432.8 mGy-cm ± 219.9, and 469.4 mGy · cm ± 209.2, respectively. The mean CTDIvol and DLP in 2013 were at or close to identified reference values; however, additional optimization is required to reach "as low as reasonably achievable" values for all examinations. CONCLUSION: Automated methods of radiation dose data collection permit a detailed analysis of radiation dose according to protocol and equipment over time. Radiation dose optimization measures were effective, but their full value may be realized only with changes in internal processes and real-time, prospective data monitoring and analysis.

Variation in the utilization and positivity rates of CT pulmonary angiography among emergency physicians at a tertiary academic emergency department.

We examined the patient and physician characteristics related to the use and yield of computed tomography pulmonary angiogram (CTPA) for the diagnosis of pulmonary embolism (PE) at a tertiary academic hospital emergency department (ED). A cross-sectional retrospective study was conducted on 835 consecutive ED patients with suspected PE who underwent CTPA. Radiology report data were extracted from our institution's RIS PACS software (Syngo Imaging, Siemens) based on a targeted search of all CTPA reports from 2010 to 2012. Utilization and PE positivity rates of CTPA were calculated and correlated with patient characteristics including age and gender, as well as emergency physician (EP) characteristics including gender, years in practice, and training certification. Acute PE was diagnosed in 17.8 % of patients. A further 32.9 % of the scans were negative for PE but had other clinically significant findings. We found higher utilization rates in female and older patients (p < 0.001), however, without corresponding differences in PE positivity rates compared to their male and younger counterparts. There was a high inter-physician variation in CTPA utilization rate (range 0.21-0.77 scans per 100 patients seen) and PE positivity rate (range 6.7-38.9 %). However, neither rates correlated with EP years of experience (p > 0.15 with cut-offs at 5, 10, and 20 years post-residency), gender (p = 0.59), or training certification (p = 0.56 between EPs certified by the 5-year program of the Royal College of Physicians of Canada versus the 3-year program of the College of Family Physicians of Canada). Our study demonstrated considerable inter-physician variability in the utilization and PE positivity rates of CTPA. These results suggest an opportunity for a more standardized approach to the use of CTPA among EPs at our institution.

The use of postoperative bone scintigraphy to predict graft retention.

BACKGROUND: Osteonecrosis of the femoral head commonly occurs in patients aged under 50 years. Because of a high rate of complications associated with joint replacement surgery in this population, surgical techniques, such as vascularized fibular grafting, have been devised in an attempt to salvage the femoral head. The purpose of this study was to investigate the use of bone scintigraphy to predict graft retention after vascularized fibular grafting for osteonecrosis of the hip. METHODS: We evaluated single photon emission computed tomography images from 104 subjects whose hips were treated with vascularized fibular grafts between 1994 and 2000. We compared the signal intensity of the graft with the intensity of the ipsilateral proximal femoral diaphysis and assigned a score of 1 if less than diaphysis, 2 if equal to diaphysis and 3 if greater than diaphysis. We defined graft failure as conversion to or on the waiting list for total hip arthroplasty. RESULTS: Thirty percent of hips failed treatment (n = 31, mean graft survival 34.9 mo), while 70% of grafts were retained (n = 73, mean follow-up 56.6 mo). Bone scan scores were significantly lower in the failed group (mean 7.1, range 6-12), compared with the retained group (mean 8.5, range 6-18; p = 0.03). Logistic regression demonstrated that a bone scan score > 6 was associated with graft retention (p = 0.028), with an odds ratio of 3.08 (range 1.13-8.40). CONCLUSION: These results suggest that having a well-perfused graft in the early postoperative period improves the chances of graft retention in the future.